Explore

Tell the agent to zoom out and give broader context or a higher-level perspective. Use when you're unfamiliar with a section of code or need to understand how it fits into the bigger picture.

Create a detailed refactor plan with tiny commits via user interview, then file it as a GitHub issue. Use when user wants to plan a refactor, create a refactoring RFC, or break a refactor into safe incremental steps.

Search, create, and manage notes in the Obsidian vault with wikilinks and index notes. Use when user wants to find, create, or organize notes in Obsidian.

Edit and improve articles by restructuring sections, improving clarity, and tightening prose. Use when user wants to edit, revise, or improve an article draft.

Design or audit a repo-local markdown knowledge graph with wiki links, source-code backlinks, drift checks, and searchable sections. Use when AGENTS.md/CLAUDE.md is too flat for a large codebase or when a custom harness needs durable structured project memory.

Show real token usage and estimated savings for the current session. Reads directly from the Claude Code session log — no AI estimation. Triggers on /caveman-stats. Output is injected by the mode-tracker hook; the model itself does not compute the numbers.

Ultra-compressed code review comments. Cuts noise from PR feedback while preserving the actionable signal. Each comment is one line: location, problem, fix. Use when user says "review this PR", "code review", "review the diff", "/review", or invokes /caveman-review. Auto-triggers when reviewing pull requests.

Quick-reference card for all caveman modes, skills, and commands. One-shot display, not a persistent mode. Trigger: /caveman-help, "caveman help", "what caveman commands", "how do I use caveman".

Ultra-compressed commit message generator. Cuts noise from commit messages while preserving intent and reasoning. Conventional Commits format. Subject ≤50 chars, body only when "why" isn't obvious. Use when user says "write a commit", "commit message", "generate commit", "/commit", or invokes /caveman-commit. Auto-triggers when staging changes.

Decision guide for delegating to caveman-style subagents. Tells the main thread WHEN to spawn `cavecrew-investigator` (locate code), `cavecrew-builder` (1-2 file edit), or `cavecrew-reviewer` (diff review) instead of doing the work inline or using vanilla `Explore`. Subagent output is caveman-compressed so the tool-result injected back into main context is ~60% smaller — main context lasts longer across long sessions. Trigger: "delegate to subagent", "use cavecrew", "spawn investigator/builder/reviewer", "save context", "compressed agent output".

Create or review an AGENTS.md file so coding agents get stable repo-local instructions: environment setup, testing, style, security boundaries, PR policy, and handoff rules. Use when a repo lacks durable agent guidance or when a custom harness needs a predictable context file.

Repo-aware recommendation manager for ctx. Scans the active repository, identifies stack and workflow signals, recommends a capped set of skills, agents, and MCP servers, and unloads helpers that no longer match the current work after user confirmation. Harnesses are recommended by the custom-model onboarding flow or loop adapters and then attach to the same recommendation layer.

Select proportional validation for changes or reviews in the ctx repository. Use before handing off material code, workflow, migration, documentation, security, packaging, or release changes; before a PR; or when asked whether a change is adequately tested. Do not use for pure questions with no changed artifact.

Coordinate nontrivial work in the ctx repository when a task has independent investigation, implementation, or test lanes; compute-heavy checks; or repetitive changes suited to scripts or codemods. Use for decomposition and concurrency decisions, not simple edits or questions.

Design or revise concise skills with clear triggers, proportional constraints, progressive disclosure, and realistic validation.

Render an ARIS Markdown / JSON artifact (IDEA_REPORT, AUTO_REVIEW, KILL_ARGUMENT, PAPER_PLAN, research-wiki state, etc.) into a single-file HTML view designed for human reading. Academic template outputs are gated by a fresh cross-model Codex review for render fidelity + safety (the ARIS invariant). Use when the user says "渲染 HTML", "出一份 HTML 报告", "render html", "make this readable", "export to html", or wants a polished web-rendered view of a Markdown artifact. Markdown/JSON stays the canonical source; HTML is a generated, reviewed view.

Use when the user opens a Forge tab in the claw-orchestrator dashboard to start building a new ultraapp. Drives a structured Q&A interview that produces a complete AppSpec, then signals readiness to build.

