Claude Code Skills · page 57

Move bytes between Gini upload space, external URLs, and workspace files. Used by every attachment / file-upload / file-download flow regardless of the target system (Linear, GitHub, S3, Notion, etc.).

File a locally-captured, already-redacted Gini crash report as a GitHub issue, with the user's consent. Reads the pending crash queue and delegates the actual filing to the github-issues skill.

Create, search, triage, label, assign, comment on, and close GitHub issues using the gh CLI, with a curl REST fallback.

Detection engine for Gmail email watches: iterates the watch list, polls gws for new matching mail per watch, dedups, drops automated/self, and hands matches (labeled by sender) to the shared drafting turn. Provisioned and run automatically by the shared email-watch backing job.

Sign a Google account into its own gws config dir and register it (tagged). Used by google-workspace-setup; runs the OAuth login + records the account.

Google Calendar via gws: list events, create, accept, find free time.

Google Docs via gws: read, append text, structured batch edits.

Google Drive via gws: search, list, upload, download, share.

Google Forms via gws: create forms, add items, read responses.

Gmail via gws: send, read, search, label, draft, reply, forward.

Google Meet via gws: create spaces, fetch join links, list recordings.

Google Sheets via gws: read/write cells, append rows, structured batch edits.

One-time setup for gws: install, OAuth, scopes, auto-approve.

Read and write Linear issues, comments, projects, cycles, users, documents, initiatives, milestones, and more via the Linear MCP server. Attach chat-uploaded screenshots to issues.

Place outbound AI phone calls via Bland AI: book reservations, make appointments, ask businesses questions, then report back the transcript and summary.

Operator's guide to the YC CLI (`yc`) for the Gini batch demo — scoped to the yc commands the demo actually uses: the validated browser-forward login flow (tmux + browser_connect) and investor research against Bookface. Assumes yc is installed but NOT logged in yet. Load before staging or running the demo.

Build and maintain a company knowledge base as a wiki of interlinked markdown notes in the workspace — a private, compounding Wikipedia. Use when the user wants to start or organize a knowledge base / wiki, ingest sources (URLs, documents, pasted notes) into it, ask questions answered from it, or audit (lint) it. Defines the wiki layout (SCHEMA / index / log / raw / pages), the frontmatter contract, [[wikilink]] conventions, and a deterministic lint script that catches broken links, orphan pages, index drift, and frontmatter problems.

Author a new SKILL.md from a user prompt, or migrate an existing non-spec skill to the Anthropic Agent Skills format.

Install a pasted SKILL.md (or one fetched from a URL or file path) into the user-skill directory, reviewing risk and connector requirements.

Turn LinkedIn connections (or any contact export) into a queryable personal CRM using the agent database.

Use when developing PenguinHarness itself — changing packages/{core,server,web,cli,desktop,landing,docs,skills}, the built-in model catalog, the installers or the release workflow; writing or auditing changelog entries; writing a blog post or capturing release screenshots; deciding what to do about data already on disk; or auditing prose that reads like a leaked authoring session. Covers the two-repo symlink layout, the CI-parity verification chain, the record-and-ship contract, where blog media is hosted, and the seams that are intentional.

Use when changing the PenguinHarness Web App (`packages/web`) — adding or restyling any UI, picking a status colour, adding an icon, laying out a row or a form field, writing user-facing copy, or building a popup. Covers the semantic tone tokens, the icon size/stroke/gap scale, the semantic-versus-formatting rule for explanatory text, the two-dictionary i18n contract, and the portal-panel pattern with its Esc and scroll caveats.

Run one specified Test Agent on one specified Benchmark Case exactly once, privately score that execution, and return one protocol result.

Initialize an Agent's settings from a user requirement by writing AGENTS.md, setting identity metadata, and installing only needed Skills.

Improve an Agent State through versioned scores and score-linked Traces from a frozen Benchmark.

Call model APIs through @prismshadow/agenthub — streaming text generation, image generation, speech synthesis, embeddings and the supported-model registry with one client.

Design and calibrate a multi-Case capability Benchmark and establish a traceable Formal Baseline.

Create and edit Bento presentations — self-contained .bento.html decks whose document is JSON. Use whenever the user wants a slide deck or presentation: from scratch, from source material, or by improving an existing file.

Complete data-analysis tasks with bounded inspection, correct data semantics, native artifact handling, complete delivery, and risk-based verification.

Search the web and scrape pages into clean markdown with the Firecrawl API — query-based discovery, single-URL extraction including public PDFs, driven by curl with a vault-stored API key.

