lossyrob/phased-agent-workflow

paw-review-feedback

Transforms evaluation findings into structured review comments with comprehensive rationale. Handles both initial draft generation and critique response iteration.

paw-review-github

Posts finalized review comments to GitHub, leaving the review pending by default or submitting it under explicit verified authorization.

paw-review-understanding

Analyzes PR changes to create ReviewContext.md and DerivedSpec.md artifacts. Handles both initial analysis and resumption after baseline research.

paw-review-workflow

Orchestrates the PAW Review workflow, coordinating activity skills to analyze PRs and generate comprehensive review feedback.

paw-git-operations

Shared git mechanics for PAW activity skills including branch naming conventions, strategy-based branching logic, and selective staging discipline.

paw-init

Bootstrap skill for PAW workflow initialization. Creates WorkflowContext.md, directory structure, and git branch. Runs before workflow skill is loaded.

paw-status

Workflow status activity skill for PAW workflow. Diagnoses workflow state, recommends next steps, explains PAW process, and optionally posts updates to Issues/PRs.

paw-final-review

Pre-PR review activity skill for PAW workflow. Reviews implementation against spec before Final PR creation with configurable single-model, multi-model, or society-of-thought execution.

paw-impl-review

Implementation review activity skill for PAW workflow. Reviews implementation for quality, adds documentation, and returns structured verdict.

paw-implement

Implementation activity skill for PAW workflow. Executes plan phases with code changes, documentation phases, and PR review comment handling. One phase per invocation.

paw-planning-docs-review

Holistic review of planning artifacts bundle (Spec.md + ImplementationPlan.md + CodeResearch.md) with configurable single-model, multi-model, or society-of-thought execution. Catches cross-artifact consistency issues before implementation begins.

paw-planning

Implementation planning activity skill for PAW workflow. Creates phased implementation plans with clear success criteria, documentation phase planning, and strategic architectural descriptions.

paw-pr

Final PR activity skill for PAW workflow. Creates comprehensive final PR to base branch with pre-flight validation, scaled descriptions, and merge guidance.

paw-sot

Society of Thought (SoT) — multi-perspective deliberative review engine. Orchestrates specialist personas with parallel or debate interaction, confidence-weighted synthesis, and interactive moderator mode. Use for code review, plan review, design analysis, or…

paw-transition

Workflow transition gate for PAW. Handles stage boundaries, session policy, preflight checks, and next activity determination.

paw-lite

Lightweight PAW workflow skill. Optional work shaping → plan → parallel fleet-style implementation → configurable review (single-model, multi-model, or SoT) → PR. Uses SQL todos for coordination and delegates to paw-work-shaping, paw-sot, paw-git-operations,…

paw-workflow

Reference documentation for PAW multi-phase implementation workflows. Provides activity tables, artifact structure, stage guidance, and PR routing patterns. Workflow enforcement rules are in PAW.agent.md.

paw-review-correlation

Synthesizes findings across multiple PRs to identify cross-repository dependencies, interface mismatches, and coordination gaps.

paw-review-critic

Critically assesses generated review comments for usefulness, accuracy, and appropriateness, adding assessment sections.

paw-review-response

Shared PR review comment response mechanics for PAW activity skills. Provides TODO workflow, commit patterns, and reply format for addressing reviewer feedback.

paw-rewind

Workflow rewind utility skill for PAW workflow. Rolls back workflow state to a previous stage or phase with safeguards and user confirmation.

paw-spec

Specification activity skill for PAW workflow. Converts issue/brief into structured feature specification with user stories, requirements, and success criteria.

paw-review-baseline

Analyzes the codebase at the PR's base commit to establish baseline understanding for review comparison.

paw-review-impact

Analyzes system-wide impact of PR changes including integration effects, breaking changes, performance, and security implications.

paw-code-research

Code research activity skill for PAW workflow. Documents implementation details with file:line references, discovers documentation infrastructure, and creates CodeResearch.md artifact.

paw-plan-review

Plan review activity skill for PAW workflow. Reviews implementation plans for feasibility, completeness, and spec alignment before implementation proceeds.

paw-spec-research

Spec research activity skill for PAW workflow. Answers factual questions about existing system behavior to inform specification writing.

paw-spec-review

Specification review skill for PAW workflow. Validates Spec.md against quality criteria and returns structured feedback for iteration.

paw-work-shaping

Interactive pre-spec ideation utility skill. Agent-led Q&A to progressively clarify vague ideas, research codebase context, and produce structured WorkShaping.md artifact.

multi-model-review

Reviews PRs or code changes using multiple AI models, synthesizes findings, and interactively applies fixes. Uses GPT 5.2, Gemini 3 Pro, and Opus 4.5 for diverse perspectives.

skill-creator

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends an agent's capabilities with specialized knowledge, workflows, or tool integrations.

paw-docs-guidance

Documentation conventions for PAW implementation workflow. Provides Docs.md template structure, include/exclude guidelines, and project documentation update patterns.

paw-review-gap

Systematically identifies gaps in correctness, safety, testing, and maintainability, categorizing findings by severity.

prompt-annotation

Annotates agent prompts with structural XML tags for comprehension, gap detection, and skill extraction. Use when analyzing agent prompt structure, comparing agents across projects, or identifying reusable vs workflow-bound content in prompts.