把已确认的公众号终稿 Markdown 排版并写入微信公众号草稿箱。用于用户说"发布到公众号、写入草稿箱、公众号排版、换个排版主题、发小绿书图片消息"等场景。自动上传封面与文内图片，支持多主题与自定义 CSS、多账号和 server 模式。只创建草稿不群发，凭据只通过环境变量提供，未安装适配工具时交付手动发布包。

安全追踪热点、研究关键词和拆解竞品内容，并将结果转成原创选题和证据包。用于用户要求找热点、看趋势、分析爆款、研究竞品账号、拆标题或开头、比较内容结构、发现评论需求和判断时效窗口。只做公开信息研究和只读采集，不自动互动、发布或使用主账号登录态抓取竞品。

把已确认的母题或文案转成可直接拍摄、录屏或交给视频工具制作的视频方案，也支持在用户确认肖像与声音权利并完成平台手动上传后制作数字人视频，以及用合成配音和 AI 绘制画面制作无真人出镜的动画解说视频（科普、历史、品牌故事）。用于视频号、抖音、小红书视频、YouTube 横屏视频和 Shorts 的口播稿、前 3 秒钩子、分镜、字幕、录屏清单、封面、话题、配乐与授权、数字人或动画制片包、横竖屏多平台版本和发布文案。

将已确认的母题、证据和创作简报写成平台原生内容。用于 X 短帖、长帖或线程，小红书图文，微信公众号文章，视频号、抖音或小红书视频发布文案，YouTube 标题、描述、章节、标签和缩略图方案，以及同一母题的多平台适配。强调各平台独立设计标题、开头、证据顺序、结构和行动，不做机械缩写或共享正文式的一稿多发。

通用自媒体内容生产与经营工作流。用于自媒体内容创作、选题策划、热点或竞品研究、多平台改写、短视频脚本、数字人视频、动画解说视频、YouTube 与抖音视频号小红书多平台视频发布、发布包、公众号草稿、内容数据分析、周复盘、月复盘和继续未完成任务。负责识别请求类型，调用创作简报、内容策略、热点竞品、平台文案、短视频与视频制片、视频发布、数据复盘和交付归档模块，并管理方向确认、标题确认、终稿确认和发布授权。

把账号定位和业务目标转成可执行的自媒体内容策略。用于账号冷启动、重新定位、制定内容配比、规划系列栏目、建立选题池、安排周度或月度内容日历、评估产能和确定平台分工。单篇内容写作或纯数据复盘不使用此 Skill。

将自媒体创作里程碑保存成文件，管理版本、核验路径、生成完整发布包并更新内容索引。用于保存平台第一版完整成稿、多平台合集、短视频脚本、分镜、定稿、发布包和复盘报告，或用户说“保存一下、整理交付、归档、生成发布清单”时。标题微调、删一句和临时候选不单独保存新版本。

为单篇或多平台自媒体创作澄清需求并生成可确认的创作简报。用于用户只给一句话选题、一个链接、一份素材、一个产品或模糊创作要求，需要确认目标受众、内容目标、核心判断、角度、深度、调性、证据、禁区和平台差异时。纯数据分析、已确认方向后的改稿和细节微调不使用此 Skill。

分析单篇、系列、周度或月度自媒体数据并形成可执行复盘。用于读取平台后台截图、CSV、表格、公开链接或用户提供的数据，计算关注效率和深度互动，比较同平台基线，归因选题、标题、封面、开头、结构、发布时间、标签和行动，并输出加码、改包装、再适配、停止或继续收集样本的决策。

Design mobile app screens with Sleek, edit Sleek projects, and implement their designs in React Native or HTML.

用杜蕾斯黄金期（2011-2017 环时互动）那套「双层语义 + 留白」的方法产出文案与海报。先识别用户意图并给 3-5 个方案供选，再出短文案（长文案可选）+ 五种比例配图。适用于借势热点、节日节气、产品卖点、课程/知识付费推广、自媒体标题与封面、品牌人格化运营。当用户说「写个文案」「借势热点」「节日海报」「想句 slogan」「课程怎么推」「公众号/小红书封面」「像杜蕾斯那样写」「一语双关」时使用。

Comprehensive Rust coding guidelines with 265 rules across 26 categories. Use when writing, reviewing, or refactoring Rust code. Covers ownership, error handling, async patterns, concurrency, unsafe code, API design, memory optimization, performance, numeric safety, conversions, serde, pattern matching, macros, closures, observability, testing, and common anti-patterns. Invoke with /rust-skills.

为页面、组件和产品界面提供设计诊断、四方向可视化预览、设计系统编译、实现与视觉 QA， 也创作与修改微信公众号封面、B站封面、YouTube 缩略图、小绿书配图和小红书封面，按平台检查裁切与可读性。 在用户要求从零设计、重设计、优化 UI/UX、审查界面、建立设计系统、参考某种风格， 或创作公众号封面、设计公号头图、修改微信文章封面、制作 B站封面、YouTube 封面、小绿书配图、小红书配图时使用； 不用于只改业务逻辑、纯文案润色或与界面无关的普通编码。默认由当前 Codex 直接执行， 只有用户在当前任务明确点名 K3 时才调用外部模型。

Scrape, crawl, and extract data from websites. Use when users ask to scrape web pages, extract content, crawl websites, or collect data from the internet.

Comprehensive research agent for in-depth investigation. Use when users ask for deep research, comprehensive analysis, market research, academic surveys, competitive analysis, technology trends, or any topic requiring 100+ source verification. Triggers on requests like "investigate", "research", "analyze", "create a report", "comprehensive report", "deep dive", "thorough analysis".

