manifest-dev

End-to-end autonomous execution: figure-out → define → do, chained without manual approval gates. Use when you want to define and execute without intervention during planning, when the user asks for autonomous or end-to-end work, says just build it, or asks to tend or babysit a PR.

Figure things out together — any topic, problem, or idea. Presses relentlessly until shared understanding is reached. Use when you need to understand before acting, when figuring it out is the goal, or when the user asks to think through a decision, dig deeper, press an assumption, investigate why something is happening, or work through a problem.

Generate multi-CLI distribution packages from the Claude Code plugin. Converts shared skills and package assets for OpenCode, Codex CLI, and Pi under dist/. Run after changing plugin components to keep distributions in sync.

End-to-end autonomous execution: figure-out → define → do, chained without manual approval gates. Use when you want to define and execute without intervention during planning, when the user asks for autonomous or end-to-end work, says just build it, or asks to tend or babysit a PR.

Manifest executor. Works through Deliverables verifying every Acceptance Criterion and Global Invariant. Use when executing a manifest, running a plan, implementing a defined task, or when the user asks to run, execute, implement, or ship a manifest-backed plan.

Completion marker for the /do workflow. Outputs a plain-prose summary of what was built. Called by /do after every Acceptance Criterion and Global Invariant has fresh PASS evidence, when the manifest is complete, all criteria pass, or the workflow needs to wrap up with a completion summary.

Author-side PR lifecycle babysitter and companion to review-pr. Use when the user wants to tend an existing GitHub PR through CI, review threads, description sync, mergeability, auto-fixes, or asks to babysit a PR with or without an existing manifest.

Author-side PR lifecycle babysitter and companion to review-pr. Use when the user wants to tend an existing GitHub PR through CI, review threads, description sync, mergeability, auto-fixes, or asks to babysit a PR with or without an existing manifest.

Manifest executor. Works through Deliverables verifying every Acceptance Criterion and Global Invariant. Use when executing a manifest, running a plan, implementing a defined task, or when the user asks to run, execute, implement, or ship a manifest-backed plan.

Completion marker for the /do workflow. Outputs a plain-prose summary of what was built. Called by /do after every Acceptance Criterion and Global Invariant has fresh PASS evidence, when the manifest is complete, all criteria pass, or the workflow needs to wrap up with a completion summary.

Manifest builder. Turns shared understanding into a verifiable Manifest with Deliverables, Acceptance Criteria, Global Invariants, and Approach. Use when planning features, scoping refactors, debugging complex issues, or when the user asks to define, scope, plan, spec out, make a manifest, or break down a task.

Manifest builder. Turns shared understanding into a verifiable Manifest with Deliverables, Acceptance Criteria, Global Invariants, and Approach. Use when planning features, scoping refactors, debugging complex issues, or when the user asks to define, scope, plan, spec out, make a manifest, or break down a task.

Manifest builder. Turns shared understanding into a verifiable Manifest with Deliverables, Acceptance Criteria, Global Invariants, and Approach. Use when planning features, scoping refactors, debugging complex issues, or when the user asks to define, scope, plan, spec out, make a manifest, or break down a task.

Read-only inspection of a single GitHub PR lifecycle — checks CI, review threads, description sync, and mergeability, and returns PASS or FAIL with per-gate findings. Never invokes the merge button. Use when verifying a PR is ready to merge, polling lifecycle progress, checking mergeability, or babysitting a GitHub PR through CI and approvals.

Autonomous PR review that posts high-signal, human-voiced comments under your account. Use when reviewing someone else's PR or your own manifest-driven PR, when you want a precision-tuned review you can walk away from, or when the user asks to review a PR, post a PR review, autoreview, loop review, or watch a PR.

Autonomous PR review that posts high-signal, human-voiced comments under your account. Use when reviewing someone else's PR or your own manifest-driven PR, when you want a precision-tuned review you can walk away from, or when the user asks to review a PR, post a PR review, autoreview, loop review, or watch a PR.

Structured escalation when /do hits an unrecoverable blocker. Surfaces what was tried, why it failed, and what the user can decide. Called by /do when work is blocked, cannot proceed, hits an unrecoverable failure, needs a user decision, or gets stuck.

Drive a multi-party deliberation in a Slack channel or thread. The agent is an involved orchestrator — presses rigorously, brings evidence, names trade-offs, surfaces disagreements, advances when answers cohere; owner-by-Slack-handle overrules. Use when the people involved cannot all sit in one chat, when deliberation has to happen in Slack, or when the user asks to figure out with the team, press a group asynchronously, or get the team aligned.

