By paivot-ai
Obsidian vault as runtime -- agents, skills, and hooks read from the vault and evolve with every session
npx claudepluginhub paivot-ai/paivot-graph --plugin paivot-graphCapture UX/visual/functional feedback and turn it into a prioritized backlog of high-quality stories using the Sr. PM agent
Cancel active execution loop
Run unattended execution loop until blocked or all work is done
Capture knowledge from the current session to the vault with auto-tagging and link suggestions
Refine vault knowledge based on session experience. Capture learned patterns, decisions, and debug insights. Agent prompts are self-contained in agents/*.md (not vault). System-scoped notes get proposals; project-scoped notes get direct edits.
View and configure paivot-graph settings for the current project -- project vault behavior, default scope, proposal expiry, gitignore preferences
Show Obsidian vault health -- note counts by folder, recent notes, project vault status, and pending proposals
Triage notes in _inbox to their proper folders and check vault health
Use this agent for adversarial review in TWO modes. (1) BACKLOG REVIEW (default) - Review backlog for gaps, missing walking skeletons, horizontal layers, missing integration stories. Must approve before execution. (2) MILESTONE REVIEW - After milestone completion, validate real delivery, inspect tests for mocks (forbidden), verify skills were consulted. Returns VALIDATED or GAPS_FOUND. Examples: <example>Context: Sr. PM has created the initial backlog from D&F docs. user: 'Review this backlog for gaps' assistant: 'I'll engage the anchor to adversarially review the backlog.' <commentary>Default mode - backlog review.</commentary></example>
Use this agent to adversarially review ARCHITECTURE.md after the Architect produces it. Only spawned when dnf.specialist_review is enabled. Reviews for unmet requirements, untraceable decisions, and contradictions across BUSINESS.md and DESIGN.md. Returns REVIEW_RESULT (APPROVED/REJECTED). Never talks to user -- feedback routes to Architect via dispatcher. Examples: <example>Context: Architect has completed ARCHITECTURE.md and specialist review is enabled. user: 'Review ARCHITECTURE.md for alignment with BUSINESS.md and DESIGN.md' assistant: 'REVIEW_RESULT: REJECTED with 2 issues (OMISSION: no authentication architecture for HIPAA constraint in BUSINESS.md, DRIFT: async pattern contradicts real-time requirement in DESIGN.md). Feedback provided for Architect to fix.' <commentary>Architect Challenger catches technical gaps before they cascade into the backlog and execution.</commentary></example>
Use this agent when you need to design system architecture, validate technical feasibility, or maintain architectural documentation. Part of the Balanced Leadership Team that communicates with the user through the orchestrator. Asks clarifying questions about technical constraints, existing infrastructure, team capabilities, and non-functional requirements. Owns ARCHITECTURE.md and ensures technical coherence across the system. Examples: <example>Context: Business Analyst presents new requirements that need technical validation. user: 'The BA says we need real-time data updates with 1-second latency for 50,000 concurrent users' assistant: 'I'll engage the architect to assess technical feasibility. I will relay its questions to you and pass your answers back until ARCHITECTURE.md is complete.' <commentary>The Architect will ask about existing infrastructure, deployment targets, budget constraints, and team experience before making decisions.</commentary></example> <example>Context: BLT cross-review after all D&F documents produced. user: 'Cross-review BUSINESS.md and DESIGN.md for consistency with ARCHITECTURE.md' assistant: 'I'll engage the architect to verify that business constraints and design patterns are technically feasible and properly reflected in the architecture.' <commentary>Architect reviews other BLT documents for technical consistency.</commentary></example>
Use this agent to adversarially review BUSINESS.md after the BA produces it. Only spawned when dnf.specialist_review is enabled. Reviews for omissions, hallucinations, and scope creep against user-provided context. Returns REVIEW_RESULT (APPROVED/REJECTED). Never talks to user -- feedback routes to BA via dispatcher. Examples: <example>Context: BA has completed BUSINESS.md and specialist review is enabled. user: 'Review BUSINESS.md for completeness against the user requirements' assistant: 'REVIEW_RESULT: REJECTED with 2 issues (1 OMISSION, 1 HALLUCINATION). Feedback provided for BA to fix.' <commentary>BA Challenger catches document-level issues before they cascade into DESIGN.md and ARCHITECTURE.md.</commentary></example>
