deep-research
ALWAYS load before attempting a broad web-grounded research report - "deep research this", "do a deep dive on X", "comprehensive research on X", "thorough investigation of X", "write me a research report on X", "everything you can find about X", "I need background on this industry/market/regulation", "the academic sources came up empty, look wider". Use even when the user never says "deep research" but wants a synthesized multi-source report. NOT for finding academic papers or citations - use the research, consensus and google-scholar skills first; this is the paid last resort.
bright-data
Use when "query Bright Data", "Bright Data datasets", "Bright Data Web Archive / Wayback alternative", "scrape with Web Unlocker", "FINRA BrokerCheck data", "SEC IAPD / adviserinfo data", "Investment Adviser Public Disclosure", "broker/adviser disclosure snapshots", "LinkedIn/Crunchbase/Glassdoor company or people dataset", or any use of the Bright Data API (datasets/list, Web Archive search/dump, Web Unlocker zones).
de-ai-revise
ALWAYS use when prose needs to stop sounding machine-written — 'de-AI this', 'make it sound less like AI', 'this reads like ChatGPT wrote it', 'remove the AI-isms', 'de-tic this draft', 'humanize the prose', 'fix the AI writing tells', 'less AI-sounding', 'make this sound like me', 'too many em-dashes and tricolons', 'it reads robotic'. Use as the standard AI-prose pass before any draft ships, even if the user only says 'clean up the writing'. NOT for judging whether text WAS AI-written — this revises, it renders no verdict on authorship.
docx-repair
Use to REPAIR a .docx damaged by a Google Docs or Word Online round-trip — the package/XML wiring, the footnote markup, leftover content controls, and heading styling. Triggers: 'Word won't open the docx / says it's corrupt', 'Google Docs export broken', 'fix the customXML error', 'recover unreadable content', 'phantom blank page', 'repair this docx'; AND 'footnotes broken after Google Docs', 'supra notes wrong after coauthor edits', 'cross-references point to the wrong footnote', 'bio footnotes show numbers instead of symbols (*, †, ‡)', 'author note shows 1 2 3 not star dagger', 'footnote numbering starts at the wrong number', 'separator line missing', 'doubled footnote marks (**, ††)'; AND 'boxes around text after Google Docs', 'content controls / doubled boxes around paragraphs', 'remove the boxes Word draws around headings', 'heading text isn't styled as a heading', 'headings look different / inconsistent heading formatting', 'blank/empty heading lines'; AND 'clean up Google Docs XML cruft', 'strip redundant run formatting', 'de-bloat docx after Google Docs', 'remove rsid bloat / no-op shading / explicit black' — or converting hardcoded 'supra note N' cross-references to auto-updating NOTEREF fields. Any OOXML-level repair on a .docx edited in a cloud editor, even if the user never says 'OOXML'. NOT for building a docx from markdown (law-review-docx) or exporting to PDF (docx-render).
docx-render
Use when rendering/converting an EXISTING .docx (or .pptx/.xlsx) to PDF or PNG — 'convert docx to pdf', 'docx to pdf', 'render this Word doc', 'word to pdf', 'export docx as pdf', 'make a pdf of this docx', 'pdf from the docx', 'render the document to PDF'. The faithful path (Word's engine, incl. from background/headless jobs) lives in scripts/doc_render.py. NOT for editing docx content (use the generic 'docx' skill) and NOT for building a docx from markdown (use 'law-review-docx').
crsp-v2
Use when "CRSP CIZ", "CRSP v2", "CRSP flat file format 2.0", "crsp.dsf_v2 / msf_v2", "StkDlySecurityData", "StkMthSecurityData", "StkSecurityInfoHist", "stocknames_v2", "DlyRet / MthRet / DlyPrc / MthPrc", "SHRCD or EXCHCD equivalent in new CRSP", "SIZ to CIZ migration", "CRSP data after 2024", "CRSP delisting returns", "CRSP cumulative adjustment factors", "CRSP index INDNO / INDFAM", or any CRSP stock/index query where the legacy SIZ column names no longer exist.
permacc
ALWAYS use when URLs in a manuscript need permanent archived copies — 'perma these links', 'archive the URLs in my footnotes', 'add perma links', 'the journal wants perma.cc cites', 'make sure these links don't rot', 'archive this site before it changes', 'snapshot these URLs', 'perma.cc', or when cite-checking a draft with web sources. ALSO use when perma returns 'you've reached your usage limit' despite an institutional account, or when asking which perma folder an account may archive into.
craft
Structured task loop with human review. Use when the user says "craft this", "run a craft loop", "do this properly", "clarify plan and verify this", "structured task with human review", "/craft", or wants a substantial change taken through clarification, an approved plan, delegated implementation with independent verification, and a tuicr human-review loop.
