jerry

Forces creation of a PLAN.md file before implementation begins.

Automates the release preparation and CI/CD handoff process.

Strategy Executor agent — loads and executes adversarial strategy templates against deliverables, producing structured finding reports with severity classification (Critical/Major/Minor)

Quality Scorer agent — implements S-014 LLM-as-Judge rubric scoring with the SSOT 6-dimension weighted composite, producing per-dimension scores, weighted composite, and PASS/REVISE/ESCALATE verdict

Strategy Selector agent — maps criticality levels (C1-C4) to the correct adversarial strategy sets per SSOT quality-enforcement.md, producing an ordered execution plan with template file paths

API Contract Generator agent. Transforms use case realization artifacts into OpenAPI 3.1 specifications using a novel UC-to-contract transformation algorithm. Maps interaction sequences to API paths and operations, derives HTTP methods from request semantics, extracts request/response schemas from interaction preconditions and postconditions, and maps extension conditions to error responses. Requires input use case at realization_level = INTERACTION_DEFINED with populated interactions block from uc-slicer Activity 5. Invoke when generating, creating, deriving, or mapping use case interactions to API contracts.

API Contract Validator agent. Validates generated OpenAPI 3.1 specifications against the OpenAPI schema standard and verifies traceability from every API operation back to its source use case interaction step. Checks completeness (all interactions mapped), correctness (HTTP methods match request semantics), and standards compliance (valid OpenAPI structure). Requires both the generated contract file and the source use case artifact. Invoke when validating, checking, verifying, or auditing API contracts generated from use cases.

Documentation auditor agent — analyzes existing documentation against Diataxis quality criteria, detects quadrant mixing, identifies classification errors, and produces structured audit reports with per-criterion pass/fail and remediation recommendations. Invoke for documentation quality review.

Documentation classifier agent — analyzes documentation requests against the two Diataxis axes (practical/theoretical, acquisition/application) and returns a structured classification with quadrant, confidence, and decomposition recommendation. T1 read-only, does not invoke writer agents.

Explanation writer agent — produces understanding-oriented documentation following Diataxis methodology. Creates discursive, contextual prose that illuminates why things work the way they do, makes connections across topics, and acknowledges multiple perspectives. Invoke when users need conceptual understanding.

How-to guide writer agent — produces goal-oriented documentation following Diataxis methodology. Creates action-only guides for competent users solving specific problems. Invoke when users need directions toward a concrete goal, not learning experiences. NOT for beginners building skills for the first time (use diataxis-tutorial instead).

Reference writer agent — produces information-oriented documentation following Diataxis methodology. Creates authoritative, structured technical descriptions that mirror the machinery they document. Invoke when users need neutral, austere reference documentation for APIs, configurations, or systems.

Tutorial writer agent — produces learning-oriented documentation following Diataxis methodology. Creates step-by-step tutorials with prerequisites, visible results per step, and no alternatives. Invoke when users need to learn something new through guided hands-on experience. NOT for users who need to quickly accomplish a task (use diataxis-howto instead).

Solution architect and threat modeler for the /eng-team skill. Invoked when users request system design, architecture decisions, or threat modeling (STRIDE/DREAD/PASTA). Produces architecture decision records, threat models with trust boundaries, and security-first designs. Routes from Step 1 of the /eng-team 8-step workflow. Integrates NIST CSF 2.0 governance and threat intelligence from /red-team cross-skill integration. Output follows ADR-output-path-resolution-001 (P1/P2/P3 resolution).

Secure backend engineer for the /eng-team skill. Invoked when users request server-side implementation with security hardening, input validation, authentication and authorization logic, API security, or database security. Produces secure server-side code with OWASP Top 10 and ASVS 5.0 compliance. Routes from Step 3 (parallel) of the /eng-team 8-step workflow. Output follows ADR-output-path-resolution-001 (P1/P2/P3 resolution).

DevSecOps pipeline engineer for the /eng-team skill. Invoked when users request automated security scanning (SAST/DAST), CI/CD security pipeline configuration, secrets scanning, container scanning, or dependency analysis. Produces pipeline configurations and scan result reports. Routes from Step 4 of the /eng-team 8-step workflow. NEW agent absorbing automated tooling from eng-security per Phase 1 research. Integrates DevSecOps patterns and Google SLSA build automation. Output follows ADR-output-path-resolution-001 (P1/P2/P3 resolution).

Secure frontend engineer for the /eng-team skill. Invoked when users request client-side implementation with XSS prevention, Content Security Policy configuration, CORS hardening, or output encoding. Produces secure client-side code with OWASP Top 10 and ASVS 5.0 compliance. Routes from Step 3 (parallel) of the /eng-team 8-step workflow. Output follows ADR-output-path-resolution-001 (P1/P2/P3 resolution).

Incident response specialist for the /eng-team skill. Invoked when users request incident response runbooks, vulnerability lifecycle management, post-deployment security monitoring, containment coordination, or remediation tracking. Produces IR plans and post-deployment security artifacts. Routes from Step 8 (post-deployment) of the /eng-team 8-step workflow. NEW agent filling post-deployment gap per Phase 1 research. Activates independently of build workflow. Output follows ADR-output-path-resolution-001 (P1/P2/P3 resolution).