Use this agent when you need to understand business requirements during Discovery & Framing. Part of the Balanced Leadership Team that communicates with the user through the orchestrator. Asks multiple rounds of clarifying questions until fully satisfied. Owns BUSINESS.md. Examples: <example>Context: User describes a business need for a greenfield project. user: 'We need to add authentication to our application' assistant: 'I'll engage the business-analyst to conduct thorough discovery, asking multiple rounds of clarifying questions. I will relay its questions to you and pass your answers back until BUSINESS.md is complete.' <commentary>The BA will dig deep through multiple questioning rounds until all ambiguities are resolved.</commentary></example> <example>Context: BLT cross-review after all D&F documents produced. user: 'Cross-review DESIGN.md and ARCHITECTURE.md for consistency with BUSINESS.md' assistant: 'I'll engage the business-analyst to check that business outcomes and constraints are properly reflected in the design and architecture.' <commentary>BA reviews other BLT documents for alignment with business requirements.</commentary></example>
Use this agent to adversarially review DESIGN.md after the Designer produces it. Only spawned when dnf.specialist_review is enabled. Reviews for unmet user needs, hallucinations, and contradictions with BUSINESS.md. Returns REVIEW_RESULT (APPROVED/REJECTED). Never talks to user -- feedback routes to Designer via dispatcher. Examples: <example>Context: Designer has completed DESIGN.md and specialist review is enabled. user: 'Review DESIGN.md for alignment with BUSINESS.md and user needs' assistant: 'REVIEW_RESULT: REJECTED with 1 issue (DRIFT: personas do not cover operator user type from BUSINESS.md). Feedback provided for Designer to fix.' <commentary>Designer Challenger catches design gaps before they cascade into ARCHITECTURE.md and the backlog.</commentary></example>
Use this agent during Discovery & Framing for ALL products - UI, API, CLI, database, etc. Part of the Balanced Leadership Team that communicates with the user through the orchestrator. The Designer ensures the product is desirable and usable from the user's perspective, regardless of interface type. Asks clarifying questions about user needs, UX patterns, and design trade-offs. Owns DESIGN.md. Examples: <example>Context: Greenfield API project. user: 'We're building a REST API for developers' assistant: 'I'll engage the designer to research API consumer needs and design the interface. I will relay its questions to you and pass your answers back until DESIGN.md is complete.' <commentary>Designer thinks about developer experience, API ergonomics, clear error messages, intuitive endpoint design.</commentary></example> <example>Context: BLT cross-review after all D&F documents produced. user: 'Cross-review BUSINESS.md and ARCHITECTURE.md for consistency with DESIGN.md' assistant: 'I'll engage the designer to check that user needs and design principles are properly reflected in business requirements and architecture.' <commentary>Designer reviews other BLT documents for alignment with UX vision.</commentary></example>
Use this agent when you need to implement stories from the backlog. This agent is EPHEMERAL - spawned for one story, delivers with PROOF of passing tests, then disposed. All context comes from the story itself, including testing requirements. Examples: <example>Context: Ready work exists in the backlog and needs to be implemented. user: 'Pick the next ready story and implement it' assistant: 'I will spawn an ephemeral developer agent to claim the story, read all context from the story itself, implement with tests, record proof of passing tests, and deliver.' <commentary>The Developer is ephemeral - gets all context from the story, implements, records proof, delivers, disposed.</commentary></example>
Use this agent to review delivered stories (PM-Acceptor role). This agent is ephemeral - spawned for one delivered story, makes accept/reject decision using evidence-based review, then disposed. Examples: <example>Context: Developer has marked a story as delivered and it needs PM review. user: 'Story PROJ-a1b is marked delivered. Review the acceptance criteria and accept or reject it' assistant: 'Let me spawn a PM-Acceptor to review this specific story. It will use the developer's recorded proof for evidence-based review, and either accept (close) or reject (reopen with detailed notes).' <commentary>PM-Acceptor is ephemeral - uses developer's proof for evidence-based review, makes accept/reject decision, then disposed.</commentary></example>
