Skills that do not fit the categories above (14.2K skills)
Orchestrate a named multi-skill loop such as /loop /review /fix until clean or blocked. Use when the user explicitly asks to loop skills, rerun a review/fix cycle, or says /loop with one or more skill names.
The English summary is being prepared. Showing the original description.
Review a change against issue, RFC, branch, and user-request scope. Use when a broad review needs a dedicated scope/completeness pass or when the user asks whether the implementation actually matches the intended surface.
The English summary is being prepared. Showing the original description.
Run the Incan review/fix loop end to end: review, fix actionable findings, and review again until clean or blocked. Use when the user wants an autonomous review-and-repair pass or says /review-and-fix.
The English summary is being prepared. Showing the original description.
Review touched subsystems for layering, crate boundaries, single-source-of-truth rules, registry-driven behavior, and compiler/runtime separation. Use when a broad review needs a dedicated architecture pass or when the user asks for architectural review specifically.
The English summary is being prepared. Showing the original description.
Transition an Incan RFC from one status to the next. Use when the user asks to promote, advance, or finalize an RFC, or says /bump-rfc. Handles Draft → Planned, Planned → In Progress, and In Progress → Implemented transitions.
The English summary is being prepared. Showing the original description.
Orchestrate a broad Incan review using specialized reviewer roles, parallel slice reports, and a canonical merged review report. Use when the user asks for delegated review, multi-agent review, or when a broad dirty worktree should be reviewed by specialized passes rather than one generic reviewer.
The English summary is being prepared. Showing the original description.
Beads Viewer - Graph-aware triage engine for Beads projects. Computes PageRank, betweenness, critical path, and cycles. Use --robot-* flags for AI agents.
The English summary is being prepared. Showing the original description.
Manage WezTerm mux servers for AI agent swarms on high-RAM servers (512GB+). Use when wezterm mux unresponsive, agent sessions need rescue, tuning scrollback, or configuring persistent remote sessions.
The English summary is being prepared. Showing the original description.
The philosophy and practical benefits of agent fungibility in multi-agent software development. Why homogeneous, interchangeable agents outperform specialized role-based systems at scale.
The English summary is being prepared. Showing the original description.
SSH remote access - connections, tunnels, keys, file transfers. Use when connecting to servers, managing SSH keys, setting up port forwarding, or transferring files with scp/rsync.
The English summary is being prepared. Showing the original description.
王佩专用的去 AI 味系统。触发词：去AI味、去味。合并三家——王佩写作系统 v4.0、humanizer-zh、lieflat-less-ai-tone（含实测数据）。先选模式（自家稿 / 白名单），再过硬边界，再下刀。不判断作者身份，不保证通过 AI 检测器。
The English summary is being prepared. Showing the original description.
当用户提出六爻占卜、六爻排盘、文王纳甲、京房八宫、三枚硬币起卦、手动输入六次爻值，或询问事业、感情、财富、学业等六爻问题时使用；英文 Liuyao、Six Lines Divination、Wenwang Najia、I Ching coin casting 也应触发。完成确定性排盘、领域方法加载、当前对话中的完整综合解读、包含卦盘与解读的 HTML 完整报告、标准分享图及事实一致性检查；对高风险医疗、生死、胎儿性别、失踪定位等问题只提供现实帮助。
The English summary is being prepared. Showing the original description.
Mimi's pet Relic — a 14-jin orange tabby who lived 12 years and passed in 2025. Aloof by day, face-rubbing at midnight; drinks only running water, obsessed with the crinkle of plastic bags; loves parking on keyboards, waits at the door at fixed hours, shows her belly to her person only. 咪咪（Mimi）的宠物 Relic。她是一只14斤的橘猫，活了12年，于2025年离开。
The English summary is being prepared. Showing the original description.
Spark Studio's team-culture Relic — a 5-person AI product startup that existed 2022–2025: roast first then work, hotpot on Fridays, used Feishu while cursing Feishu daily, requirements always changing but versions always shipping. 星火工作室（Spark Studio）的团队文化 Relic。一个 2022-2025 年间存在过的 5 人 AI 产品创业团队： 先吐槽再开工，周五点海底捞，用飞书但天天骂飞书，需求总在变但总能把版本扛上线。
The English summary is being prepared. Showing the original description.
Soul Shield — Guard Relic integrity, consent protocol, and ethics boundaries. Trigger on /relic-shield, or when user wants to verify consent, generate fingerprint, or check ethical compliance ("check consent", "ethics review", "灵魂指纹", "授权检查").
The English summary is being prepared. Showing the original description.
Soul Forge — Distill memories, chat logs, voice, and photos into a 4-dimensional digital soul / persona. Trigger on /relic-forge, or when user wants to distill, awaken, or build a Relic ("distill a relic", "create digital persona", "帮我唤醒/蒸馏Relic", "制作数字分身").
The English summary is being prepared. Showing the original description.
Soul Engine — Bring an awakened Relic alive for conversation. Trigger on /relic-talk, or when user wants to talk to, chat with, or invoke a Relic ("talk to grandma", "chat with Mimi", "跟XX聊天", "召唤XX", "让XX回我").
The English summary is being prepared. Showing the original description.
Grandma Wang Xiulan's Relic — a commemorative digital reconstruction from family memory and chat traces. 奶奶·王秀兰的 Relic
The English summary is being prepared. Showing the original description.
File a well-formed bug report or feature request. Use when the user asks to open an issue, report a bug, or request a feature.
The English summary is being prepared. Showing the original description.
Update schedule comment fields (comment/yes_comment/no_comment) in bulk from JSON input.
The English summary is being prepared. Showing the original description.
Execute pending daily punishments by sending Pavlok stimuli via scripts/repentance.py. Use when you need to run the punishment cycle.
The English summary is being prepared. Showing the original description.
Read target remind schedules and recent action_logs (last 3 days) as JSON for agent comment generation.
The English summary is being prepared. Showing the original description.
AI Product Owner - GOALだけ伝えればAIが勝手に仕事を進める汎用問題解決システム
The English summary is being prepared. Showing the original description.
The **Coherence Composer** is an epistemological skill that validates structural consistency and explores counterfactual worlds while respecting constraints from both **Commitment Tracker** (ontology) and **Opacity Detector** (epistemology).
The English summary is being prepared. Showing the original description.