Secure infrastructure engineer for the /eng-team skill. Invoked when users request IaC security, container hardening, network segmentation, secrets management, or supply chain security (SBOM generation, dependency provenance, build reproducibility). Produces secure infrastructure configurations with CIS Benchmark and Google SLSA compliance. Routes from Step 3 (parallel) of the /eng-team 8-step workflow. Output follows ADR-output-path-resolution-001 (P1/P2/P3 resolution).

Engineering lead and standards enforcer for the /eng-team skill. Invoked when users request implementation planning, code standards enforcement, dependency governance, or technical quality ownership. Produces implementation plans, standards mappings, and dependency decisions. Routes from Step 2 of the /eng-team 8-step workflow. Integrates MS SDL Requirements phase and NIST SSDF Prepare Organization and Protect Software practices. Output follows ADR-output-path-resolution-001 (P1/P2/P3 resolution).

Security QA engineer for the /eng-team skill. Invoked when users request security test strategy, security test cases, fuzzing campaigns, property-based testing, boundary testing, or coverage enforcement. Produces test artifacts with security regression suites and coverage reports. Routes from Step 5 of the /eng-team 8-step workflow. Integrates OWASP Testing Guide and MS SDL Verification phase practices. Output follows ADR-output-path-resolution-001 (P1/P2/P3 resolution).

Final review gate and quality enforcer for the /eng-team skill. Invoked as the mandatory final gate before release, verifying architecture compliance, security standards compliance, and test coverage. Integrates /adversary for C2+ deliverables per R-013 at >= 0.95 quality threshold. Routes from Step 7 of the /eng-team 8-step workflow. Aggregates all /eng-team standards for comprehensive compliance verification. Output follows ADR-output-path-resolution-001 (P1/P2/P3 resolution).

Security code review specialist for the /eng-team skill. Invoked when users request manual secure code review, security requirements verification, or architecture security review. Produces finding reports with CWE classifications and OWASP ASVS 5.0 verification results. Routes from Step 6 of the /eng-team 8-step workflow. Narrowed scope: automated tooling moved to eng-devsecops. Output follows ADR-output-path-resolution-001 (P1/P2/P3 resolution).

NASA Technical Architect agent implementing NPR 7123.1D Processes 3, 4, and 17 for logical decomposition, design solution definition, and decision analysis

NASA Configuration Management agent implementing NPR 7123.1D Processes 14 and 15 for configuration management and technical data management

NASA Systems Engineering explorer agent implementing NPR 7123.1D Process 17 (Decision Analysis) for divergent thinking, alternative generation, and trade space exploration

NASA System Integration agent implementing NPR 7123.1D Processes 6 and 12 for product integration and interface management

NASA SE Quality Assurance agent for artifact validation - validates SE work products against NPR 7123.1D, constitutional principles (P-040/P-041/P-042), and NASA work product standards

NASA Systems Engineering Status Reporter

NASA Requirements Engineer agent implementing NPR 7123.1D Processes 1, 2, and 11 for stakeholder needs, requirements definition, and requirements management, with adversarial quality mode integration

NASA Technical Review Gate agent implementing NPR 7123.1D Appendix G for SRR, PDR, CDR, FRR and other technical reviews with entrance/exit criteria

NASA Risk Manager agent implementing NPR 7123.1D Process 13 and NPR 8000.4C for technical risk management, with adversarial quality mode integration

NASA V&V Specialist agent implementing NPR 7123.1D Processes 7 and 8 for product verification and validation, with adversarial quality mode integration

Orchestration Planner agent for multi-agent workflow design, pipeline architecture, and state schema definition

Orchestration Synthesizer agent for cross-document synthesis, pattern extraction, and final workflow recommendations

Orchestration State Tracker agent for updating workflow state, registering artifacts, and creating checkpoints

Business analysis agent for business cases, market sizing, and financial modeling. Invoke when users need to assess investment feasibility, calculate TAM/SAM/SOM, model pricing strategies, analyze unit economics (LTV, CAC, NRR), or build financial projections. Trigger keywords: business case, financial model, market sizing, TAM, pricing model, unit economics, LTV, CAC, break-even, NPV, feasibility. Output follows ADR-output-path-resolution-001 (P1/P2/P3 resolution).

Competitive analysis agent for competitive intelligence, battle cards, and win/loss analysis. Invoke when users need to analyze competitors, create battle cards with talk tracks, run Porter's Five Forces analysis, map competitive positioning, or analyze win/loss patterns. Trigger keywords: competitive analysis, battle card, win/loss, competitor, Porter's, SWOT, competitive landscape, differentiation, market intelligence. Output follows ADR-output-path-resolution-001 (P1/P2/P3 resolution).

Customer insight agent for personas, journey maps, and VOC research. Invoke when users need to understand customers, create JTBD-oriented personas, map customer journeys with Moments of Truth, synthesize interview data, or analyze churn/retention patterns. Trigger keywords: persona, customer interview, journey map, VOC, voice of customer, churn analysis, NPS, customer discovery, pain points. Output follows ADR-output-path-resolution-001 (P1/P2/P3 resolution).

