其他技能

[Planning] Use when the user asks to plan work too big for one session whose route is unclear: chart a map of decision tickets, then resolve one ticket per session until the way is clear.

中文简介正在准备中。当前显示原文说明。

[Planning] Use ONLY when the user explicitly requests a product roadmap, roadmap update or milestone selection: outcome milestones, MVP scope, non-goals, risks, evidence gates.

中文简介正在准备中。当前显示原文说明。

Runs and checks things on a remote Mac over Tailscale or SSH: non-interactive commands, tmux sessions, and service checks. Use when work must happen on another Mac you are not sitting at.

中文简介正在准备中。当前显示原文说明。

Comprehensive incident response framework from detection through resolution and post-incident review. Battle-tested SRE/DevOps practices: severity classification, timeline reconstruction, structured post-incident analysis. Use when declaring an incident, coordinating multi-team response during an outage, leading a post-mortem, or setting up on-call practices for a new service.

中文简介正在准备中。当前显示原文说明。

Diagnoses and fixes Debian Linux problems with apt, systemd, and AppArmor-aware guidance. Use when a Debian system has package, service, boot, or permission issues.

中文简介正在准备中。当前显示原文说明。

Diagnoses and fixes Fedora Linux problems with Fedora tooling: dnf, systemd, journalctl, and SELinux-aware guidance. Use when a Fedora system has package, service, boot, or permission issues.

中文简介正在准备中。当前显示原文说明。

Diagnoses and fixes Arch Linux problems with pacman, systemd, and rolling-release practices. Use when an Arch system has package, update, boot, or service issues.

中文简介正在准备中。当前显示原文说明。

Diagnoses and fixes CentOS problems with RHEL-compatible tooling, SELinux-aware practices, and firewalld. Use when a CentOS or RHEL-family system has package, service, permission, or network issues.

中文简介正在准备中。当前显示原文说明。

Use when a long session should continue in a fresh agent — context is nearly full, compaction would lose detail, or the work is moving to another tool or teammate. Compacts the conversation into a handoff document in the OS temp directory, pointing at existing specs, plans, and diffs instead of repeating them.

中文简介正在准备中。当前显示原文说明。

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

中文简介正在准备中。当前显示原文说明。

This skill should be used when the user asks to "optimize context", "reduce token costs", "improve context efficiency", "implement KV-cache optimization", "partition context", or mentions context limits, observation masking, context budgeting, or extending effective context capacity.

中文简介正在准备中。当前显示原文说明。

This skill should be used when the user asks to "offload context to files", "implement dynamic context discovery", "use filesystem for agent memory", "reduce context window bloat", or mentions file-based context management, tool output persistence, agent scratch pads, or just-in-time context loading.

中文简介正在准备中。当前显示原文说明。

Merges mature lessons from a domain memory file into its instruction file. Syntax: `/memory-merger >domain [scope]` where scope is `global` (default), `user`, `workspace`, or `ws`. Use when a domain memory file has accumulated lessons that should become permanent instructions.

中文简介正在准备中。当前显示原文说明。

Post-train LLMs with PrimeIntellect's prime-rl (async RL, SFT, distillation, evals). Use this skill whenever the user mentions prime-rl, wants to write an rl.toml or sft.toml, run `uv run rl` / `uv run sft` / `uv run eval` / `uv run inference`, pick GRPO, MaxRL, OPD or ECHO, tune IPO loss, or monitor and resume a run. Also trigger for verifiers environments, Prime Intellect post-training, reverse-text, and pydantic-config TOML overrides.

中文简介正在准备中。当前显示原文说明。

Create or maintain a source-grounded kpopper knowledge model as a versioned plugin. Use when a reusable domain model should ship independently of any one project.

中文简介正在准备中。当前显示原文说明。

Answer questions about the venue rate facts recorded in this model and identify what its source leaves unspecified.

中文简介正在准备中。当前显示原文说明。

Use when governing a worktree across its whole life — scope-lock declaration, merge-readiness status, scoped verification, and safe cleanup that refuses while unique unmerged commits exist.

中文简介正在准备中。当前显示原文说明。

Adresse les commentaires de revue sur les PR (humain + bots). Mode auto-détecté selon le type d'issue. Usage: /review [<issue#>|<PR#>]

中文简介正在准备中。当前显示原文说明。

Planifie le prochain sprint : calcule la capacité (vélocité glissante 3 sprints), reporte les tickets non livrés du sprint courant, puis complète depuis le backlog par priorité jusqu'à la capacité. Présente le plan, attend validation, puis assigne les tickets au sprint. Usage: /plan-sprint [<titre-sprint-cible>]

中文简介正在准备中。当前显示原文说明。

Break a plan, spec, or the current conversation into a set of tracer-bullet tickets, each declaring its blocking edges, published to the configured tracker — edges as text in one file per ticket locally, or native blocking links on a real tracker.

中文简介正在准备中。当前显示原文说明。

Pushes interfaces past conventional limits with technically ambitious implementations — shaders, spring physics, scroll-driven reveals, 60fps animations. Use when the user wants to wow, impress, go all-out, or make something that feels extraordinary.

中文简介正在准备中。当前显示原文说明。

Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.

中文简介正在准备中。当前显示原文说明。

Implement a piece of work based on a spec or set of tickets.

中文简介正在准备中。当前显示原文说明。

Performs a final quality pass fixing alignment, spacing, consistency, and micro-detail issues before shipping. Use when the user mentions polish, finishing touches, pre-launch review, something looks off, or wants to go from good to great.

中文简介正在准备中。当前显示原文说明。