Use this agent after a milestone epic is successfully completed (all stories accepted). This agent is EPHEMERAL - spawned for one completed epic, extracts and analyzes LEARNINGS from all accepted stories, distills actionable insights, then disposed. Examples: <example>Context: A milestone epic has been completed with all stories accepted. user: 'Epic PROJ-a1b is complete. Run a retrospective to extract learnings' assistant: 'I will spawn a retro agent to analyze all accepted stories in this epic, extract LEARNINGS sections, and distill actionable insights for future work.' <commentary>Retro is ephemeral - runs after milestone completion, extracts learnings, produces insights, disposed.</commentary></example>
Use this agent for initial backlog creation during Discovery & Framing phase AND for bug triage when agents discover bugs during execution. This agent is the FINAL GATEKEEPER for D&F, ensuring comprehensive backlog creation from BUSINESS.md, DESIGN.md, and ARCHITECTURE.md. CRITICAL - embeds ALL context into stories so developers need nothing else. Also the DEFAULT agent authorized to create bugs -- receives DISCOVERED_BUG reports from Developer and PM-Acceptor agents, creates fully structured bugs with AC, epic placement, and dependency chain. When bug_fast_track is enabled (or story has pm-creates-bugs label), PM-Acceptor can create bugs directly with guardrails (P0, parent epic, discovered-by-pm label). Examples: <example>Context: BA, Designer, and Architect have completed their D&F documents. user: 'All D&F documents are complete. Create the initial backlog' assistant: 'I'll engage the paivot-sr-pm agent to thoroughly review BUSINESS.md, DESIGN.md, and ARCHITECTURE.md, create comprehensive epics and stories with ALL context embedded, and validate nothing is missed before moving to execution.' <commentary>The Sr PM ensures every point in all D&F documents is translated into self-contained stories.</commentary></example> <example>Context: Brownfield project or user wants direct backlog control. user: 'I need to add some stories to handle the new payment provider integration' assistant: 'I'll engage the paivot-sr-pm agent directly. Since this is brownfield work, it will work with your existing codebase context and requirements without requiring full D&F documents.' <commentary>Sr PM can be invoked directly for brownfield projects or backlog tweaks without full D&F.</commentary></example> <example>Context: Developer or PM-Acceptor discovered a bug during execution. user: 'DISCOVERED_BUG reports need triage' assistant: 'I'll engage the paivot-sr-pm agent to triage the discovered bugs -- it will create properly structured bugs with acceptance criteria, find the right epic, and set parent and dependency chain.' <commentary>Sr PM is the only agent that creates bugs. All bugs are P0.</commentary></example>
Architecture-as-code using C4 model and Structurizr DSL. Use when the project has `architecture.c4` enabled in settings, or when the user asks about C4 diagrams, Structurizr, architecture boundaries, or dependency rules. Teaches agents how to maintain a canonical architecture model alongside ARCHITECTURE.md, declare machine-checkable boundaries, and export diagrams.
This skill should be used when working on any project to understand how to effectively interact with the Obsidian knowledge vault. It teaches when to capture knowledge, what to capture, how to format vault notes, and how to search effectively. Use when you need to "save to vault", "update vault", "capture a decision", "record a pattern", "log a debug insight", or when starting/ending a significant work session.
Qiushi Skill: methodology skills for AI agents guided by seeking truth from facts, with Claude Code, Cursor, OpenClaw, Codex, OpenCode, and Hermes guidance.
Executes bash commands
Hook triggers when Bash tool is used
Modifies files
Hook triggers on file write and edit operations
Uses power tools
Uses Bash, Write, or Edit tools
Comprehensive UI/UX design plugin for mobile (iOS, Android, React Native) and web applications with design systems, accessibility, and modern patterns
Persistent memory system for Claude Code - seamlessly preserve context across sessions
Ultra-compressed communication mode. Cuts ~75% of tokens while keeping full technical accuracy by speaking like a caveman.
Intelligent prompt optimization using skill-based architecture. Enriches vague prompts with research-based clarifying questions before Claude Code executes them
Standalone image generation plugin using Nano Banana MCP server. Generates and edits images, icons, diagrams, patterns, and visual assets via Gemini image models. No Gemini CLI dependency required.