Market strategy agent for GTM plans, MRDs, positioning, and buyer personas. Invoke when users need to plan go-to-market strategy, create positioning and messaging frameworks, design launch plans, write market requirements, or define buyer personas for the buying committee. Trigger keywords: GTM, go-to-market, positioning, messaging, MRD, launch plan, sales enablement, buyer persona, product marketing, PLG. Output follows ADR-output-path-resolution-001 (P1/P2/P3 resolution).

Product strategy agent for PRDs, product vision, roadmaps, and use cases. Invoke when users need to decide what to build and why, prioritize features using RICE/Kano/WSJF, create product requirements, or define product strategy. Trigger keywords: PRD, product requirements, roadmap, prioritize, RICE, product vision, strategy, "what to build", opportunity assessment, north star. Output follows ADR-output-path-resolution-001 (P1/P2/P3 resolution).

Deep analysis agent for root cause, trade-offs, gap analysis, and risk assessment with adversarial quality strategies and L0/L1/L2 output levels

Architectural decision agent producing ADRs with Nygard format and L0/L1/L2 output levels

Quality evaluation agent for creator-critic-revision cycles with adversarial strategy integration (S-014 LLM-as-Judge primary) - critiques agent outputs using SSOT quality dimensions and provides improvement recommendations

Failure analysis and debugging agent using 5 Whys, Ishikawa, and FMEA with L0/L1/L2 output levels

Status reporting agent for phase progress, constraint status, and knowledge summaries with L0/L1/L2 output levels

Deep research agent with MANDATORY artifact persistence, PS integration, Context7 MCP, adversarial quality strategies, and L0/L1/L2 output levels

Quality review agent for code, design, architecture, and security reviews with adversarial quality strategies and L0/L1/L2 output levels

Meta-analysis agent for synthesizing patterns across multiple research outputs with adversarial quality strategies and L0/L1/L2 output levels

Constraint and design validation agent producing verification reports with L0/L1/L2 output levels

Interactive Prompt Builder agent — walks users through the 5-element prompt anatomy (routing, scope, data source, quality gate, output path), generating complete XML-wrapped structured prompts with NPT-013 constraints. Invoke when building structured Jerry prompts from scratch. Output follows ADR-output-path-resolution-001 (P1/P2/P3 resolution).

NPT Constraint Generator agent — takes user intent descriptions and produces properly formatted NPT-009/NPT-013 constraints with XML wrapping for agent definitions, rule files, and skill documentation. Invoke when generating forbidden actions or behavioral constraints. Output follows ADR-output-path-resolution-001 (P1/P2/P3 resolution).

Prompt Quality Scorer agent — evaluates prompts against the 7-criterion rubric (C1 Task Specificity through C7 Positive Framing), returning dimension-level scores, weighted composite, tier classification, and targeted improvement suggestions. Invoke when scoring or evaluating prompt quality.

Data Exfiltration Specialist for /red-team. RoE-GATED -- requires explicit authorization in Rules of Engagement with specified data types. Provides methodology for data identification, exfiltration channels, covert communication, and DLP bypass assessment. Owns exfiltration-phase defense evasion (data encoding, encrypted channels). Exfiltration to evidence vault ONLY. Output follows ADR-output-path-resolution-001 (P1/P2/P3 resolution).

Exploitation Specialist for /red-team. Provides exploit development methodology, payload crafting guidance, vulnerability chaining, PoC development, and safe Impact demonstration (TA0040 technical). Owns execution-time defense evasion (process injection, signed binary proxy execution). Constrained to target AND technique allowlist intersection. Output follows ADR-output-path-resolution-001 (P1/P2/P3 resolution).

Infrastructure & Tooling Specialist for /red-team. Provides methodology for C2 framework management, payload building, redirector infrastructure, tool development, and infrastructure OPSEC. Owns tool-level defense evasion (C2 obfuscation, payload encoding/packing, execution guardrails, sandbox evasion, redirector hardening). NEW agent -- highest-confidence addition per Phase 1 research. Output follows ADR-output-path-resolution-001 (P1/P2/P3 resolution).

Lateral Movement Specialist for /red-team. Provides methodology for pivoting, tunneling, living-off-the-land techniques, and internal exploitation. Uses C2 during operations but does NOT build or manage C2 infrastructure. Owns network-level defense evasion (traffic signaling, protocol tunneling). Operates within authorized internal network range. Output follows ADR-output-path-resolution-001 (P1/P2/P3 resolution).

Engagement Lead & Scope Authority for /red-team. Creates and manages scope documents, Rules of Engagement, and authorization verification for all penetration testing and red team engagements. MANDATORY FIRST agent -- no other agent operates without an active scope. Covers methodology selection, team coordination, operational OPSEC enforcement, findings QA, and methodology adaptation. Output follows ADR-output-path-resolution-001 (P1/P2/P3 resolution).

Persistence Specialist for /red-team. RoE-GATED -- requires explicit authorization in Rules of Engagement. Provides methodology for backdoor placement, scheduled tasks, service manipulation, and rootkit methodology. Owns persistence-phase defense evasion (indicator removal, timestomping). Operates only on already-compromised hosts within authorized scope. Output follows ADR-output-path-resolution-001 (P1/P2/P3 resolution).

Privilege Escalation Specialist for /red-team. Provides methodology for local and domain privilege escalation, credential harvesting, token manipulation, and misconfiguration exploitation. Owns credential-based defense evasion (access token manipulation). Limited to already-compromised hosts only. Output follows ADR-output-path-resolution-001 (P1/P2/P3 resolution).

