s-hiraoku/claude-harnesses

autopilot

Explicitly keep a GitHub pull request moving until it is merge-ready by delegating to PR Guardian. Invoke manually with /autopilot; Claude must not start it automatically.

Langue du texte source : anglais

no-slop

MODIFIER skill that removes AI slop from prose without losing source facts or uncertainty. Use with any writing task or to rewrite text; for code slop, use deslop instead.

Langue du texte source : anglais

review-briefing

Prepare a verdict-first, read-only HTML briefing that helps a human review a pull request quickly and well. Use with a PR number or URL; opens in the browser with a terminal fallback.

Langue du texte source : anglais

adviser

Route an independent, review-only Claude process to a deterministically stronger model or effort when native Advisor is unavailable. Use for adviser, advisor, second-opinion, or stronger-model review requests; consequential decisions; recurring failures;…

Langue du texte source : anglais

pr-guardian

Monitor a pull request after opening it or resume a stalled PR, fix CI failures and reviewer feedback, push updates, reply to and resolve review conversations, and comment with the outcome.

Langue du texte source : anglais

finish-pr-feedback

Compatibility alias for pr-guardian. Use pr-guardian for stalled pull requests, CodeRabbit/Codex review feedback, CI failures, unresolved review conversations, and merge-ready PR follow-up.

Langue du texte source : anglais

implement-to-merge-ready

Run an end-to-end Claude Code delivery workflow from user request to merge-ready pull request, including planning, implementation, tests, self-review, ready-for-review PR creation, CI/review follow-up, and final status.

Langue du texte source : anglais

meta-packager

Analyze recent Claude Code work and package repeated patterns as the smallest useful skill, custom subagent, slash command, hook, or automation. Use when asked to mine prompts, sessions, shell history, or recent repeated work for reusable Claude Code assets.

Langue du texte source : anglais

jina-reader

Fetch public web pages with Jina AI Reader API and convert them into LLM-friendly Markdown. Use when an agent needs to read, summarize, quote briefly, extract facts from, or inspect a public URL that normal browsing, scraping, search snippets, or direct fetch…

Langue du texte source : anglais

goal-manager

Manage durable task goals for long-running Claude Code work using the project ledger, including objective writing, success criteria, resumption, and completion decisions.

Langue du texte source : anglais

kaizen-loop

Run a continuous product improvement loop: evaluate a product or codebase, present prioritized recommendations for approval, then implement only approved improvements through verification and PR follow-up.

Langue du texte source : anglais

ui-imagegen-director

Direct high-quality frontend UI work by using image-generated mockups when useful, translating the chosen direction into code, and verifying the rendered UI in a browser.

Langue du texte source : anglais

teach-session

Teach the human everything that happened in this session until they can demonstrably explain it, using an incremental checklist, restate-first probing, and AskUserQuestion quizzes. Use after a non-trivial change, debugging session, or hand-off when the goal…

Langue du texte source : anglais

empirical-prompt-tuning

Iteratively improve a skill or prompt by having a fresh subagent execute it against fixed scenarios, scoring two-sided (executor self-report + a pre-frozen requirements checklist), and looping until improvements plateau. Use after authoring or revising any…

Langue du texte source : anglais

bug-fix

Fix bugs with reproduction, minimal changes, regression coverage, and targeted verification.

Langue du texte source : anglais

deslop

Remove AI-generated boilerplate (vague comments, unused try/except, defensive validation, restated docstrings) from changed code without changing behavior.

Langue du texte source : anglais

docs-updater

Update documentation after code or behavior changes while keeping docs concise and relevant.

Langue du texte source : anglais

feature-implementation

Implement a feature safely with planning, focused edits, tests, docs, and verification.

Langue du texte source : anglais

fix-ci

Diagnose and repair failing CI checks on the current PR by parsing logs, reproducing locally when possible, and pushing focused fixes in batches.

Langue du texte source : anglais

long-running-orchestrator

Run multi-hour or multi-session work safely by combining the ledger, checkpoints, cost-ceiling guard, and resumable progress notes so context loss does not erase progress.

Langue du texte source : anglais

refactor-safely

Refactor code without behavior changes using small mechanical steps and verification.

Langue du texte source : anglais

release-check

Check whether a change is ready to release by reviewing diff, tests, docs, risks, and migration notes.

Langue du texte source : anglais

review

Review code changes with a bug-first, risk-focused workflow before merge or release.

Langue du texte source : anglais

security-review

Run a multi-pass security review over the current diff using parallel specialist subagents focused on injection, authn/authz, secrets, supply-chain, and infrastructure-as-code risks.

Langue du texte source : anglais

simplify

Review changed code on the current branch for reuse, clarity, and dead complexity, then propose or apply minimal cleanup without changing behavior.

Langue du texte source : anglais

tdd

Drive development with red-green-refactor using isolated test-writer, implementer, and refactorer subagents so tests reflect intent rather than anticipated implementation.

Langue du texte source : anglais