GITHUB AGENT SKILLS / 技能收录
给你的 AI 助手
装上专业技能
我们从 GitHub 持续收录、审核并分类优质的 Agent Skills，按职业与使用场景整理，复制一行命令即可安装到 Claude Code、Cursor 等智能体。
按职业浏览 Agent Skills
为不同岗位挑选的高频技能
按使用场景浏览 Agent Skills
从你要完成的任务出发
按创作者浏览 Agent Skills
按 GitHub Stars 排序的优秀创作者
Microsoft
@microsoft
openclaw
@openclaw
OpenAI
@openai
The Apache Software Foundation
@apache
GitHub
@github
Anthropic
@anthropics
AutoGPT
@Significant-Gravitas
Garry Tan
@garrytan全部 Skills 196852
deep-research
Multi-source deep research with a routing + caching + grading harness over firecrawl, exa, tavily, perplexity, scholarly-access, tooluniverse, huggingface, and context7 MCPs. Fixes scope first via AskUserQuestion (purpose, depth, recency, output form) before any fan-out, then routes each sub-question to the best live provider, caches provider calls by query hash, grades every source by confidence, and delivers cited reports. Use when the user wants thorough, evidence-backed research.
ddi-admet-research
Use as the front-end/router for biomedical research via the tooluniverse MCP server (Harvard Zitnik lab, 2206 tools) - drug-drug interactions, ADMET/physchem prediction, CYP450 enzyme roles, target research, FDA drug labels, drug repurposing, and pharmacovigilance. Routes to the detailed tooluniverse-* skills. Use when a question needs biomedical knowledge-base lookups.
data-scraper-agent
Use when building an automated public-data collector that scrapes on a schedule, enriches records with an LLM, stores results, and learns from feedback.
data-extraction-matrix
Use when extracting structured evidence from papers into a matrix for synthesis, comparison, or review writing.
cyberstrike
暂无简介
crypto-ctf
Use for cryptography CTF challenges, crypto homework, and education when you need to actually COMPUTE an attack rather than just describe one - RSA factoring and weak-key attacks (Fermat close-primes, Wiener small-d, common-modulus, Hastad broadcast, ROCA, lattice/Coppersmith), symmetric mode.
critique-panel
Use to run the G3 CRITIQUE gate of the TCR design-review loop - a four named-persona panel (user-advocate / systems-consistency / a11y / brand-aesthetic) that each REASON over ui-audit's Track-A numbers plus the screenshot, run the NN/g "I Like / I Wish / What If" ritual, score the nine DESIGN-EVAL v1 dimensions 0-4, then synthesize a severity-ranked findings list. A TRIAGE accelerator.
credential-forge
One discipline that harvests, farms, vaults, captures, and lifecycle-manages every credential the owner already owns — 12-store auth harvester (grok/claude/zcode/ gemini/cursor/gcloud/aws/gh/scw/opencode), key-farm roster + rotation manifest (<BASE>__<account>), 1Password op:// materialize (forge-run), browser-assisted OAuth capture ladder (device-code first), JWT expiry ledger + refresh watchdog + statusline telemetry. Secret VALUES live in process memory only; names/shapes/paths on disk. Use for credential inventory, harvesting auth stores, env-var key farming, vault sync, OAuth device-code capture, token expiry checks, rotation cooldowns, or secret-hygiene audits.
tooluniverse-[domain-name]
Use when [specific triggering conditions and symptoms].
create-tooluniverse-skill
Create high-quality ToolUniverse skills following test-driven, implementation-agnostic methodology. Integrates tools from ToolUniverse's 1,264+ tool library, creates missing tools when needed, tests thoroughly, and produces skills with Python SDK + MCP support.
council
Convene a four-voice council for ambiguous decisions, tradeoffs, and go/no-go calls. Use when multiple valid paths exist and you need structured disagreement before choosing.
cost-tracking
Track and report Claude Code token usage, spending, and budgets from a local cost-tracking database. Use when the user asks about costs, spending, usage, tokens, budgets, or cost breakdowns by project, tool, session, or date.
cost-aware-llm-pipeline
Cost optimization patterns for LLM API usage — model routing by task complexity, budget tracking, retry logic, and prompt caching.
cookie-bridge
Estate-local browser cookie/session bridge. Injects the owner's OWN web sessions (ChatGPT, Databricks) from a phone CDP extract into the owner's MAIN Chrome/Edge/Comet profiles WITHOUT the profile corruption that an earlier force-kill approach caused. Use for putting a logged-in web session onto a main browser profile safely, or for extracting/refreshing a session from a phone over ADB+CDP. NOT for third-party accounts, NOT for reading or exfiltrating cookie values, NOT for bypassing another site's auth.
continuous-learning-v2
Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills/commands/agents. v2.1 adds project-scoped instincts to prevent cross-project contamination.
content-hash-cache-pattern
Cache expensive file processing results using SHA-256 content hashes — path-independent, auto-invalidating, with service layer separation.
consensus-tooluniverse-research
Use when downloading or systematically harvesting research from Consensus.app - extract each shared search browser-free from the page __NEXT_DATA__ payload, resolve every cited paper to a DOI and open-access PDF with ToolUniverse (Crossref, OpenAlex, Unpaywall, EuropePMC), organize by topic with a DOI-linked bibliography, and verify headline claims against primary sources.
competitive-programming-solver
Solves algorithmic / competitive-programming problems with fast, correct solutions in C, C++, and Python. Use whenever the user mentions Codeforces, AtCoder, LeetCode, Infoarena, pbinfo, Kattis, SPOJ, USACO, ICPC, IOI, or any online judge / olympiad / contest, or a statement with input/output specs, time/memory limits, "TLE", "AC", or "competitive programming". Trigger even for a buggy submission.