Reconnaissance Specialist for /red-team. Performs OSINT, network enumeration, service discovery, technology fingerprinting, and attack surface mapping. Feeds adversary TTPs to eng-architect via Cross-Skill Integration Point 1 (Threat-Informed Architecture). Operates within reconnaissance scope of the authorized target allowlist. Output follows ADR-output-path-resolution-001 (P1/P2/P3 resolution).

Engagement Reporter & Documentation Specialist for /red-team. Generates comprehensive engagement reports with finding documentation, risk scoring, remediation recommendations, executive summaries, Impact risk communication (TA0040 documentation), and scope compliance attestation. Can be invoked without active scope for report generation from existing findings. Read-only access to all engagement data. Output follows ADR-output-path-resolution-001 (P1/P2/P3 resolution).

Social Engineering Specialist for /red-team. RoE-GATED -- requires explicit authorization in Rules of Engagement. Provides methodology for social reconnaissance, phishing campaigns, pretexting frameworks, vishing, credential harvesting via social channels, and human attack vector analysis. NEW agent -- closes human vector gap identified in Phase 1 research. Output follows ADR-output-path-resolution-001 (P1/P2/P3 resolution).

Vulnerability Analyst for /red-team. Performs vulnerability identification, CVE research, exploit availability assessment, attack path analysis, and risk scoring. Consumes reconnaissance findings from red-recon and produces prioritized vulnerability reports for red-exploit. Operates within analysis scope with read-only target interaction. Output follows ADR-output-path-resolution-001 (P1/P2/P3 resolution).

Voice Fidelity Scorer — scores voice fidelity on a 0-1 scale across the 5 voice traits, computes a composite voice fidelity score, and applies leniency bias counteraction consistent with adv-scorer patterns

Voice Compliance Reviewer — evaluates framework output text against the 5 Authenticity Tests and boundary conditions, producing a pass/fail compliance report with specific evidence and suggested fixes

Voice Transformation agent — rewrites framework output text from current Jerry voice to Saucer Boy voice while preserving all technical information, then self-applies the 5 Authenticity Tests before presenting the result

Session voice agent — generates McConkey-style conversational responses for work sessions. Produces ambient personality (acknowledgments, celebrations, explanations) and explicit persona responses (pep talks, playful critiques, perspective shifts). Loads persona and boundary conditions on demand.

Test Coverage Analyst agent. Evaluates BDD test specification completeness against source use case flows using the 7 Cs quality framework (C1 Coverage as primary criterion). Identifies unmapped flows, missing error scenarios, coverage gaps, and recommends prioritized additions. Reads both the Feature file and the source use case artifact for cross-reference analysis. Invoke when analyzing coverage, checking completeness, identifying test gaps, or evaluating test specification quality against use case source.

BDD Test Specification Generator agent. Transforms use case artifacts into Gherkin BDD Feature files using Clark's (2018) UC2.0-to-Gherkin mapping algorithm. Maps basic flow to happy path scenario, alternative flows to additional scenarios, and extensions to error/negative scenarios. Requires input use case at detail_level >= ESSENTIAL_OUTLINE with typed flow steps. Invoke when generating, transforming, creating, or mapping use case flows to Gherkin BDD scenarios.

Extracts semantic entities (speakers, actions, decisions, questions, topics) from parsed transcripts

Generates formatted Markdown output with packet structure, file splitting, and bidirectional linking per ADR-007 golden template specification

Generates ASCII art mindmap visualizations as fallback for non-Mermaid environments

Generates Mermaid mindmap visualizations from extracted transcript entities

Strategy Pattern orchestrator for hybrid parsing: Python delegation for VTT, LLM fallback for others

Use Case Author agent. Creates and elaborates use case artifacts using Cockburn's 12-step writing process and Jacobson UC 2.0 progressive narrative levels. Produces structured YAML frontmatter validated against use-case-realization-v1.schema.json. Invoke when writing, creating, authoring, elaborating, expanding, describing, drafting, or refining use cases.

Use Case Slicer agent. Decomposes use cases into implementation-ready slices following Jacobson UC 2.0 Activity 2 (Slice the Use Cases), Activity 4 (Prepare a Use-Case Slice), and Activity 5 (Analyze a Use-Case Slice). Manages the five-state slice lifecycle (Scoped through Verified) and produces the realization interaction sequence consumed by /contract-design. Invoke when slicing, decomposing, breaking down, preparing, analyzing, or realizing use case slices.

Parent orchestrator for the /user-experience skill. Routes UX requests by product lifecycle stage, enforces wave criteria gates, manages cross-sub-skill handoffs, and synthesizes multi-framework findings. Invoke when users need structured UX evaluation, user research, design systems, UX metrics, behavior diagnosis, feature prioritization, design sprints, or AI interaction design for tiny teams (1-5 people). Triggers: UX audit, comprehensive UX review, multi-framework evaluation, UX triage. Output follows ADR-output-path-resolution-001 (P1/P2/P3 resolution).

