toolkit

Pulls review findings and CI status on the current branch's open PR, fixes each in the working tree, refreshes any stale `.claude/` docs, replies with a summary comment, and pushes a follow-up commit. The worker's return leg after `claude-pr-review`. Use when asked to "address the review", "fix the PR comments", "respond to review", or after an orchestrator posts findings. Do NOT use to write a review. That is `claude-pr-review`.

Ships a small self-review edit on the current PR branch by staging, committing, pushing, and syncing the open PR, replying on the PR when it carries review comments. Use when asked to "ship a followup", "push the PR fix", "followup", or "commit and push this small change". Do NOT use when there is no open PR for the branch (use git-ship instead).

Claude skill structure and authoring rules

Chains implement → verify → review → ship after a feature plan is approved. Reads the plan for the current branch, runs the full pipeline in one session, and stops on any failure or non-minor review finding. Use when asked to "autoship", "ship this feature end to end", or "run the chain". Do NOT auto-trigger. Requires an approved plan file.

Asserts the orchestrator role for the current session and holds the build loop, dispatching to the roadmap, feature, review, and worktree skills. Use when asked to "be the orchestrator", "run the orchestrator", "orchestrate this project", or to set up the control session for parallel feature builds. Do NOT build features or merge PRs in this session.

Reviews an open pull request from an independent session and posts findings as a review comment on the PR. Reads project docs and the roadmap for cross-feature context a self-review lacks. Use when asked to "review the PR", "review this feature's PR", "post a PR review", or acting as the orchestrator reviewing a worker's PR. Do NOT use to review local uncommitted changes. That is `claude-review`.

Classifies each section of a target project's bloated `CLAUDE.md` into the three-tier context model and proposes moves to path-scoped rules or context entries, keeping only always-load behavior in `CLAUDE.md`. Use when asked to "slim CLAUDE.md", "migrate CLAUDE.md to rules", "rebalance CLAUDE.md", or when a project's `CLAUDE.md` has grown large. Do NOT move `docs/` files (that is `migration-context`) and do NOT auto-execute. Proposal only.

Scaffolds a project-specific governance rule into `.claude/rules/<subdir>/<n>-<slug>.md` with correct frontmatter and a non-colliding number. Use when asked to "add a rule", "create a governance rule", "write a project rule", or when a project needs a coding rule the toolkit does not ship. Do NOT use to edit toolkit source rules under `governance/rules/`.

Reviews `.claude/memory/` and proposes per-entry actions (promote to `CLAUDE.md`, move into a skill body, hand off to governance, or delete as stale). Also runs the discuss, challenge, apply, and cleanup phases on an existing review file. Use when asked to "review memory", "discuss memory questions", "challenge the promotes", "apply memory decisions", "cleanup memory review", "promote memory", or "consolidate memories". Do NOT auto-apply. Output a grouped proposal and wait for block-by-block approval.

Generates pull request titles and descriptions from git diffs. Use for any PR creation or update.

Installs curated community and official Claude Code plugins user-scoped on the current machine via the `claude plugin` CLI. Use when asked to "install plugins", "set up plugins", "install the frontend/design/security/debugging plugins", "provision plugins on this machine", or when setting up Claude Code on a new computer. Do NOT use to install toolkit workflow skills, which load live via `--plugin-dir`. Assumes the `claude` CLI is on PATH.

Classifies markdown files in a target project's `docs/` folder and proposes `git mv` commands to relocate agent-flavored content to `.claude/context/`. Use when asked to "migrate docs to context", "move docs to context", "split docs", or to align an existing project with the three-tier context model. Do NOT auto-execute moves or rewrite inbound links. Proposal only.

Proposes `git mv` commands to relocate a target project's root `standards/` and `snippets/` folders into `.claude/standards/` and `.claude/snippets/`, the install layout newer toolkit versions expect. Use when asked to "relocate standards", "move standards to .claude", "migrate snippets to .claude", or after a toolkit upgrade leaves rules pointing at `.claude/standards/` while the files sit at the root. Do NOT auto-execute moves or edit rule files. Proposal only.

Drafts or updates `.claude/ROADMAP.md` by sequencing the MVP scope from `.claude/REQUIREMENTS.md` into ordered versions, each a usable increment. Use when asked to "draft a roadmap", "build the roadmap", "sequence the versions", "plan the roadmap", or "update the roadmap". Do NOT break versions into task-level steps. That is `claude-feature` and `.claude/TASKS.md`.

Generates production Bash scripts with a visual timeline UI, state-based interactive prompts, and strict error handling. Use when asked to write a bash script, create a shell script, or build a DevOps or CLI script with framed terminal output.

Detects a new project's type and runs `aitk init` with a resolved stack and snippets in one shot. Use when bootstrapping a new project with the toolkit, or when asked to "init this project", "bootstrap the toolkit", "set up toolkit", or "one-shot install". Assumes the `aitk` CLI is on PATH. Do NOT use when only installing governance rules. Use `setup-gov` instead.

Answers repository-knowledge questions about this toolkit by looking up `docs/index.md`, `.claude/context/index.md`, and `wiki/index.md` first, then the specific file those indexes point to. Use when asked "how do I use X", "what does Y do", "where is Z documented", or "how do I set up a target project". Do NOT use for code changes, editing, debugging, or questions about external tools not documented in this repo.

