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
@microsoftopenclaw
@openclawAnthropic
@anthropicsOpenAI
@openaiThe Apache Software Foundation
@apacheGitHub
@githubAutoGPT
@Significant-GravitasGarry Tan
@garrytan全部 Skills 482556
scopus-wos-coverage-auditor
Use when comparing Scopus, Web of Science, Dimensions, or related indexing outputs and the user needs a disciplined explanation of differences.
schrodinger-maestro-driver
Use when driving the local schrodinger MCP server for structure-based drug discovery on a Schrodinger Suite install - SMILES to 3D, LigPrep, Protein Preparation Wizard, Glide grid generation, Glide docking, Prime MM-GBSA binding free energy, QikProp ADMET, structure format conversion, RDKit descriptors, or the run_schrodinger_python escape hatch. Covers SCHRODINGER environment setup and the license-token-free vs token-consuming split. NOT for the whole prep-to-rescore campaign (use structure-based-screening).
scholarly-literature-review
Use when given DOIs, PMIDs, arXiv ids, or paper titles and needing canonical metadata, access-status tables, citation/reference expansion, or structured summaries from legally available abstracts via Scholarly Access MCP ; do NOT use for biomedical evidence ranking (use biomedical-paper-triage) or PDF downloading (use oa-pdf-retrieval) ; returns metadata, access classification, and citation graph.
run-taskwatch_monitor
Use when running, launching, or smoke-testing taskwatch_monitor - the general-purpose long-task progress monitor - to watch a long-running job (build, download, CI run, FEP/BPMD driver, LLM generation, rclone transfer) with an honest, BLIND-aware status, p50/p90 ETA, and no fabricated percentages. Covers register/list/status, the live watch TUI, the MCP server, and the smoke test.
run-agent-monitor
Run and smoke-test the monitorcore agent tail + discovery - the read-only per-agent tailer and flat/workflow subagent discovery for Claude Code Task subagents. Use when asked to run, watch, or smoke-test the agent monitor / subagent dashboard, or tail a subagent transcript. NOT the launcher itself (use monitor-launcher).
rubric-verifier
暂无简介
rtv-pdr
Use when a hard coding work-unit has failed once, is contentious, or scores HIGH on the ESE (Ensemble Semantic Entropy) gate — spawns N parallel Opus rollouts, runs a recursive tournament where fresh judge agents (never contestants) pick the winner, then optionally runs a PDR refine pass. Expensive; do NOT fire on routine tasks.
reverse-engineering-toolkit
Use when selecting or sequencing reverse-engineering tools for Windows native analysis, dump triage, live debugging, binary diffing, signature generation, import repair, or MCP disassembler workflows. Choose from WinDbg Preview, x64dbg, Cheat Engine, IDA Pro MCP, Ghidra MCP, Binary Ninja MCP, HexStrike AI, Frida, BinDiff/BinExport, ret-sync. NOT for triaging a binary (use re-triage-preflight).
ret-sync
Use when synchronizing a live debugger with IDA Pro, Binary Ninja, or compatible disassemblers so stepping and addresses stay aligned during native reverse-engineering.
research-paper-craft
Use when writing, structuring, or revising a state-of-the-art scientific research paper, review, preprint, or thesis chapter and you want it to read well and land. Covers the craft of paper architecture, the narrative spine, the title and abstract, figures as the paper UI, reproducible methods.
research-ops
Thin router for the research stack. Use when you want fresh facts, comparisons, enrichment, or evidence-backed recommendations -- it picks the right skill. NOT the full multi-source pass (use deep-research).
research-integrity-forensics
Use when checking a paper, corpus, or draft for integrity risks such as citation abuse, duplication, image problems, implausible claims, or unsupported certainty.
requesting-code-review
Use when completing tasks, implementing major features, or before merging to verify work meets requirements
reporting-guideline-router
Use when the manuscript or protocol needs the correct reporting guideline lane such as PRISMA, CONSORT, STROBE, ARRIVE, STARD, CARE, or COREQ.
repomix
Use when packing a repository into an AI-friendly bundle with Repomix, or when exposing Repomix as an MCP server to Codex, Claude Code, or Gemini CLI.
render-deploy
Use when deploying an application to Render.com, generating render.yaml Blueprints, or getting Render Dashboard deeplinks ; do NOT use for Vercel (use vercel-deploy), Netlify (use netlify-deploy), or Cloudflare (use cloudflare-deploy) ; returns Render Blueprint and deployment status.
regex-vs-llm-structured-text
Decision framework for choosing between regex and LLM when parsing structured text — start with regex, add LLM only for low-confidence edge cases.
reframe-video-cutting
Use when selecting and cutting moments from a long talk, podcast, interview, stream, or vlog into shorts with scene-aware, sentence-safe boundaries.