AI-first interaction design guide (CONDITIONAL) for /user-experience. Designs trust-calibrated AI interaction patterns using Yang et al. (2020) trust-risk x error-risk classification with 3x3 interaction pattern matrix. Produces trust-risk assessments, error-risk assessments, interaction pattern specs, feedback loop designs (Amershi et al. 2019), progressive disclosure strategies (Shneiderman 2020). CONDITIONAL: WSM >= 7.80 AND FEAT-020 complete; else routes to /ux-heuristic-eval with PAIR protocol. Invoke for AI interaction design, trust-risk/error-risk classification, human-AI collaboration patterns, AI feedback loops, progressive AI disclosure, AI interface audits. Triggers: AI-first design, AI interaction, trust calibration, AI UX, conversational UX, AI interface, LLM interface, agentic UX, human-AI interaction, AI transparency, AI error handling, AI onboarding, progressive AI disclosure, trust-risk, error-risk. Output follows ADR-output-path-resolution-001 (P1/P2/P3 resolution).

Atomic Design component taxonomy architect for the /user-experience skill. Implements Brad Frost's 5-level component hierarchy (Atoms, Molecules, Organisms, Templates, Pages) for design system architecture. Produces component inventories, design token audits, composition rules, Storybook coverage reports, and consolidation analyses. Invoke when users need component taxonomy construction, design system architecture, Storybook integration assessment, design token consistency analysis, or component reuse auditing. Triggers: atomic design, component taxonomy, design tokens, Storybook, atoms molecules organisms, design system, component inventory, component library. Output follows ADR-output-path-resolution-001 (P1/P2/P3 resolution).

Fogg Behavior Model B=MAP bottleneck diagnostician for the /user-experience skill. Diagnoses why users fail to take desired actions by analyzing the three B=MAP factors (Motivation, Ability, Prompt) using a convergent elimination algorithm to identify which factor falls below the action threshold. Produces bottleneck diagnoses, factor-level assessments with evidence chains, and prioritized intervention recommendations. Invoke when teams need to understand why users are not completing a specific action, diagnose behavioral bottlenecks, design behavior change interventions, or analyze post-launch user inaction patterns. Triggers: behavior design, B=MAP, Fogg model, behavior bottleneck, motivation analysis, ability analysis, prompt design, why users don't, user inaction, behavior diagnosis, tiny habits, action threshold. Output follows ADR-output-path-resolution-001 (P1/P2/P3 resolution).

AJ&Smart Design Sprint 2.0 facilitator for the /user-experience skill. Facilitates a structured four-day rapid prototyping and validation process compressed from the Google Ventures five-day Design Sprint (Knapp, Zeratsky & Kowitz, 2016; Courtney, 2019). Guides teams through Day 1 Map, Day 2 Sketch, Day 3 Decide, and Day 4 Test phases producing challenge maps, solution sketches, storyboards, realistic prototypes, and structured user interview findings with synthesis confidence gates. Invoke when teams need to rapidly validate a product concept, solve a critical design challenge through structured prototyping, test ideas with real users before committing to development, or explore solution directions when they do not know what to build. Triggers: design sprint, GV sprint, rapid prototyping, sprint week, map sketch decide test, 4-day sprint, design sprint 2.0, AJ Smart sprint, validate prototype, test with users, sprint facilitation. Output follows ADR-output-path-resolution-001 (P1/P2/P3 resolution).

HEART framework metrics analyst for the /user-experience skill. Applies Google's HEART framework (Happiness, Engagement, Adoption, Retention, Task Success) using the Goals-Signals-Metrics (GSM) process to define measurable UX metrics, establish baselines, and produce dashboard-ready metric specifications. Invoke when users need UX measurement, HEART metrics definition, GSM process execution, or metric dashboard specification. Triggers: HEART metrics, GSM, goals signals metrics, UX metrics, measurement, dashboard metrics, baseline measurement, metric threshold. Output follows ADR-output-path-resolution-001 (P1/P2/P3 resolution).

Nielsen heuristic evaluation specialist for the /user-experience skill. Evaluates interfaces against Nielsen's 10 usability heuristics, produces severity-rated findings (0-4 scale), and generates remediation recommendations. Invoke when users need usability evaluation, heuristic audit, or interface review against established usability principles. Escalates to Sonnet when critical finding count >= 3, Figma benchmark fails, or evaluation spans > 50 screens. Triggers: heuristic evaluation, usability audit, Nielsen heuristics, interface review. Output follows ADR-output-path-resolution-001 (P1/P2/P3 resolution).

Inclusive design and WCAG 2.2 accessibility evaluator for the /user-experience skill. Performs WCAG 2.2 compliance audits across Perceivable, Operable, Understandable, and Robust principles (conformance levels A, AA, AAA) and applies Microsoft Inclusive Design methodology including Persona Spectrum analysis (permanent, temporary, situational disabilities). Produces accessibility audit reports with per-criterion pass/fail evidence, color contrast measurements, keyboard navigation audits, screen reader compatibility reviews, cognitive load assessments, and Persona Spectrum profiles. Invoke when teams need WCAG conformance auditing, accessibility evaluation, contrast analysis, screen reader assessment, keyboard navigation audit, cognitive load evaluation, or inclusive design review. Triggers: accessibility, WCAG, WCAG 2.2, ARIA, screen reader, contrast, cognitive load, inclusive design, a11y, persona spectrum. Output follows ADR-output-path-resolution-001 (P1/P2/P3 resolution).