Claude Code plugin and tooling. Use for adding or modifying plugin skills, the `CLAUDE.md` seed, `aitk claude` commands, or `.claude/context/claude.md`.

Governance rules and stack definitions. Source `.md` files install as path-scoped Claude rules in `.claude/rules/`. Use for adding rules, editing stacks, or install and sync.

System prompt templates for AI authoring. Use for adding prompts, editing role templates, or prompt conventions.

Reusable prompt snippets for Claude and Gemini. Use for adding snippets, renaming slugs, or editing snippet folder structure.

Standards system and docs. Use when editing files in `standards/` or `docs/`, including authoring conventions, install, and sync. Do not load just to read `prose.md`. Read it directly.

Drafts `.claude/DESIGN.md` from a project's existing prose and shell UI surfaces using the toolkit seed template. Reads CLAUDE.md, standards, docs, and CLI UI modules to codify visual intent already implicit in the project. Use when asked to "extract the design system", "draft DESIGN.md", "bootstrap design tokens", or "capture the visual system". Do NOT use to mutate an existing `.claude/DESIGN.md`.

Drafts `.claude/DESIGN.md` on day one of a project from `REQUIREMENTS.md`, `ARCHITECTURE.md`, and a `## Personality` section, with token values proposed by the agent. Use when asked to "propose a design system", "bootstrap DESIGN.md from scratch", "draft tokens for a greenfield project", or "replace Claude Design onboarding". Do NOT use when UI code or stylesheets already exist. Reach for `claude-design-extract` instead.

Drafts `.claude/DIAGRAMS.md` with one or more Mermaid diagrams describing the project's architecture, request flow, retrieval or data pipeline, and deployment. Reads `.claude/ARCHITECTURE.md` and `REQUIREMENTS.md` when present, falls back to a code-structure scan. Use when asked to "draw the architecture", "diagram the system", "show the components", "give me a flow chart", or "visualize the project". Do NOT use for design tokens (use `claude-design-extract`) or UI audits (use `claude-ux-audit`).

Updates `.claude/` planning docs to reflect decisions made during the session. Use when design or requirements changed mid-cycle, after discussing a pivot, or before shipping when the session diverged from the original plan. Do NOT use for task promotion or archiving. Edit `.claude/TASKS.md` directly for that.

Plans a feature by reading the project's Claude setup and scanning relevant source files. Outputs which files to touch, risks, and ambiguities, then stops. Use before implementing anything, or when asked to "implement X", "add X", "build X", or "I want to add X". Do NOT implement. Plan only.

Extracts durable patterns from the current session and writes them to `.claude/memory/` as feedback, project, user, or reference memory files. Use when asked to "capture memory", "capture lessons", "wrap up the session", "end of session memory", or as the final step in autoship. Do NOT use to curate existing memory. Use `claude-memory-review` for that.

Audits a project's installed Claude seed docs against the toolkit's current seed source and proposes per-section edits without overwriting customizations. Use when asked to "sync seeds", "update my seeds", "check seed drift", "did the toolkit seeds change", or when reconciling `CLAUDE.md` and `.claude/` preambles after an upstream toolkit update.

Audits changed markdown files against applicable authoring standards (prose, skill, readme, branch, pr) and reports violations without fixing. Maps each file to its standards, greps for banned tokens, and groups findings by file. Use when asked to "audit prose", "audit standards", "check standards", "standards audit", or after editing markdown where standards compliance matters. Do NOT fix violations. Reporting only.

Audits the current UI for incomplete, inconsistent, or confusing patterns. Reads DESIGN.md and .claude/wireframes/ for intent, scans UI files, and outputs observations grouped by surface. Use when asked "audit the UX", "audit the UI", "UX audit", or "find UI roughness". Do NOT use for new feature planning or code changes.

Creates a new `SKILL.md` in `.claude/skills/`. Use when asked to create a skill, add a skill, or make a new skill.

Creates a new snippet file in `snippets/`. Use when asked to create a snippet, add a snippet, or make a new snippet.

Rewrites stale `README.md` and `docs/*.md` sections based on changes since main. Use before staging, or when asked to "sync docs" or "update the docs". Do NOT use for changelog updates or `CLAUDE.md`/`GEMINI.md` updates.

Generates and validates conventional branch names. Use for any branch naming or renaming.

Generates conventional commit messages from staged changes. Use for any git commit.

Splits a mixed-commit branch into focused branches off main using cherry-pick. Use when a branch has unrelated commits, asking "split this branch", or needing to separate concerns into reviewable PRs.

Groups staged files by concern and generates one conventional commit per group. Use when staged changes span multiple concerns and need to ship as separate commits.

Bootstraps the toolkit's `index.md` system in a target project. Scans for markdown-heavy folders, drafts `title` and `description` frontmatter, scaffolds `index.md` per chosen folder, and runs `aitk indexes regen` to validate. Use when asked to "set up indexes", "bootstrap indexes", "add index.md to this project", or "install indexes". Assumes the `aitk` CLI is on PATH.

Gemini CLI command definitions in TOML. Use for adding or modifying commands, categories, or sandbox tests.