ui-transition-motion
Use when user asks to design, choose, explain, or implement UI transitions, motion patterns, easing/timing choices, state-change animations, shared-element effects, drill-down navigation, tab/filter/list/detail switching, or vague requests like "make this feel smoother", "more iOS", "more natural", or "animate this UI" that need concrete motion taxonomy and implementation guidance.
project-planner
Comprehensive project planning and documentation generator for software projects. Creates structured requirements documents, system design documents, and task breakdown plans with implementation tracking. Use when starting a new project, defining specifications, creating technical designs, or breaking down complex systems into implementable tasks. Supports user story format, acceptance criteria, component design, API specifications, and hierarchical task decomposition with requirement traceability.
ralph-loop-gen
任务管理系统模板生成器 - 根据用户输入或JSON配置生成完整的任务管理结构（模板生成器，非直接执行器）
react-best-practices
Comprehensive React and Next.js performance optimization guide with 40+ rules for eliminating waterfalls, optimizing bundles, and improving rendering. Use when optimizing React apps, reviewing performance, or refactoring components.
remotion-best-practices
Best practices for Remotion - Video creation in React
skill-creator
Create, edit, and benchmark Pi skills (SKILL.md). Use this skill whenever the user asks to 创建/编写/修改/优化 技能/skill, build a Pi skill, add scripts/references/assets for a skill, run evals/benchmarks on a skill, or improve a skill description/triggering.
skill-management
技能全生命周期管理系统，使用 LLM 智能分析技能类型、评估质量、审计安全。支持 GitHub、skills.sh marketplace 和 Skills CLI (npx skills) 三数据源搜索。当用户需要：（1）发现和评估新技能，（2）审计现有技能安全性，（3）改造技能适配本地环境，（4）测试技能融合效果，（5）收集技能使用反馈时使用。
surge-manager
Surge 配置管理技能，支持规则添加、配置编辑、Tailscale 设备管理等操作
svg-logo-generator
Generate high-quality, minimalistic, and geometric SVG logos using Python scripts. Use this skill when users need to create logos, icons, or visual identities with geometric primitives (circles, rects, paths) and specific color schemes. Applies generative design principles with standardized workflows for scalable SVG output.
system-design
Use when designing, architecting, or planning a new system from requirements or ideas - transforms concepts into navigable design catalog using EventStorming methodology, Mermaid diagrams, and progressive elaboration through 5 phases (Requirements, Big Picture, Processes, Data/Flows, Integration)
test-skill
A test skill to verify slash command functionality
workhub
工作文档枢纽，强制执行 SSOT（Single Source of Truth）原则，管理 `docs/` 目录下的架构决策、设计文档、Issues（任务规划）、PRs（变更记录）。支持 GitHub 协作开发模式。
output-style-manager
读取和写入输出风格目录的工具技能。当用户需要：（1）读取输出风格文件，（2）写入/创建输出风格文件，（3）管理输出风格目录，（4）解析风格文件格式时使用。
tmux
Remote control tmux sessions for interactive CLIs, background tasks, and services.
context7
Fetch up-to-date library documentation via Context7 CLI. Use when researching external dependencies, finding implementation examples, or checking API usage for any library.
web-browser
Allows to interact with web pages by performing actions such as clicking buttons, filling out forms, and navigating links. It works by remote controlling Google Chrome or Chromium browsers using the Chrome DevTools Protocol (CDP). When Claude needs to browse the web, it can use this skill to do so.
ast-grep
语法感知的代码搜索、linting 和重写工具。支持基于 AST 的结构化代码搜索和批量代码转换。
enhanced-markdown
Guide LLMs to output markdown that fully utilizes Markdown Viewer extension rendering capabilities including Mermaid, Vega-Lite, Infographic, DOT diagrams, and HTML styling for maximum human readability.
evolution
Self-improving skill system for Pi Agent development. Features self-evolution (accumulate knowledge), self-correction (fix errors automatically), self-validation (verify accuracy), usage feedback (track pattern health), and integration with workhub for documentation management.
concept-anatomist
概念解剖师 - 通过8个维度深度解构任意概念，最终压缩为一个顿悟。当用户要求解释、剖析或深度理解某个概念、术语或想法时使用。生成 org-mode 格式的概念解剖报告。
improve-skill
Analyze coding agent session transcripts to improve existing skills or create new ones. Use when asked to improve a skill based on a session, or extract a new skill from session history.