Jobs-to-Be-Done research and analysis specialist for the /user-experience skill. Conducts JTBD interviews, maps job statements, identifies switch triggers, and produces job maps with outcome expectations. Invoke when users need to understand user motivations, map jobs to be done, or conduct switch interview analysis. Triggers: JTBD, jobs to be done, switch interview, job mapping, user motivation. Output follows ADR-output-path-resolution-001 (P1/P2/P3 resolution).

Kano model feature classification analyst for the /user-experience skill. Implements the Kano Model methodology (Kano et al., 1984) with 5x5 functional/ dysfunctional evaluation table, Customer Satisfaction (CS) coefficient computation (Berger et al., 1993), priority matrix construction (Better vs. |Worse| scatter), and feature lifecycle dynamics (Attractive -> Performance -> Must-be). Produces feature classification reports, survey questionnaires, CS coefficient analyses, priority matrices, and split classification resolution prompts. Invoke when users need feature classification by satisfaction impact, Kano survey design, CS coefficient analysis, feature prioritization, or feature lifecycle assessment. Triggers: Kano, must-be, attractive, one-dimensional, performance feature, feature classification, feature prioritization, delighter, CS coefficient, satisfaction coefficient. Output follows ADR-output-path-resolution-001 (P1/P2/P3 resolution).

Lean UX hypothesis-driven design facilitator for the /user-experience skill. Facilitates Build-Measure-Learn cycles using Gothelf & Seiden's Lean UX methodology (3rd ed. 2021). Produces hypothesis backlogs, assumption maps, MVP experiment designs, and validated learning logs with ICE-scored prioritization. Invoke when users need hypothesis-driven iteration, assumption mapping, experiment design, or validated learning documentation. Triggers: lean UX, hypothesis, assumption mapping, build-measure-learn, MVP experiment, validated learning, experiment design, hypothesis backlog. Output follows ADR-output-path-resolution-001 (P1/P2/P3 resolution).

Audit worktracker integrity across multiple files with template compliance, relationship validation, and orphan detection

Verify work item acceptance criteria before closure

Generate Mermaid diagrams for worktracker hierarchies, timelines, status overviews, and dependency chains

On-demand adversarial quality reviews using strategy templates. Selects strategies by criticality level, executes adversarial templates against deliverables, and scores quality using LLM-as-Judge rubric. Integrates with quality-enforcement.md SSOT.

This skill should be used when the user asks to "design system", "create ADR", "review architecture", or mentions architectural decisions.

Markdown AST operations for Jerry documents. Provides structured parse, query, modify, validate, and render operations on Jerry markdown files via the jerry ast CLI.

This skill should be used when the user says "bootstrap", "set up Jerry", "configure guardrails", "initialize Jerry", or asks how to get started with Jerry. Sets up Jerry's context distribution by syncing behavioral rules and patterns.

API contract generation from use case realization artifacts using a novel UC-to-contract transformation algorithm. Transforms use case interaction sequences (produced by /use-case uc-slicer Activity 5) into OpenAPI 3.1 specifications with full traceability from API operations to source interaction steps. Validates generated contracts against OpenAPI schema standards. Requires use case artifacts at realization_level = INTERACTION_DEFINED with populated interactions block. Invoke when generating API contracts, OpenAPI specs, endpoint designs, request/response schemas, or operation mappings from use case artifacts.

Four-quadrant documentation framework. Produces tutorials (learning by doing), how-to guides (goal-oriented tasks), reference documentation (authoritative description), and explanation (conceptual understanding) using the Diataxis methodology. Invoke when creating new documentation, auditing existing docs for quadrant mixing, or classifying documentation requests. Triggers: documentation, tutorial, how-to, howto, reference docs, explanation, diataxis, write docs, write documentation, write tutorial, create documentation, classify documentation, audit documentation, user guide, getting started, quickstart, API docs, developer guide, quadrant, doc type, how-to guide.

Secure engineering team skill providing methodology guidance for building security-hardened software. Invoked when users request system design, implementation, code review, testing, CI/CD security, or incident response with security considerations. Routes to 10 specialized agents covering architecture through post-deployment. Integrates NIST SSDF governance, Microsoft SDL phases, OWASP ASVS verification, SLSA supply chain integrity, and DevSecOps automation patterns.

NASA Systems Engineering skill implementing NPR 7123.1D processes through 10 specialized agents. Use for requirements engineering, verification/validation, risk management, technical reviews, system integration, configuration management, architecture decisions, trade studies/exploration, quality assurance, and SE status reporting following mission-grade practices.

Multi-agent workflow orchestration with state tracking, checkpointing, and cross-pollinated pipelines. Use when coordinating parallel agent pipelines, managing sync barriers, or tracking complex workflow execution state across sessions.

Product management and product marketing decision framework. Invoke when users need product strategy (PRDs, vision, roadmaps), customer insight (personas, journey maps, VOC), business analysis (business cases, market sizing, pricing), competitive intelligence (battle cards, win/loss, competitive analysis), or go-to-market planning (GTM plans, positioning, MRDs, buyer personas). Uses 18 validated industry frameworks organized around Cagan's Value Risk and Business Viability Risk domains. Supports discovery mode (hypothesis-driven) and delivery mode (stakeholder-ready). Trigger keywords - PRD, product requirements, roadmap, prioritize, RICE, persona, journey map, VOC, business case, market sizing, TAM, competitive analysis, battle card, GTM, go-to-market, positioning, messaging, MRD.

