s-hiraoku/codex-harnesses

autopilot

Run the PR Guardian workflow when the user explicitly invokes $autopilot to keep a GitHub pull request moving toward merge-ready without merging it. Do not select this skill implicitly for ordinary PR follow-up.

原文语言：英语

pr-guardian

Monitor or resume GitHub pull requests, fix CI failures and actionable CodeRabbit, Codex, bot, or human review feedback, push focused updates, and stop only when the PR is merge-ready or has a concrete external blocker.

原文语言：英语

no-slop

Strip AI slop from prose output and raise its information density — filler openings/closings, restated questions, contentless emphasis, stacked hedges, repeated points, structure that outweighs substance — while preserving every fact, number, caveat, and…

原文语言：英语

review-briefing

Prepare a human reviewer to review a pull request in the least time with the best judgment. Given a PR number or URL, produce a verdict-first HTML briefing opened in the browser (terminal fallback available): the conclusion up front, the basis for trusting…

原文语言：英语

adviser

Route an independent review-only agent to a stronger model tier or reasoning effort at key decision points, then continue the task in the main agent. Use when the user asks for an adviser, advisor, second opinion, stronger review, or Claude Code /advisor-like…

原文语言：英语

retrospective-codify

Convert review feedback, CI failures, bug fixes, or task retrospectives into a durable project feedback ledger, then make future implementation work consult that ledger before planning.

原文语言：英语

implement-to-merge-ready

Run an end-to-end implementation delivery workflow from user request to merge-ready pull request. Use when the user asks Codex to implement a change and expects planning, goal tracking, UI design where relevant, code edits, tests, self-review, regular…

原文语言：英语

meta-packager

Analyze recent Codex work and package repeated patterns as the smallest useful skill, custom subagent, hook, or automation. Use when asked to mine sessions, memories, or recent repeated work for reusable Codex assets.

原文语言：英语

frontend-design

Guidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults.

原文语言：英语

deslop

Remove common AI-generated boilerplate and readability noise from changed code without changing behavior.

原文语言：英语

fix-ci

Diagnose and repair failing CI checks on the current branch or pull request with focused, reproducible fixes.

原文语言：英语

security-review

Review a diff for concrete security risks across injection, authn/authz, secrets, supply chain, infrastructure, and business logic.

原文语言：英语

simplify

Remove avoidable complexity from changed code while preserving behavior exactly.

原文语言：英语

tdd

Drive implementation through red-green-refactor with isolated test design, minimal implementation, and behavior-preserving cleanup.

原文语言：英语

jina-read-url

Read, summarize, inspect, or extract content from a public URL through Jina Reader. Use when the user asks to use Jina Reader, read a note.com/blog/article/X/Twitter/GitHub/page URL, recover Markdown from a URL that normal browsing cannot read cleanly, or…

原文语言：英语

kaizen-loop

Run a continuous product improvement loop: evaluate a product or codebase end to end, identify product-quality improvement opportunities, present prioritized recommendations for user approval, then implement only approved improvements through the plan, goal,…

原文语言：英语

ui-imagegen-director

Direct high-quality frontend UI work by using Codex Image Gen for visual mockups, then implementing the selected direction in code with browser-based visual QA. Use when the user asks for a better-looking web UI, UI mockup, app screen, dashboard, landing…

原文语言：英语

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…

原文语言：英语

empirical-prompt-tuning

Methodology for iteratively improving agent-facing instructions (skills / slash commands / CLAUDE.md / code-gen prompts) by having a bias-free executor run them and evaluating two-sidedly (executor self-report + instruction-side metrics) until improvements…

原文语言：英语

goal-manager

Manage /goal usage for concrete Codex work, including objective writing, success criteria, done criteria, long-running implementation, verification, PR creation, resumption, and completion decisions.

原文语言：英语

review

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

原文语言：英语

bug-fix

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

原文语言：英语

docs-updater

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

原文语言：英语

feature-implementation

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

原文语言：英语

refactor-safely

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

原文语言：英语

release-check

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

原文语言：英语