Rewrite or edit prose in any language so it reads like edited human writing in the register of books, newspapers and encyclopedias rather than default AI output. A small drafting core — vary every pattern, build density from anchored facts in whole grammar, cap the quotables, put a real writer with real material behind the text, let structure serve content, write each language from inside its idiom and typography, verify what you assert, and aim for the natural distribution of edited prose rather than a perfect scorecard — backed by a three-layer tell catalog, per-language cue files for six languages and a seven-round measured case study shipped as reference files for the diagnostic census.

Fine-tune LLMs with LlamaFactory — register datasets, train via YAML configs, merge LoRA adapters and serve the result.

Deploy and serve local models with Ollama — pull and run them, then expose the OpenAI-compatible endpoint to apps and agents.

Manage model API keys, default models and per-agent vault secrets with the penguin CLI.

Drive PenguinHarness itself from a shell — list and create agents and sessions, send and steer messages mid-flight, and query costs and scheduled tasks via the penguin CLI over the local server.

Use whenever the user wants to build an agent application — their own program with an embedded agent, such as an AI app, an agentic app or a RAG app. This is writing application code on the Penguin Harness SDK, not configuring an Agent State inside PenguinHarness. Covers self-contained projects, the createSession/run streaming loop with thinking and image messages, wiring the user's existing tools in as CLI commands, and a complete RAG recipe that ingests documents into a knowledge base and answers with citations behind a web UI.

Run Claude Code on a remote host over SSH — a persistent expect-driven login session, headless claude -p with the stdin fix, the interactive TUI inside a remote tmux driven by send-keys/capture-pane (one keystroke at a time, capture-verified; relayed user messages go through verbatim), and multi-turn continuity via --session-id/--resume or stream-json; hosts and credentials are placeholders resolved at runtime from the user or the vault, never hardcoded.

Install skills from external ecosystems into this agent's agent_state/skills/ — resolve Claude Code plugin marketplaces, the Codex plugin repo, skills.sh registry names, GitHub repos, or local folders to their skill directories, review every file, and normalize SKILL.md frontmatter to the Penguin format.

Complete software-engineering tasks — investigate and review code, implement bug fixes, features and refactors with minimal scope, validate changes, and report verified outcomes.

Deploy and serve LLMs with vLLM behind an OpenAI-compatible endpoint, with tool calling enabled for agent workloads.

Penguin visual language for generated web pages and app UIs — GitHub-style simplicity with a single blue accent, light and pure-black dark themes, design tokens, component and chat-interface recipes, plus an opt-in warm paper editorial theme.

Build a central library to manage .claude folders across projects. One repo for skills, agents, commands, hooks, and configs.

Build and verify one canonical project skill for Claude Code and Codex, or create an agent-local global skill.

Use this skill when the user asks about Ni Haisha / 倪海厦 TCM course material, especially Shang Han Lun / 伤寒论, Jingui / 金匮要略, Zhongjing Xinfa / 仲景心法, clinical cases / 临床案例 / 倪师医案, Bagang Bianzheng / 八纲辨证, Fuyang Forum / 扶阳论坛, Yijinjing / 易筋经, Liang Dong dialogue / 梁冬对话倪师, Stanford lecture / 斯坦福大学演讲, Tianji / 天纪 / 易经 / 阳宅 / 紫微斗数, Huangdi Neijing / 黄帝内经, Shennong Bencao / 神农本草, acupuncture / 针灸, meridians, acupoints, acupuncture depth safety / 危险进针深度 / 气胸风险, six-channel pattern identification, symptom-to-formula routing, formula comparison, lesson review, board/PPT screenshot evidence, or course-derived study notes. This skill is for educational distillation and study support only, not medical diagnosis, prescriptions, dosage, individualized treatment, or self-administered acupuncture.

Build and verify Superglue natural-language integrations. Use this skill when an agent is asked to plan, build, review, or verify Superglue workflows and needs plugin-specific acceptance criteria.

Run the local Agent Safehouse release flow: inspect commits since the last published release, propose the next SemVer version and changelog, present a dry-run for confirmation, then update changelog, publish the GitHub release, and publish the stable Homebrew tap when confirmed.

Review an open GitHub pull request or the current local branch and working tree with parallel, independent reviewers and evidence-based validation. Use when the user asks for code review, invokes the Code Review action from Git Review, or explicitly mentions this skill.

Create or update LiveAgent runtime skills. Use when you need to summarize a workflow into a skill, write it into the fixed user skills root, validate it, package it, or refine a skill's references for LiveAgent's SkillsManager flow.

Install, list enabled, validate, or package LiveAgent skills. Use when you need to inspect the skills enabled in the current conversation, import a local skill directory or package, search/install from ClawHub, install from a GitHub repo/tree URL, or reconcile conflicts during an upgrade.