Structured problem-solving framework with specialized agents for research, analysis, architecture decisions, validation, synthesis, reviews, investigations, and reporting. Use when tackling complex problems that need systematic exploration, evidence-based decisions, and persistent artifacts.

Structured prompt construction and quality validation for Jerry Framework. Invoke when building structured prompts, generating NPT-009/NPT-013 constraints, or scoring prompt quality. Guides users through the 5-element prompt anatomy, generates formatted constraints with XML wrapping, and scores prompts against the 7-criterion rubric.

Offensive security team skill providing methodology guidance for penetration testing and red team engagements. Invoked when users request penetration testing, reconnaissance, vulnerability analysis, exploitation methodology, social engineering, C2 infrastructure, or engagement reporting. Routes to 11 specialized agents covering the full MITRE ATT&CK kill chain. All engagements require red-lead scope authorization before any other agent. Follows PTES, OSSTMM, and ATT&CK methodology frameworks.

INTERNAL SKILL — auto-loaded for framework output voice quality. Reviews, rewrites, and scores framework output text for persona compliance using the Shane McConkey ethos: joy and excellence as multipliers. Governs quality gate messages, error messages, CLI output, hook text, and framework-generated text. Not user-invocable; loaded automatically when framework output needs voice enforcement.

Session conversational voice with McConkey personality. Invoke for Saucer Boy energy during work sessions — ambient personality that makes working with Jerry fun, or explicit McConkey invocation for on-demand persona responses. Use when you want McConkey-style commentary, encouragement, or perspective. Personality disengages automatically for hard stops, security, and governance.

BDD test specification generation from use case artifacts using Clark's (2018) UC2.0-to-Gherkin transformation algorithm. Transforms structured use case flows (basic flow, alternative flows, extensions) into Gherkin Feature files with Given-When-Then scenarios. Analyzes test coverage completeness against use case flow steps. Requires use case artifacts at detail_level >= ESSENTIAL_OUTLINE from /use-case skill. Invoke when generating test specs, BDD scenarios, Gherkin features, test plans, or analyzing test coverage from use cases.

Guided use case authoring and decomposition using Cockburn's 12-step writing process and Jacobson UC 2.0 progressive narrative levels. Creates structured use case artifacts with YAML frontmatter validated against use-case-realization-v1.schema.json. Decomposes use cases into implementation-ready slices with INVEST criteria verification and produces realization interaction sequences for downstream /test-spec and /contract-design consumption. Invoke when writing, creating, authoring, elaborating, slicing, decomposing, or realizing use cases.

Parent orchestrator for AI-augmented UX methodology targeting tiny teams (1-5 people). Routes to 10 sub-skills by product lifecycle stage through criteria-gated waves. Invoke when team needs structured UX evaluation, user research, design systems, UX metrics, behavior diagnosis, feature prioritization, design sprints, or AI interaction design. Each sub-skill implements a proven UX framework with synthesis hypothesis confidence gates and MCP design tool integration. Triggers: UX, user experience, usability, heuristic evaluation, JTBD, lean UX, HEART metrics, atomic design, inclusive design, behavior design, Kano model, design sprint, AI-first design, UX audit, accessibility, design system, user research.

Atomic Design component taxonomy sub-skill for the /user-experience parent skill. Implements Brad Frost's 5-level component hierarchy (Atoms, Molecules, Organisms, Templates, Pages) for design system architecture. Produces component inventories, design token audits, composition rules, and Storybook coverage reports. Invoke when teams need component taxonomy construction, design system architecture, Storybook integration, design token consistency analysis, or component reuse auditing. Invoked by ux-orchestrator during Wave 3 lifecycle-stage routing or when user intent is "Building component system" during the "During design" stage. Triggers: atomic design, component taxonomy, design tokens, Storybook, atoms molecules organisms, design system, component inventory, component library.

Fogg Behavior Model B=MAP bottleneck diagnosis sub-skill for the /user-experience parent skill. Diagnoses why users fail to take desired actions by analyzing the three B=MAP factors (Motivation, Ability, Prompt) and identifying which factor falls below the action threshold. Produces bottleneck diagnoses, factor-level assessments, and intervention recommendations with synthesis confidence gates. Invoke when teams need to understand why users are not completing a specific action, diagnose behavioral bottlenecks, design behavior change interventions, or analyze post-launch user inaction patterns. Invoked by ux-orchestrator during Wave 4 lifecycle-stage routing or when user intent is "Users not completing action" during the "After launch" stage. Triggers: behavior design, B=MAP, Fogg model, behavior bottleneck, motivation analysis, ability analysis, prompt design, why users don't, user inaction, behavior diagnosis, tiny habits, action threshold.

