Menu
O SkillsMP coletou 26 skills de s-hiraoku/claude-harnesses. Abra uma skill para revisar a origem e os detalhes.
Mostrando 26 de 26 skills coletadas.
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.
Idioma do texto original: inglês
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.
Idioma do texto original: inglês
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.
Idioma do texto original: inglês
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;…
Idioma do texto original: inglês
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.
Idioma do texto original: inglês
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.
Idioma do texto original: inglês
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.
Idioma do texto original: inglês
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.
Idioma do texto original: inglês
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…
Idioma do texto original: inglês
Manage durable task goals for long-running Claude Code work using the project ledger, including objective writing, success criteria, resumption, and completion decisions.
Idioma do texto original: inglês
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.
Idioma do texto original: inglês
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.
Idioma do texto original: inglês
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…
Idioma do texto original: inglês
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…
Idioma do texto original: inglês
Fix bugs with reproduction, minimal changes, regression coverage, and targeted verification.
Idioma do texto original: inglês
Remove AI-generated boilerplate (vague comments, unused try/except, defensive validation, restated docstrings) from changed code without changing behavior.
Idioma do texto original: inglês
Update documentation after code or behavior changes while keeping docs concise and relevant.
Idioma do texto original: inglês
Implement a feature safely with planning, focused edits, tests, docs, and verification.
Idioma do texto original: inglês
Diagnose and repair failing CI checks on the current PR by parsing logs, reproducing locally when possible, and pushing focused fixes in batches.
Idioma do texto original: inglês
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.
Idioma do texto original: inglês
Refactor code without behavior changes using small mechanical steps and verification.
Idioma do texto original: inglês
Check whether a change is ready to release by reviewing diff, tests, docs, risks, and migration notes.
Idioma do texto original: inglês
Review code changes with a bug-first, risk-focused workflow before merge or release.
Idioma do texto original: inglês
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.
Idioma do texto original: inglês
Review changed code on the current branch for reuse, clarity, and dead complexity, then propose or apply minimal cleanup without changing behavior.
Idioma do texto original: inglês
Drive development with red-green-refactor using isolated test-writer, implementer, and refactorer subagents so tests reflect intent rather than anticipated implementation.
Idioma do texto original: inglês