菜单
SkillsMP 已收集 jleechanorg/claude-commands 中的 447 个 Skill。打开任一 Skill 可查看来源和详情。
已展示 40 / 447 个已收集 Skill。
Token-efficient second opinion slash command /advice. Extracts decision point + artifact (≤150 lines), then fans out in parallel: (1) Opus subagent reviewer with fallback chain codex→agy→cursor, (2) /research on the decision topic, (3) /secondo multi-model…
原文语言：英语
Use this skill when working in repositories managed by Agent Orchestrator or when the user asks how to use `ao` properly. Covers the default AO workflow: bootstrap with `ao start`, dispatch work with `ao spawn`, inspect progress with `ao status` or `ao…
原文语言：英语
Generate a full agento PR status report — draft readiness, canonical /green, zero-touch rate, inline display, and Slack summary.
原文语言：英语
Pre-spawn checklist for Agent Orchestrator worker dispatch.
原文语言：英语
Use BEFORE bulk or iterative AO spawns over 3 workers. Respect the channel max_spawn setting, enforce the absolute 30-worker cap, spawn at most 15 per batch, and never use load average as the gate.
原文语言：英语
Build apps with the Claude API or Anthropic SDK. TRIGGER when: code imports `anthropic`/`@anthropic-ai/sdk`/`claude_agent_sdk`, or user asks to use Claude API, Anthropic SDKs, or Agent SDK. DO NOT TRIGGER when: code imports `openai`/other AI SDK, general…
原文语言：英语
Run or maintain the cmux approval worker that scans cmux terminal surfaces for approval dialogs, classifies them with `codex exec`, and sends the matching approval key. Use when testing or operating the launchd-based auto-approver, debugging missed prompts,…
原文语言：英语
Create Excalidraw diagram JSON files that make visual arguments. Use when the user wants to visualize workflows, architectures, or concepts.
原文语言：英语
How to run pairv2 directly and via the benchmark script, including what "minimax" means as a CLI option
原文语言：英语
Use when you have a spec or requirements for a multi-step task, before touching code
原文语言：英语
Aside browser is the PRIMARY browser tool for all Hermes/Claude/Codex work. Use aside CLI (repl/mcp/exec modes) or aside-mcp before Playwright MCP / superpowers-chrome. Use when opening browsers, scraping, UI tests, localhost verification, cookie injection…
原文语言：英语
Use when the user explicitly invokes /af or /auto-factory for a coding task.
原文语言：英语
Diagnose why the automation system is not autonomously completing draft readiness and driving PRs to green. Invoked by `/auton`; measures canonical zero-touch readiness, detects stale sessions, and reviews worker outcomes.
原文语言：英语
Watch one or more AO worker tmux sessions, classify their state (WORKING/IDLE/QUEUED/DEAD/COMPLETED), auto-remediate known failures (trust TUI, queued prompt), and push-notify on stuck sessions. Reuses ao-session-monitor state detection. Use /babysit to start…
原文语言：英语
Use whenever asked whether "the backup" is working, or after invoking scripts/backup-home.sh or any multi-target backup script, or when detecting config drift, missing files in repo, rsync failures, or /green-style verdicts that depend on backup state.…
原文语言：英语
Safe wrapper and settings editing playbook for ~/.bashrc — hardening protocol for editing Claude/claude CLI wrappers and model routing without breaking base claude behavior. Slash command: /bashrc.
原文语言：英语
Use when creating, querying, updating, closing, syncing, or diagnosing Beads issues with the br CLI.
原文语言：英语
Genesis vs Ralph orchestrator benchmark — runs both orchestration systems on the same project spec in isolated tmux sessions, then compares quantitative metrics (files, LOC), runs a consensus code review, does live build/test validation, and produces a…
原文语言：英语
Control real websites and authenticated browser sessions, inspect pages, complete approved UI flows, or troubleshoot browser automation. Use for general browser work, site settings, OAuth consent, existing tabs, and Slack app configuration. Uses Aside first…
原文语言：英语
Use when testing localhost URLs or web UIs. PRIMARY: aside browser (CLI / aside-mcp). FALLBACK: mcp__playwright-mcp (headless); forbids mcp__claude-in-chrome__* (requires extension).
原文语言：英语
Scrape browser traffic with Playwright → infer API endpoints → generate Python client + MCP tools artifacts.
原文语言：英语
Use when dispatching work through the Hermes gateway with /claw, especially when the task may resolve slash commands or hand off into AO worker orchestration.
原文语言：英语
Backup all cmux workspaces, surfaces, and their current working directories via the socket API. Produces a timestamped JSON snapshot at ~/.cmux-backups/.
原文语言：英语
Run or maintain the cmux approval worker that scans cmux terminal surfaces for approval dialogs, classifies them with `codex exec`, and sends the matching approval key. Use when testing or operating the launchd-based auto-approver, debugging missed prompts,…
原文语言：英语
Set Claude Code's builtin /goal for yourself (the running session) via the cmux socket CLI — types the /goal command into your own composer so the Stop hook + purple UI indicator activate. Use when the user asks you to set your own goal, when /ironclad step 3…
原文语言：英语
Control cmux tabs, workspaces, and terminal panes via Unix socket. Use when reading terminal output, sending commands to another agent's pane, switching tabs, or monitoring coder progress.
原文语言：英语
User-scope code/diff/PR review against the user-wide standards — ZFC, ZFC leveling, root-cause-first, and the ponytail (lazy senior dev) ladder. Dispatched by the /code-standards command.
原文语言：英语
Codex-native AO evolve loop. Run a deterministic local observe/measure cycle, then optionally delegate targeted fixes via /claw using the canonical evolve-loop skill.
原文语言：英语
Run the Dark Factory DOT pipeline runner against a goal.
原文语言：英语
Final whole-docset publishability gate for design-retro / adversarial-doc swarm workflows. Use as the LAST stage of any design-retro, solutions-hardening, /innov, pr-retro, or code-quality-swarm run, after all writer/verifier lanes finish and before the PR…
原文语言：英语
Diagnose and fix AO lifecycle-worker backfill failures (stale worktrees, branch conflicts, claim_failed loops)
原文语言：英语
Use when checking local disk capacity, investigating disk growth, or reviewing safe cleanup candidates.
原文语言：英语
Use when diagnosing disk capacity or growth and when previewing repository-gated cache, temp, or worktree cleanup.
原文语言：英语
Use when a user asks why a disk is filling, what uses its capacity, what grew over time, or what can be safely reclaimed.
原文语言：英语
Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', or requests to produce professional documents with formatting like tables of…
原文语言：英语
Lifecycle contract for opening PRs, driving them green, and fixing CI. Triggers on: opening a PR, driving a PR to green, fixing CI on a PR, /green, /es, /er, /advice on a PR.
原文语言：英语
Autonomous improvement loop for AO + Antigravity — observe, measure, diagnose, fix, repeat. Targets zero-touch rate as quality metric.
原文语言：英语
Enforcement rules for reviewing evidence artifacts against the evidence-standards skill. Invoked by /er. Produces PASS / PARTIAL / FAIL / INCONCLUSIVE verdicts.
原文语言：英语
General cross-project evidence standards (user scope). Use for the /es skill. Repo-level .claude/skills/evidence-standards.md files add project-specific extensions — always consult both.
原文语言：英语
Generic autonomous improvement loop — observe, measure, diagnose, fix, repeat. System-agnostic framework; configure a system profile to target any repo/agent/IDE ecosystem.
原文语言：英语