Platform-neutral guidance for using Open Computer Use, the open-source Computer Use MCP server and CLI for macOS, Linux, and Windows. Use when an agent needs to install, verify, troubleshoot, configure, or operate Open Computer Use through its native CLI, stdio MCP server, or direct Computer Use tool calls.

>-

>-

Collect Bilibili video and creator evidence with MediaCrawler through search, exact BV detail, comments, dynamics, contacts, and optional media. Use for topic, format, title, creator, or audience research with explicit time-range and quality controls.

Collect Douyin competitive evidence with MediaCrawler using keyword search, exact video detail, comments, media, and creator profiles. Use for trend, hook, format, audience-language, or creator research that needs reproducible raw evidence and a documented selection method.

Collect Kuaishou competitive evidence with MediaCrawler using keyword search, exact video detail, comments, media, and creator profiles. Use for trend, format, audience-language, or creator research requiring reproducible source records and explicit collection limits.

Collect Baidu Tieba thread and user evidence with MediaCrawler using keyword or bar discovery, exact thread detail, replies, and creator pages. Use for community pain-point, vocabulary, objection, topic, or user research with thread-context preservation.

Collect Weibo posts and creator evidence with MediaCrawler using search, exact post IDs, comments, optional media, and creator IDs. Use for discourse, trend, messaging, audience-language, or account research requiring preserved provenance and risk-aware detail enrichment.

Collect Zhihu answers, articles, videos, comments, and creator evidence with MediaCrawler through search and exact URLs. Use for expert discourse, problem framing, objections, terminology, topic, or creator research where content type and question context must remain explicit.

Install, authenticate, configure, operate, and troubleshoot the external MediaCrawler client shared by Douyin, Kuaishou, Bilibili, Weibo, Tieba, and Zhihu collectors. Xiaohongshu uses the separate browser-first xiaohongshu-mcp Collector. Use when auditing this client, onboarding a supported platform account, selecting search/detail/creator modes, enabling comments or media, locating outputs, or diagnosing crawler failures.

渐进式研究当前产品，并把已经稳定、可追溯的产品认知增量写入根目录 SOUL.md。首次接入产品代码、原型或线上 URL，需要确认产品形态与已有能力，或某个增长 loop 在执行中发现新的产品事实、用户场景、问题与价值证据时使用。不得一次性臆造完整产品画像，也不得仅凭代码功能推断用户、问题或价值。

完整调研并确定 SEO 机会：从产品理解、领域词表拆解、关键词矩阵扩展、Bing 真实热度验证、竞品发现、实时 SERP 抓取，到头部页面的搜索引擎层、用户层和质量层拆解。需要查热词、验证搜索量、判断搜索意图、研究竞品页面、寻找信息增益缺口或决定应该做什么 SEO 页面时使用。

使用本机 browser-first xiaohongshu-mcp 只读搜索小红书、下载候选首图、补全用户选择的笔记详情，并把脱敏证据写入调用方 Memory。用于 xhs-replicate 的选题和视觉参考研究，取代小红书 MediaCrawler 路径。

根据完整的 SEO 需求与头部竞品页面证据，设计、撰写并在产品现有仓库中实现高质量 SEO 页面。需要匹配搜索意图决定工具页、资源页、教程页、比较页或解决方案页，创建页面设计文档、提高信息增益、编写 metadata、加入图片、结构化数据、内链并完成工程验证时使用。

Generate, edit, or batch-create SEO, marketing, social, and document images with Gemini or OpenAI through the repository-owned Growth Lab image client. Use when a page or content loop needs illustrations, diagrams, covers, reference-image edits, multiple candidates, or verified image text and composition. This is the only AI image-generation Executor in Growth Lab.

从目标用户的真实搜索场景出发，对抗式审查并修改 SEO 页面，找出搜索意图偏离、低信息量、批量同构、重复转化、AI 腔、术语漂移、无依据主张、metadata 问题和配图场景错位。需要审查 SEO 内容价值、降低 AI 味、检查图片相关性或决定页面保留、合并、重写、删除时使用。

使用 Bing Webmaster 页面与查询数据、索引状态、产品结果和 Bing AI Performance 证据复盘 SEO 页面，诊断收录、排名、点击率、意图、内容、转化和 AI 引用问题。需要比较周期表现、分析 citations、cited pages、grounding queries、query fan-out 或决定下一步 SEO/GEO 行动时使用。

Capture authenticated product screenshots through the repository-owned Playwright CDP script and archive them in the invoking loop's Memory. Use when content needs truthful UI evidence, reusable product screenshots, a selected component, or a full-page browser capture. Requires only user-installed uv and Chrome configured by onboarding; never depends on MCP tools, external Skills, private repositories, or external scripts.

