Menu
System prompt templates for AI authoring. Use for adding prompts, editing role templates, or prompt conventions.
Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.
Basé sur la classification professionnelle SOC
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`.
| name | aitk-prompts |
| description | System prompt templates for AI authoring. Use for adding prompts, editing role templates, or prompt conventions. |
Read .claude/context/prompts.md for system overview and categories before editing.
# BASH SCRIPT ARCHITECT), all-caps H2 sections (## ROLE, ## CRITICAL CONSTRAINTS), title case H3 subsections (### Must Do).## ROLE, ## CRITICAL CONSTRAINTS, ## OUTPUT FORMAT.## VALIDATION when the output involves multi-step logic or edge cases. Omit for simple single-purpose prompts.prompts.toml using the file stem as the name.essentials is the curated minimum for aitk prompts install. Keep it tight: only prompts that earn their weight on nearly every project. Slugs may overlap with other categories.When adding an exportable prompt:
.md file in prompts/ starting with a frontmatter block carrying title and description. See .claude/standards/prose.md for the style rule.prompts.tomlessentials, also add it to the [essentials] section.claude/context/prompts.mdprompts/index.md. It is generated by scripts/core/regen-indexes.sh (runs as part of bun run check), and it fails if any prompt is missing required frontmatter..claude/context/prompts.md: system overview, categories, CLI, heading conventions, required sectionsprompts/meta-prompt.md: system prompt generator template, output format, constraint patterns