agent-capability-standard

Establish cause-effect relationships between events or states. Use when analyzing root causes, mapping dependencies, tracing effects, or building causal models.

Produce a comprehensive audit trail of actions, tools used, changes made, and decision rationale. Use when recording compliance evidence, tracking changes, or documenting decision lineage.

Identify capability gaps and propose new skills with prioritization. Use when analyzing missing capabilities, planning skill development, performing ontology expansion, or assessing coverage.

Create a safety checkpoint marker before mutation or execution steps. Use when about to modify files, execute plans, or perform any irreversible action. Essential for the CAVR pattern.

Assign labels or categories to items based on characteristics. Use when categorizing entities, tagging content, identifying types, or labeling data according to a taxonomy.

Compare multiple alternatives using explicit criteria, weighted scoring, and tradeoff analysis. Use when choosing between options, evaluating alternatives, or making decisions.

Enforce policies, guardrails, and permission boundaries; refuse unsafe actions and apply least privilege. Use when evaluating actions against policies, checking permissions, or reducing scope to safe boundaries.

Find failure modes, edge cases, ambiguities, and exploit paths in plans, code, or designs. Use when reviewing proposals, auditing security, stress-testing logic, or validating assumptions.

Execute the Debug Code Change workflow end-to-end with safety gates. Use when debugging code changes, investigating issues, or performing root cause analysis with audit trail.

Break a goal into subgoals, constraints, and acceptance criteria. Use when planning complex work, creating work breakdown structures, or defining requirements.

Split work across subagents with explicit contracts, interfaces, and merge strategies. Use when parallelizing tasks, distributing workload, or orchestrating multi-agent workflows.

Determine whether a specific pattern, entity, or condition exists in the given data. Use when searching for patterns, checking existence, validating presence, or finding signals.

Build a rigorous world model with state, dynamics, uncertainty, and provenance. Use when creating digital twins, constructing system representations, building simulation foundations, or establishing baseline world state.

Run the digital twin sync loop to synchronize real-world signals with a digital model. Use when updating digital twins, detecting drift, managing real-time state synchronization, or maintaining model-reality alignment.

Analyze a task description to detect required capabilities from the ontology, identify gaps, and synthesize a valid workflow automatically. Trigger: "discover capabilities", "what capabilities do I need", "analyze task", "synthesize workflow"

Find latent patterns, relationships, anomalies, or insights not explicitly specified. Use when exploring unknown structure, finding hidden connections, or uncovering emergent phenomena.

Run code or scripts deterministically with captured output. Use when running tests, executing build commands, invoking tools, or performing read-only operations that produce results.

Produce clear reasoning with assumptions, causal chains, and evidence. Use when clarifying decisions, teaching concepts, justifying recommendations, or documenting rationale.

Create a new artifact (text, code, plan, data) under specified constraints. Use when producing content, writing code, designing solutions, or synthesizing outputs.

Anchor claims to evidence from authoritative sources. Use when validating assertions, establishing provenance, verifying facts, or ensuring claims are supported by evidence.

Request clarification when input is ambiguous. Use when user request has missing parameters, conflicting interpretations, or insufficient constraints for reliable execution.

Combine heterogeneous data sources into a unified model with conflict resolution, schema alignment, and provenance tracking. Use when merging data from multiple systems, consolidating information, or building comprehensive views.

Execute a composed workflow by name. Use when running predefined workflows, orchestrating multi-step processes, or delegating to workflow templates.

Quantify values with uncertainty bounds. Use when estimating metrics, calculating risk scores, assessing magnitude, or measuring any quantifiable property.

Change persistent state with checkpoint and rollback support. Use when modifying files, updating databases, changing configuration, or any operation that permanently alters state.

Watch and report current state of a target system, process, or entity. Use when monitoring status, inspecting live systems, checking current conditions, or observing runtime behavior.

Write stable learnings, decisions, and patterns to durable storage like CLAUDE.md or knowledge files. Use when saving project decisions, recording patterns, or updating long-term memory.

Create a Perspective Validation Checklist (PVC) report for a change, workflow, schema, or policy. Use when performing socio-technical review, governance review, operational readiness review, or when a PR touches schemas/hooks/skills/tools and needs a PVC report.

Create an executable plan with steps, dependencies, verification criteria, checkpoints, and rollback strategies. Use when preparing changes, designing workflows, or structuring multi-step operations before execution.

Forecast future states or outcomes based on current data and trends. Use when estimating future values, projecting trajectories, forecasting outcomes, or anticipating system behavior.

Retrieve prior decisions, rationale, and learned patterns from memory to apply consistently. Use when needing context from previous interactions, looking up past decisions, or ensuring consistency with prior reasoning.

Ingest and parse incoming messages, events, or signals into structured form. Use when processing external inputs, handling API responses, parsing webhook payloads, or ingesting sensor data.

Fetch known facts or data from specified sources with citations and evidence pointers. Use when you know what you need and where to find it. Emphasizes provenance and verifiable references.

Safely undo changes by restoring to a checkpoint. Use when verify fails, errors occur, or explicit undo is requested. Essential for the CAVR pattern recovery.

Find relevant items under uncertainty across repositories, databases, web sources, or any searchable corpus. Use when exploring unknown territory, finding related information, or discovering relevant resources.

Emit a message or event to an external system with policy enforcement and approval gates. Use when publishing messages, calling APIs, sending notifications, or triggering external workflows. REQUIRES EXPLICIT APPROVAL.

Run what-if scenarios to explore outcomes and test hypotheses. Use when evaluating alternatives, stress-testing designs, exploring edge cases, or predicting system behavior under different conditions.

Create representation of current world state for a domain. Use when modeling system state, building world models, capturing entity relationships, or establishing baseline snapshots.

Merge outputs from multiple sources, resolve conflicts, and reconcile constraints into a unified result. Use when combining parallel agent outputs, merging data from different systems, or reconciling conflicting information.

Convert data between formats, schemas, or representations with explicit loss accounting and validation. Use when reformatting data, mapping between schemas, normalizing inputs, or translating structures.

Define how state changes over time through rules, triggers, and effects. Use when modeling state machines, defining workflows, specifying event handlers, or documenting system dynamics.

Check correctness against tests, specs, or invariants; produce pass/fail evidence. Use when validating changes, testing hypotheses, checking invariants, or confirming behavior matches expectations.

2 hooks across 2 events