bendrucker/claude

agents-handoff

Hand the current conversation off to a fresh background agent that picks up the work immediately, so you can step away and track it independently. Use when the user wants to background the current work, keep going without them, continue in a separate session,…

原文の言語: 英語

github-copilot

Get a cross-model second opinion on a code change from GPT via the Copilot CLI, then triage what it finds. Use when the ask names GPT, Copilot, a second model, or a cross-model check, and as the cross-model pass on a change that clears the review gate.

原文の言語: 英語

observability-session

Query Claude Code session history via a DuckDB index over `~/.claude/projects/`. Use when asked about Claude Code activity ("how many tokens today?", "what did I work on this week?", "which sessions discussed X?") or instead of reading, grepping, or jq-ing…

原文の言語: 英語

review-human

Request Ben's own review of the working diff or a document before it leaves the machine, for architecture and slop rather than bugs. Runs after the mechanical passes (code-review or simplify, comments:audit). Use for "get my review", "let me look at this…

原文の言語: 英語

review-peer

Review a pull request when requested by a peer. Use when reviewing PRs, providing code review feedback, or analyzing proposed changes. Supports GitHub and GitLab. Pass --triage to summarize a PR and estimate its review effort without reviewing it.

原文の言語: 英語

improve-claude-code

Triage and batch-implement Claude-tagged Things todos as PRs for the claude config repo, discover improvement candidates from session history, or watch open PRs to implement review feedback and close shipped todos. Use when the user wants to work on their…

原文の言語: 英語

ship

Finish a branch: infer which review passes the change warrants, run them, open the PR, babysit CI to green, triage bot comments, and refresh the body from a clean context.

原文の言語: 英語

tdd

Test-driven development. Use when building a feature or fixing a bug test-first, when the user asks for red-green-refactor, or when a change needs its tests written before its implementation.

原文の言語: 英語

agent-ideas

Harvest agent-tooling ideas from prominent developers.

原文の言語: 英語

gitlab-ci-monitor

Watch GitLab CI and investigate pipeline failures. Use when a pipeline or job is failing or red, when watching MR CI, branch builds, or a specific pipeline, when waiting for CI to go green, or when authoring or validating .gitlab-ci.yml.

原文の言語: 英語

pull-request-create

Create a pull request, merge request, or change request (PR, MR, CR). Use when the user asks to open one, including right after committing changes.

原文の言語: 英語

pull-request-update

Update a pull request or merge request body to reflect the current state of changes. Use when a PR/MR has evolved through additional commits and the body needs to reflect what will be merged.

原文の言語: 英語

github-pr-comments

Fetch, reply to, and resolve review threads on a GitHub pull request. Use when checking what review feedback needs addressing, whether threads are resolved, replying to review comments, or clearing AI-reviewer threads after acting on them.

原文の言語: 英語

gitlab-merge-request

Working with GitLab merge requests via glab. Use when creating, updating, reviewing, or merging MRs, enabling auto-merge or merge trains, requesting or re-requesting reviewers, handling approvals, or working review threads, discussions, and draft notes. Load…

原文の言語: 英語

pull-request-follow-up

Follow up as the author on review feedback on your PR/MR: triage and draft replies, catch silent resolves, and drive bot reviewers to a passing score. Triggers: "address reviewer feedback", "make the bot reviewer pass", "greptile/coderabbit review", "bot…

原文の言語: 英語

herdr

Drive the herdr terminal workspace manager: inspect workspaces, tabs, and panes, hand work to sibling coding agents in other panes (distinct from in-session `Agent` subagents), split panes for collaborative file viewing or long-running processes, and…

原文の言語: 英語

things-url

Write to Things 3 from this machine's CLI, including quick inbox captures. Prefer the things MCP tools, which reach the same writes from any machine. Use this skill for a raw json data= payload, or when that server is unreachable.

原文の言語: 英語

agent-browser

Real-browser automation via the `agent-browser` CLI. Use when a task needs an actual browser — navigating pages, filling forms, clicking, taking screenshots, scraping or extracting page data — or for exploratory testing, QA, and dogfooding of web apps. Pulls…

原文の言語: 英語

atuin-history

Report shell history from atuin's local capture. Covers what commands ran, when, where, and how they exited. Use when asked "what commands did I run", "what was I working on in the terminal", "have I ever run X", "how do I usually invoke X", or about recent…

原文の言語: 英語

mac-jxa

Reference for writing JXA (JavaScript for Automation) scripts run through `osascript -l JavaScript`. Covers the JavaScriptCore ES5 constraints, `run(argv)`, and the `Application()` bridge.