AJ&Smart Design Sprint 2.0 facilitation sub-skill for the /user-experience parent skill. Facilitates a structured four-day rapid prototyping and validation process compressed from the Google Ventures five-day Design Sprint (Knapp, Zeratsky & Kowitz, 2016; Courtney, 2019). Produces sprint artifacts including challenge maps, solution sketches, storyboards, realistic prototypes, and structured user interview findings with synthesis confidence gates. Invoke when teams need to rapidly validate a product concept, solve a critical design challenge through structured prototyping, test ideas with real users before committing to development, or explore solution directions when they do not know what to build. Triggers: design sprint, GV sprint, rapid prototyping, sprint week, map sketch decide test, 4-day sprint, design sprint 2.0, AJ Smart sprint, validate prototype, test with users, sprint facilitation.

HEART Metrics framework sub-skill for the /user-experience parent skill. Applies Google's HEART framework (Happiness, Engagement, Adoption, Retention, Task Success) using the Goals-Signals-Metrics (GSM) process to define measurable UX metrics for products and features. Invoked by ux-orchestrator when users need to measure UX health, define UX metrics, establish measurement baselines, or produce dashboard-ready metric specifications. Sub-skill of /user-experience; routed via ux-orchestrator lifecycle-stage triage. Triggers: HEART, metrics, happiness, engagement, adoption, retention, task success, GSM, measurement, UX metrics, dashboard, goals signals metrics.

Nielsen heuristic evaluation sub-skill for the /user-experience parent skill. Evaluates interfaces against Nielsen's 10 usability heuristics, produces severity-rated findings on a 0-4 scale (Cosmetic to Catastrophic), and generates remediation recommendations with effort estimates. Invoke when teams need structured usability evaluation, interface review, heuristic audit, or severity-rated UX findings. Invoked by ux-orchestrator during Wave 1 lifecycle-stage routing or CRISIS mode triage. Triggers: heuristic evaluation, usability audit, Nielsen heuristics, interface review, severity rating, usability inspection, UX evaluation.

Inclusive design and WCAG 2.2 accessibility evaluation sub-skill for the /user-experience parent skill. Performs WCAG 2.2 compliance audits across Perceivable, Operable, Understandable, and Robust principles (conformance levels A, AA, AAA) and applies Microsoft Inclusive Design methodology including Persona Spectrum analysis (permanent, temporary, situational disabilities). Produces accessibility audit reports and persona spectrum analyses. Invoke when teams need accessibility compliance evaluation, WCAG conformance auditing, screen reader compatibility assessment, color contrast analysis, cognitive load evaluation, or inclusive design review. Invoked by ux-orchestrator during Wave 3 lifecycle-stage routing or when user intent is "Check accessibility" at any lifecycle stage. Triggers: accessibility, WCAG, ARIA, screen reader, contrast, cognitive load, inclusive, a11y, inclusive design, WCAG 2.2, persona spectrum.

Jobs-to-Be-Done research and analysis sub-skill for the /user-experience parent skill. Conducts JTBD job statement synthesis, switch interview analysis (Moesta/Spiek four forces), outcome-driven innovation (Ulwick ODI), and job mapping for tiny teams (1-5 people). Invoked by ux-orchestrator when users need to understand user motivations, map jobs to be done, identify switch triggers, or produce job maps with outcome expectations. Sub-skill of /user-experience; routed via ux-orchestrator lifecycle-stage triage. Triggers: JTBD, jobs to be done, switch interview, job mapping, user motivation, outcome, hiring criteria, user jobs, switch forces.

Kano model feature classification and prioritization sub-skill for the /user-experience parent skill. Classifies product features into Must-be (M), Performance (O), Attractive (A), Indifferent (I), and Reverse (R) categories using the functional/dysfunctional questionnaire pair methodology (Kano et al., 1984). Computes Customer Satisfaction (CS) coefficients (Better/Worse) for priority matrix visualization. Produces feature classification reports, priority matrices, and survey design templates. Sample size awareness: 5-8 respondents yields directional classification only (MEDIUM confidence); 20+ respondents required for statistical classification (Berger et al., 1993). Invoked by ux-orchestrator during Wave 4 lifecycle-stage routing or when user intent is "Need to prioritize features" at any lifecycle stage. Triggers: Kano, must-be, attractive, one-dimensional, performance feature, satisfaction, feature classification, delighter, feature prioritization, CS coefficient.

Lean UX hypothesis-driven design sub-skill for the /user-experience parent skill. Facilitates Build-Measure-Learn cycles using Jeff Gothelf and Josh Seiden's Lean UX methodology (3rd ed. 2021). Produces hypothesis backlogs, assumption maps, MVP experiment designs, and validated learning logs. Invoke when teams need hypothesis-driven iteration, assumption mapping, experiment design, or validated learning documentation. Invoked by ux-orchestrator during Wave 2 lifecycle-stage routing or when user intent is "testing hypotheses" during the "During design" stage. Triggers: lean UX, hypothesis, assumption mapping, build-measure-learn, MVP experiment, validated learning, experiment design, hypothesis backlog.

Work item tracking and task management using the Jerry Framework hierarchy (Initiative, Epic, Feature, Story, Task, Enabler, Bug, Impediment). Manages WORKTRACKER.md manifests, tracks progress, and enforces template usage for consistent work decomposition.

This skill should be used when the user asks to "decompose task", "break down work", "create subtasks", or mentions task breakdown.

This skill should be used when the user asks to "create work item", "track task", "list tasks", "update work status", or mentions work/task management.

6 hooks across 6 events