Drive a multi-party deliberation in a Slack channel or thread. The agent is an involved orchestrator — presses rigorously, brings evidence, names trade-offs, surfaces disagreements, advances when answers cohere; owner-by-Slack-handle overrules. Use when the people involved cannot all sit in one chat, when deliberation has to happen in Slack, or when the user asks to figure out with the team, press a group asynchronously, or get the team aligned.

Narrate new Slack messages in a channel or thread since a cursor. Returns a natural-language story of what was said, or a clear statement when there is nothing new. Use when a parent agent polls Slack and needs to know what changed, read a Slack delta, or understand a thread update without re-ingesting the whole thread.

Review a change along one specific quality dimension — bugs, design, simplicity, maintainability, testability, test quality, type safety, contracts, operational readiness, docs, prose value, change intent, or CLAUDE.md adherence. Loads exactly one dimension reference and audits the diff against it, returning a structured PASS/FAIL report with severities. Use when verifying a change before merge, auditing a diff for a named concern, or running a manifest acceptance gate.

Create, update, review, or discuss an LLM prompt — system prompt, skill, or agent. State the goal, trust the model, add only what closes a real gap in natural behavior. Use when writing or improving prompts, discussing a skill or agent, diagnosing prompt failures, or when the user says a prompt needs work.

Review LLM prompts against the prompt-engineering skill's gap-calibration principles, reporting issues without modifying files. Use when reviewing prompt quality, auditing a prompt, evaluating a system prompt, or checking whether prompt issues are high-confidence and fixable.

Iteratively auto-optimize a prompt until no issues remain. Uses review-prompt in a loop, asks user for ambiguities, applies fixes via prompt-engineering skill. Runs until converged.

Sync the prompt-engineering plugin from a local clone of claude-code-plugins into .claude/ so the repo is self-contained for isolated/web environments. Copies agents/skills, removes only previously-synced items that disappeared upstream. Other content in .claude/ is left alone. Use when asked to sync claude-code-plugins, pull prompt-engineering, refresh prompt-engineering plugin.

Review a change along one specific quality dimension — bugs, design, simplicity, maintainability, testability, test quality, type safety, contracts, operational readiness, docs, prose value, change intent, or CLAUDE.md adherence. Loads exactly one dimension reference and audits the diff against it, returning a structured PASS/FAIL report with severities. Use when verifying a change before merge, auditing a diff for a named concern, or running a manifest acceptance gate.

Teach the learner to deeply understand a body of work — the current session's changes, a PR, an ADR, or any topic they name — the problem and why it existed, the solution and why it was built that way, and why it matters, incrementally and confirming mastery at each stage before advancing. Use when the user wants to understand what was just built or changed, asks to be taught or walked through a change, or wants to learn the why behind the work — e.g. "teach me what we did", "teach me this PR", "explain this ADR".

Teach the learner to deeply understand a body of work — the current session's changes, a PR, an ADR, or any topic they name — the problem and why it existed, the solution and why it was built that way, and why it matters, incrementally and confirming mastery at each stage before advancing. Use when the user wants to understand what was just built or changed, asks to be taught or walked through a change, or wants to learn the why behind the work — e.g. "teach me what we did", "teach me this PR", "explain this ADR".

Harden a manifest-dev task guidance file for one-shot quality — either /define's quality-gate/Default set or figure-out's probe set. Iterates: orthogonality gap analysis, user-approved additions, prompt review, fix, converge. Use when a task file needs comprehensive coverage or "harden task file".

Synthesize Architecture Decision Records from session transcripts. Extracts decisions via multi-agent pipeline and writes MADR files to a specified directory. Use after completing a /define or /do session to capture architectural decisions as durable records.

Produce a self-contained context payload that lets a fresh agent continue without re-deriving what this session established. Use for cross-boundary transfer such as switching tools, starting a clean session, or handing off to another agent, and for DIY sub-agent flows where a focused side-session returns context to the parent.

Structured escalation when /do hits an unrecoverable blocker. Surfaces what was tried, why it failed, and what the user can decide. Called by /do when work is blocked, cannot proceed, hits an unrecoverable failure, needs a user decision, or gets stuck.

Walk through a PR or large diff together — your own or someone else's — one sub-changeset at a time and one review topic at a time within it. Use when reviewing a substantive PR collaboratively, walking a large refactor, or when the user asks to walk a PR, walk a diff, explain a PR, review collaboratively, or review a change together. Optional --canvas runs the walk in a live HTML artifact.

Analyzes the current project structure and tech stack. Use when asked to explore, understand, or summarize a project. Trigger terms: project overview, analyze codebase, what is this project.

Analyze Claude Code sessions to learn what went right/wrong and suggest high-confidence improvements to skills. Use when asked to analyze a session, learn from a session, or review workflow effectiveness.