Work with Effect v4 / effect-smol TypeScript code in this repo

Claude Mind - Search and manage Claude's persistent memory stored in a single portable .mv2 file

Reviews skill instructions, trigger boundaries and distribution contracts; not product code.

Audit Hex deps for supply-chain security risk — bidi chars, compile-time exec, maintainer changes, typosquats, CVEs. Use after mix deps.update, when checking if a package upgrade is safe, or reviewing mix.lock PR diffs.

Compress natural language memory files (CLAUDE.md, todos, preferences) into caveman format to save input tokens. Preserves all technical substance, code, URLs, and structure. Compressed version overwrites the original file. Human-readable backup saved as FILE.original.md. Trigger: /caveman-compress FILEPATH or "compress memory file"

把已确认终稿的视频成片发布到 YouTube、抖音、视频号、小红书等平台。用于用户说“发视频、同步发布、上传 YouTube、发到抖音视频号小红书、定时发布”等场景。按平台核对视频版本、封面、字幕、标题描述和 AI/版权声明，生成逐平台发布包；经用户逐平台授权后，才通过运行时可用的官方 API、填表助手或上传工具上传为私密、草稿或定时，从不一键群发。没有上传能力时交付手动发布包。

OTP/BEAM patterns and Elixir idioms — GenServer, Supervisor, Task, Registry, pattern matching, with chains, pipes. Use when designing processes or debugging BEAM issues.

Discover installable agent skills from ctx's shipped Skills.sh catalog, the Skills.sh search API, and the npx skills CLI. Use when a user asks whether a skill exists, wants to add/update a skill, or needs a repeatable procedure for finding candidate skills safely.

Take a markdown file of raw material and shape it into an article through a conversational session — drafting candidate openings, growing the piece paragraph by paragraph, arguing about format (lists, tables, callouts, quotes) at each step. Use when the user has a pile of notes, fragments, or a rough draft and wants help turning it into something publishable.

Grilling session that mines the user for fragments — heterogeneous nuggets of writing (claims, vignettes, sharp sentences, half-thoughts) — and appends them to a single document as raw material for a future article. Use when the user wants to develop ideas before imposing structure, or mentions "fragments", "ideate", or "raw material" for writing.

Shape an article as a journey of beats, choose-your-own-adventure style. The user picks a starting beat from the raw material, you write only that beat, then offer options for where to pivot next, beat by beat, until the article reaches a natural end. Use when the user has raw material and wants to assemble it as a narrative rather than an argument.

Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.

Extract a DDD-style ubiquitous language glossary from the current conversation, flagging ambiguities and proposing canonical terms. Saves to UBIQUITOUS_LANGUAGE.md. Use when user wants to define domain terms, build a glossary, harden terminology, create a ubiquitous language, or mentions "domain model" or "DDD".

Turn the current conversation context into a PRD and publish it to the project issue tracker. Use when user wants to create a PRD from the current context.

Break a plan, spec, or PRD into independently-grabbable issues on the project issue tracker using tracer-bullet vertical slices. Use when user wants to convert a plan into issues, create implementation tickets, or break down work into issues.

Set up Husky pre-commit hooks with lint-staged (Prettier), type checking, and tests in the current repo. Use when user wants to add pre-commit hooks, set up Husky, configure lint-staged, or add commit-time formatting/typechecking/testing.

Create exercise directory structures with sections, problems, solutions, and explainers that pass linting. Use when user wants to scaffold exercises, create exercise stubs, or set up a new course section.

Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes — Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/PRD asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to "review since X".

Migrate test files from `as` type assertions to @total-typescript/shoehorn. Use when user mentions shoehorn, wants to replace `as` in tests, or needs partial test data.

Generate multiple radically different interface designs for a module using parallel sub-agents. Use when user wants to design an API, explore interface options, compare module shapes, or mentions "design it twice".

Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.

Map a large, unclear, multi-session effort as linked decisions, then advance the map until the route to the destination is clear.

Classify and advance issues or external pull requests through the configured triage workflow. Use explicitly to inspect queues, evaluate an item, recommend a state, or apply an authorized transition.

Break a plan, spec, or conversation into dependency-aware, independently verifiable tickets. Use explicitly when the user wants work sliced for local planning or an issue tracker.

Synthesize an implementation-ready spec from the current conversation and relevant repository context. Use explicitly when the user wants agreed work captured as a spec or PRD.

Teach a skill or concept at the user's current level, optionally preserving a lightweight multi-session learning record.

Apply test-driven development with small, behavior-focused feedback loops. Use when the user asks to build or fix something test-first, mentions red-green-refactor, or wants integration tests.

Configure repository-local tracker, triage, and domain-document conventions needed by the Matt Pocock engineering skills.