Browse Skills

Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.

Create AI digital twins of real people from WhatsApp chat history exports. Clone your friends, colleagues, or contacts into AI agents that talk, think, and react like them. Use when the user wants to: create a digital twin, clone a WhatsApp contact into an AI agent, build a persona from chat history, make an AI version of someone, create a doppelgänger agent, or simulate a conversation with someone based on their real messages. Triggers: digital twin, clone friend, chat clone, persona, doppelgänger, twin agent, AI clone, simulate person, WhatsApp clone, chat personality, mimic friend. Important: Requires explicit consent from the person being cloned. Always confirm permission before proceeding.

Interview the user relentlessly about a plan, document, content piece, or design until reaching shared understanding and resolving each branch of the decision tree. Use when the user wants to stress-test a plan, get grilled on their design, or says “挑战/拷打这个方案、文档、内容、设计” or “grill me”.

Generates conventional commit messages from staged changes. Use when committing and needing a well-formatted message. Do not use for full PR prep; use pr-prep.

Comprehensive guide for creating software diagrams using Mermaid syntax. Use when users need to create, visualize, or document software through diagrams including class diagrams (domain modeling, object-oriented design), sequence diagrams (application flows, API interactions, code execution), flowcharts (processes, algorithms, user journeys), entity relationship diagrams (database schemas), C4 architecture diagrams (system context, containers, components), state diagrams, git graphs, pie charts, gantt charts, or any other diagram type. Triggers include requests to "diagram", "visualize", "model", "map out", "show the flow", or when explaining system architecture, database design, code structure, or user/application flows.

Professional graphic design principles for digital and print media. Use when creating visual designs, choosing color palettes, typography, layouts, or providing design feedback.

Self-improving skill that analyzes conversations for corrections and preferences, then persists them to skill files with optional Git versioning. Use when: (1) User runs "/reflect" or "/reflect [skill-name]" to manually extract learnings, (2) User says "reflect on" or "reflect off" to toggle automatic reflection, (3) User says "reflect status" to check mode, (4) User wants Claude to remember corrections for future sessions. Supports manual and automatic (hook-based) modes.

Automate common Word/WPS document operations on Windows via COM (read text, replace, insert, headings, headers/footers, page breaks, merge, split, export to PDF/TXT, add/replace images). Use for single-document actions (no batch).

Use when building TypeScript applications requiring advanced type systems, generics, or full-stack type safety. Invoke for type guards, utility types, tRPC integration, monorepo setup.

用《高性价比人生指南》(github.com/eternity4719/HowToLiveBetter) 的正文回答具体的人生决策：该不该做、值不值、怎么选、出事了先做什么、能领哪笔钱、这么干犯不犯法。先把相关条目查出来再答，按成本（钱/时间/毅力）、收益量级和证据等级 A/B/C 排序，每条都注明出自第几节第几条。触发词：该不该、值不值、要不要、划不划算、怎么选、帮我决定、这样犯法吗、能领什么、先做什么、性价比。

Extract text from PDFs with OCR support. Perfect for digitizing documents, processing invoices, or analyzing content. Zero dependencies required.

Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.

Decision-grade entity research skill — produces a hypothesis-tested dossier on a specific company, person, nonprofit, or government org, not a generic profile. Forcing intake makes the user state their hypothesis upfront (what they already believe and want to verify or disprove) so the dossier tests it rather than confirms it. Output is an editable Word document (.docx) with verdict on the hypothesis, identity facts, 12-month activity timeline, network signals, reputation signals, red flags, 3-5 conversation hooks tied to specific findings, and source-provenance audit log. Uses WebSearch + WebFetch + free APIs (SEC EDGAR, GitHub, ProPublica Nonprofit Explorer) as workhorses; optional BYOK MCPs (LinkedIn, Crunchbase, Apollo, Pitchbook, SimilarWeb) enhance coverage. Triggers: 'research [company]', 'dossier on [person/company]', 'background check on [entity]', 'prep me for a meeting with [person/company]', 'due diligence on [company]', 'what should I know about [entity]', 'research [person] before I [meet/hire/invest]', 'competitor research on [company]', 'investor diligence [company]', 'interview prep for [company]'. Honors sensitivity exclusions for journalism + personal-vetting contexts.

Backup Clawdbot workspace and config to GitHub with git-crypt encryption. Use for daily automated backups or manual backup/restore operations.

OpenClaw skill discovery, security vetting & install. Searches 3000+ curated skills from ClawHub registry and awesome-openclaw-skills catalog. Scores credibility, detects prompt injection & malicious patterns, manages installations. Quick-checks GitHub for new skills.

Memory consolidation protocol. Reviews all stored memories, merges duplicates, removes noise and credentials, rewrites unclear entries, and enforces TTL expiration. Use when the user asks to clean up, consolidate, or review their memories. Also triggers automatically after sufficient activity (configurable).

Compress large language models using knowledge distillation from teacher to student models. Use when deploying smaller models with retained performance, transferring GPT-4 capabilities to open-source models, or reducing inference costs. Covers temperature scaling, soft targets, reverse KLD, logit distillation, and MiniLLM training strategies.

Your habits, imprinted on AI. Learns how you work from conversation, builds a portable profile, and applies judgment that adapts to you: when to act, when to check with you, when to follow the project's rules over your own defaults. Use this skill whenever the user starts a new session, opens a project, writes or reviews code, debugs, plans, or writes commits. If .dna.md does not exist yet, start the onboarding conversation before doing anything else. Active in almost every working session.

Build and query embedded GraphRAG knowledge graphs with DuckDB-backed vector, full-text, and hybrid search. Use when the user wants to store entities and relations, run RAG over a graph, extract knowledge graphs from text with DSPy, run graph algorithms (PageRank, centrality, components), merge/upsert nodes and edges, fuzzy-dedupe an existing graph, or visualize interactively in a browser. Trigger phrases include "knowledge graph", "GraphRAG", "graph database", "hybrid search", "extract entities and relations", "DuckDB graph", "embedded graph store", "dedupe graph nodes".

Build chat interfaces for querying documents using natural language. Extract information from PDFs, GitHub repositories, emails, and other sources. Use when creating interactive document Q&A systems, knowledge base chatbots, email search interfaces, or document exploration tools.