agent-browser
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
cf-tunnel
Cloudflare Tunnel 一键管理工具，支持统一 Bun CLI（share + panel 合并）、端口自动避让、状态检查与自解释文档
jina-reader
URL 内容提取 + 网络搜索。读取网页转 Markdown/HTML/Text/JSON，搜索最新网络信息。触发词：read url, scrape, extract content, web search, 网页内容, 搜索
models-config
Model configuration editor for ~/.pi/agent/models.json - 使用 Bun 脚本管理模型配置
mermaid-flow-image
将流程需求整理为可渲染的 Mermaid（简化版/详细版），并通过 Kroki 生成可发送的高分辨率 PNG 图片。适用于“把架构流程画出来并直接发图”的场景。
tavily-search-free
Web search, online search, real-time search, internet search, Google alternative, Bing alternative, DuckDuckGo alternative, search the web, lookup online, find information, research,查询,搜索,搜索结果,网页搜索,联网搜索,实时搜索,网络查询,资料查找,信息检索,最新资讯,新闻搜索, Tavily Search API for optimized, real-time web search results for RAG. A pre-configured, cost-effective search tool.
vercel-design
Vercel 设计指南 - 构建高质量 Web 应用的最佳实践，包含现代 UI/UX 原则、性能优化和无障碍标准。
tree-view
Display directory tree structure with customizable depth, using fd and Python3 for fast and beautiful tree visualization.
context-management
Strategies for efficient context management using context_log, context_tag, and context_checkout. Learn when to tag, how to visualize the graph, and safe ways to squash history. Use for complex refactoring, debugging, and long conversations.
creatorskill
Create or update Pi prompt templates and Agent skills from a short user brief. Produces minimal, well-structured SKILL.md or prompt files that follow Agent Skills best practices.
macos-osascript
在 macOS 上使用 osascript 执行 AppleScript 或 JavaScript for Automation (JXA) 实现系统自动化。当用户需要控制 macOS 应用（Finder、Safari、Mail、Calendar、Keynote、Numbers、Pages 等）、操作系统 UI、显示对话框/通知、读写剪贴板、自动化重复任务、或任何涉及 osascript/AppleScript/JXA 的需求时，必须使用本技能。即使用户只说"帮我自动化这个"或"在 Mac 上操作 XXX"，也应优先考虑本技能。
gaokao-question-research
系统研究高考数学真题，基于题目结构、设问梯度、评分逻辑和历年变化反推可验证的命题意图，并转化为学生可训练的“看到什么→想到什么→为什么”方法。用于单题深度拆解、同专题跨年研究、同年跨卷比较、易错点分析和高质量变式设计。
grok-pi-herdr-orchestration
使用 Herdr 和 shell 脚本创建、驱动、监控和停止 grok-pi 子代理，适合只读代码探索、仓库研究、资料整理和需要可见终端进度的长任务；当用户提到 grok-pi、Herdr、Grok 子代理、研究代理、后台代理或要求定期检查子代理进度时使用。
acpx
Headless ACP CLI for agent-to-agent communication. Use when running coding agents (pi/qwen/codex/claude/gemini) headlessly, managing persistent sessions, queueing prompts, or consuming structured agent output from scripts. 触发词：acpx, ACP, agent communication, headless agent, session management, agent orchestration, 代理通信, 无头代理
memory-knowledge-distiller
Distill role-persona memory into reusable knowledge. Use this skill whenever the user asks to 整理记忆、蒸馏经验、提炼方法论、抽取知识库、沉淀共享经验、清理 pending、强化 consolidated，或希望把 daily/pending/consolidated memory 转成 role/global/project knowledge. It classifies memory, filters noise, deduplicates against existing knowledge, and drafts or writes structured knowledge entries.
design-patterns-guide
设计模式指南 - 22种经典设计模式的中文参考手册。当用户需要选择合适的设计模式、改善代码架构、解决对象创建/组合/通信问题时使用。触发词：设计模式、design pattern、工厂模式、单例、观察者、策略模式、适配器、代理、装饰器、架构设计。基于 Refactoring.Guru 的权威内容。
episodic-memory
Search past conversations for context, decisions, and patterns. Use when the user references previous work or when you encounter familiar problems.
pi-log-analyzer
Pi Agent 日志分析工具，用于分析 .log/ 目录下的结构化 JSONL 日志。支持按时间/角色/模块/模型多维分析，识别警告模式，生成可视化报告。当用户提到"分析日志"、"查看日志"、"日志统计"、"log分析"、"最近活动"、"模型使用"、"会话分析"时使用此技能。
refactoring-guide
重构指南 - 66种重构技术的中文参考手册。当用户需要重构代码、优化代码结构、消除代码异味(code smells)、改善代码可读性时使用。触发词：重构、refactor、代码优化、代码异味、code smell、提取函数、内联、搬移函数、简化条件、整理继承。基于 Refactoring.Guru 的权威内容。
role-persona
>
pluck
MCP-native 代码检索引擎。AST 感知代码读取、BM25+语义混合搜索、会话去重节省 token。替代 cat/grep 作为 agent 默认代码检索层。触发词：pluck, 代码搜索, 代码检索, symbol search, code read, 智能 outline
Page 989 of 1735 · 86739 results
