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.

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.

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.

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;…

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.

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.

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.

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.

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…

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.

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.

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.

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…

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…

bug-fix

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

deslop

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

docs-updater

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

feature-implementation

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

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.

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.

refactor-safely

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

release-check

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

review

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

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.

simplify

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

tdd

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