Daily review of the latest origin triage-* branch. Operator-prepared invariant — the operator fetches origin and switches the local repository to the triage branch before invocation. The skill verifies that the current branch matches `triage-*`, then dispatches `Skill(prompt-tuning)` per prompt-eligible changed file, `Skill(skill-review)` with `Base ref: main`, and `Skill(publicity-review)` with `Base ref: main` in sequence, finally emits a summary. Project-local routine — not for marketplace distribution.
Consult with a peer engineer for plan review, code review, implementation discussions, or problem-solving brainstorming. Use when you need a second opinion, want to validate your approach, or check for overlooked issues.
Guided development workflow that orchestrates planning, review, implementation, testing, and rule maintenance. Use this skill whenever the user wants to develop a feature, fix a bug, refactor code, or make any code changes following a structured process — even if they don't explicitly mention "workflow" and simply describe what they want built or fixed.
Triage open issues in the dev-workflow-bundle retrospective repo. Read each open issue, judge each Finding (accept / reject), apply accepted fixes to the triage-scope skills (the bundle skills dev-workflow, ask-peer, extract-rules, rules-review, plus dev-workflow-triage itself for self-targeted findings from its own self-retrospective), post a triage comment, and close the issue. Designed for non-interactive routine execution (no plan mode, no user prompts) on Claude Code on the Web.
Review uncommitted diff for content unsuitable for publication to a public repository — secrets/credentials, user-specific absolute paths, internal-only URLs/hostnames, and personal identifiers. Each iteration dispatches a fresh subagent that returns findings; the main thread applies the subagent's mechanical fixes and re-dispatches until the subagent declares no remaining findings or max iterations is reached. Non-interactive — no user prompts. Use as a final gate before publishing changes; designed to be called from non-interactive routines such as dev-workflow's hooks.on_complete or dev-workflow-triage's per-Finding sub-flow.
Review uncommitted skill changes against an internal checklist of skill-creator best practices and apply improvements. Use this whenever the user asks to "review skills", "check best practices", "improve SKILL.md", or wants a quality check on skill files before committing. Use this when there are uncommitted diffs in SKILL.md, README.md, or references/ files under skills/ or .claude/skills/. This is for reviewing existing skill changes, not creating new skills from scratch. Runs standalone — no external skill dependencies.
Empirically verify that a code diff achieves its stated objective by dispatching a bias-free executor that actually runs auto-derived evaluation scenarios against the post-diff file. The executor returns a JSON verdict with `suggested_edits`, and this skill applies them iteratively until the executor declares no further fixes are needed, max-iterations is reached, or a safety rail trips. Non-interactive — no user prompts. Use after applying an Edit when you need a dynamic cross-check that complements static reviewers like skill-review.
Extract project-specific coding rules and domain knowledge from existing codebase, generating markdown documentation for AI agents. Use when onboarding a new project, after code review discussions about coding style, or when coding conventions need documenting. Also consider running after sessions where coding preferences were discussed or corrected (--from-conversation), or after PRs with significant review feedback (--from-pr).