原文の言語: 英語

performance-hill-climb

Use when asked to make software faster or leaner (runtime, startup, throughput, memory, bundle size) through repeated measured changes. For prompts or skills scored by an eval suite, use prompting:hill-climb.

原文の言語: 英語

prompting-hill-climb

Hill-climb a skill, agent, rule, or CLAUDE.md against its eval suite. Use when changing one to raise an eval score, when judging whether a score change beat noise, or when testing whether an instruction still earns its tokens.

原文の言語: 英語

review-follow-up

Follow up as the reviewer on a PR/MR you reviewed: did the author's fixes actually grasp each concern you raised, or just go through the motions? Finds silently resolved or mechanically-fixed threads and returns a graded re-review call. Use when you left…

原文の言語: 英語

issue-refine

Refining issues with technical context and structured details. Use when asked to refine, draft, or write up an issue, including expanding a brief bug, feature, refactor, or spike (timeboxed investigation) description into a detailed issue suitable for…

原文の言語: 英語

writing-analyze

Curate the writing plugin's trope ruleset by auditing wordlist entries against session history and surfacing candidate phrases. Use when refreshing trope detection, reviewing wordlist health, or mining sessions for new AI-writing patterns to add or stale…

原文の言語: 英語

cli

Type-safe CLI argument parsing with commander and @commander-js/extra-typings, the standard parser for this repo's Bun scripts. Use when writing or editing any script that takes arguments (flags, positional parameters, subcommands, nested subcommands, --help)…

原文の言語: 英語

job

Daily routines for a corporate software engineering job. Start mode triages the inbound review queue, your own open PRs, and the issue tracker's plan for today. End mode clears the outbox, surfaces review debt, sweeps worktrees for unpushed work, and tidies…

原文の言語: 英語

review-inbox

Dispatch inbound pull request reviews as background sessions that collect in `claude agents`. Use when reviewing multiple PRs, checking the review queue, batch reviews, or managing your review inbox across GitHub and GitLab. Pass --queue to dispatch an…

原文の言語: 英語

afk

Signal that you are stepping away so the agent keeps working without stalling on prompts. Drives the current task to completion, batches reversible decisions behind safe defaults, raises only irreversible ones via push, and defers bandwidth- or power-heavy…

原文の言語: 英語

performance-benchmark

Use when timing a program or command, asking whether a change or version made it faster, or building a benchmark harness. For repeated optimization toward a target, use performance:hill-climb.

原文の言語: 英語

bun

Bun runtime patterns. Use when running bun commands, working with package.json/bun.lock, writing TypeScript scripts under Bun, or developing Claude Code plugins.

原文の言語: 英語

writing-scan

Detect AI writing tropes in repository prose. Use `audit` to scan a directory or glob (READMEs, docs, skill files, proposals) for slop already committed and gate on it, reporting every match with file, line, and column. Use `score` to measure trope density of…

原文の言語: 英語

git-conflicts

Resolve git merge conflicts from a rebase, merge, or cherry-pick. Use also for a request to finish the operation and push, such as "fix conflicts and push".

原文の言語: 英語

writing-writing

Enforce direct, concise prose style and catch writing slop. Use when writing or editing PR descriptions, issue bodies, commit messages, documentation, Slack messages, or any human-facing text. Also use when asked to clean up, rewrite, or "de-AI" existing text.

原文の言語: 英語

comments-audit

Audit code comments for AI slop: restatement, narration/decision-log, self-praise, docstring-scope, and section-divider banners. Audits a diff (the comments a change introduced) or a whole repo, ranks by intrinsic complexity, fans out judging agents, and…

原文の言語: 英語

agents-agent-team

Orchestrating Claude Code agent teams. Use when creating teams, spawning teammates, assigning tasks, configuring teammate modes, or setting up team quality gate hooks.

原文の言語: 英語

review-meat-proxy

Draft a reply that hands AI-relayed work back to its author.

原文の言語: 英語

inbox

Live inbox for reviewing inbound pull requests across forges.

原文の言語: 英語

peer

Review a pull request when requested by a peer.

原文の言語: 英語

solo

Entry skill whose name matches its plugin.

原文の言語: 判定不能