把已批准的小红书草稿、单一分析参考和真实产品素材变成可审查卡片：先完成 DAI 与 image plan，再按确定性、完整效果或可分离图层模式制作，机械验证 PNG 与清单并运行合规检查。精确文字和真实 UI 不交给模型猜测；AI 生图需要单独配置和授权。

通过自然语言完成 Growth Lab 的统一依赖审计与配置。检查所有能力所需的 API key、可直接安装的第三方 CLI/Client、浏览器与登录态；拒绝隐含的外部 Skill 或脚本依赖，告诉用户哪些已配置、哪些缺失、从哪里获取，并允许本轮绕过。需要首次配置、检查环境、修复依赖或询问“还缺什么”时使用。

Run an SEO page observation-action-review loop with persistent Memory by coordinating demand research, page creation, adversarial review, image generation, IndexNow submission, and performance review. Use when taking an SEO page from opportunity discovery through publication, measurement, iteration, or continuing a previous SEO loop from Memory.

小红书内容增长闭环 —— 从调研找 idea、锚定爆款骨架、填入真实产品内容、生图与合规检查，到回收 24h/48h/7d 发布结果并完成复盘。用户要求出稿、复刻、月度复盘、查看发布数据或修订内容规律时使用。

Extract full context of the last task from the most recent parent session

For CLI agents WITHOUT subagent support (e.g., Codex CLI). Search previous code agent sessions for specific work, decisions, or code patterns.

Use this skill when you learn one or more design pattern(s) in the

Design patterns for the Langroid multi-agent LLM framework. Covers

>-

CLI utility to communicate with other CLI Agents or Scripts in other tmux panes; use it only when user asks you to communicate with other CLI Agents or Scripts in other tmux panes.

This skill should be used when the agent needs to give a spoken voice update to the user, or when reminded by a Stop hook to provide audio feedback. Use this skill to speak a short summary of what was accomplished.

Use this when user wants you to walk through (code or text) files in a EDITOR to either explain how some code works, or to show the user what changes you made, etc. You would typically use this repeatedly to show the user your changes or code files one by one, sometimes with specific line-numbers. This way the user is easily able to follow along in their favorite EDITOR as you point at various files possibly at specific line numbers within those files.

Log the work segment that you did after the last work log until now in a

Create a markdown document that describes a specific task along with

>-

>-

>-

Guide the user through installing, configuring, and launching

Literature-backed English technical-prose writing rules (agent-style, 21 rules). Its lane is FORMAL technical prose (papers, design docs, proposals, READMEs, commit messages). Use ONLY when the user explicitly asks for agent-style by name (e.g. "apply agent-style", "write/revise this per agent-style rules", "iterate until agent-style clean"). NOT for de-AI-ing casual or voiced text — use remove-ai-patterns for that. Do not auto-trigger for ordinary prose or documentation tasks.

Remove AI-writing patterns ("AI-isms") from text using the

Audit and rewrite content to remove AI writing patterns ("AI-isms"). Use this skill when asked to "remove AI-isms," "clean up AI writing," "edit writing for AI patterns," "audit writing for AI tells," or "make this sound less like AI." Supports a detect-only mode, an edit-in-place mode for files, an optional voice profile (casual / professional / technical / warm / blunt), and an iterate-to-convergence pass.

Run any question, idea, or decision through a council of 5 AI advisors who independently analyze it, peer-review each other anonymously, and synthesize a final verdict. Based on Karpathy's LLM Council methodology. MANDATORY TRIGGERS: 'council this', 'run the council', 'war room this', 'pressure-test this', 'stress-test this', 'debate this'. STRONG TRIGGERS (use when combined with a real decision or tradeoff): 'should I X or Y', 'which option', 'what would you do', 'is this the right move', 'validate this', 'get multiple perspectives', 'I can't decide', 'I'm torn between'. Do NOT trigger on simple yes/no questions, factual lookups, or casual 'should I' without a meaningful tradeoff (e.g. 'should I use markdown' is not a council question). DO trigger when the user presents a genuine decision with stakes, multiple options, and context that suggests they want it pressure-tested from multiple angles.

Heal skill documentation by applying corrections discovered during execution with approval workflow

Set up and configure Geoffrey Huntley's original Ralph Wiggum autonomous coding loop in any directory with proper structure, prompts, and backpressure.

Expert guidance for creating, writing, building, and refining Claude Code Skills. Use when working with SKILL.md files, authoring new skills, improving existing skills, or understanding skill structure and best practices.

{{What it does}} Use when {{trigger conditions}}.

Expert guidance for creating, configuring, and using Claude Code hooks. Use when working with hooks, setting up event listeners, validating commands, automating workflows, adding notifications, or understanding hook types (PreToolUse, PostToolUse, Stop, SessionStart, UserPromptSubmit, etc).