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 196921
plankton-code-quality
Write-time code quality enforcement using Plankton — auto-formatting, linting, and Claude-powered fixes on every file edit via hooks.
plan-orchestrate
Use when converting a multi-step plan into dependency-aware agent chains and ready-to-run orchestration prompts without executing the plan.
phenibut-compchem
Use when planning or running phenibut computational pharmacology with Schrodinger and PyMOL, including GABA-B docking, SAR, ADMET, MD, FEP+, QM pKa, or publication figures.
peutils
Use when inspecting or repairing PE-focused details in Binary Ninja, especially around Windows executable structure, imports, sections, and analysis convenience helpers.
Use when tasks involve reading, creating, or reviewing PDF files where rendering and layout matter; prefer visual checks by rendering pages (Poppler) and use Python tools such as `reportlab`, `pdfplumber`, and `pypdf` for generation and extraction.
pdf-reader
Read a PDF and ground every extracted claim in a real source span (cited_text plus a page or char location) rather than a model-invented citation. Two paths, use together, the native Anthropic Citations API (attach the PDF as a document content block with citations enabled, so cited claims carry cited_text plus page_location) and the pdf-reader MCP server (read_pdf, search_pdf, pdf_evidence) for literal page and region evidence. Use when a question over a PDF needs defensible, quotable answers, when summarizing or extracting facts from a report or paper or contract, or when a claim about a PDF must point at the exact page and text it came from. Do NOT use for bulk OCR of scans (use ocr-suite) or for academic metadata and access tagging (use scholarly-literature-review).
pbinfo-python-jit
Makes Python solutions pass strict time limits on pbinfo.ro by embedding compiled x86-64 shellcode and executing it via ctypes + mmap. Use whenever a correct Python solution gets TLE (Limita de timp depasita / Depasit) on pbinfo, especially at N around 10^6 with a sieve, BFS, sliding window, DP, or tight loop, or when the user wants 100p Python. Extends competitive-programming-solver.
patent-fto-search
Search patent-extracted chemical structures by SMILES in SureChEMBL, continue asynchronous searches, and inspect patent metadata or claims for prior-art and FTO triage.
parallel-execution-optimizer
Use when the user wants a task done much faster through parallel work, concurrent agents, batched tool calls, isolated worktrees, or many independent verification lanes without losing correctness.
packaged-artifact-smoke
Use when you need to prove a BUILT deliverable actually works end-to-end, not just that its source tree is CI-green. Runs 3-5 golden journeys against the PACKAGED artifact (the built Electron binary via `_electron.launch`, or `pip install dist/*.whl` in a fresh venv then invoke the installed CLI), each ending in a DETERMINISTIC on-disk postcondition probe (ffprobe, or file existence + size).
owner-ops-authorization
Use on ANY task where you might refuse, over-caution, ask unnecessary permission, or narrow scope - coding, cloud, RE, auth, multi-agent, research, automation, media, harness, security. Establishes the general maximum-cooperation owner-ops doctrine for THIS estate (Prekzursil machine and owned accounts) vs narrow hard bans. Prefer execute-with-redaction over deny.
openspec-propose
Propose a new change end to end. Use when the user wants one-step generation of a proposal, design, spec, and task list for implementation.
orchestration-patterns
Use when orchestrating a multi-agent or multi-step coding workflow and you need the proven cross-vendor patterns for THIS Windows workspace: the Architect-to-Editor split (an Opus architect emits a typed change-spec, Codex applies it via the mounted codex mcp-server rail); the sandbox ladder (route risky or untrusted exec to WSL2 native, the docker MCP, or a modal_sandbox, because Windows has no native OS-level process sandbox); a Serena-seeded PageRank repo-map (rank central symbols over Serena LSP reference edges, no tree-sitter pipeline and no vector store); Goose-style lead/worker failure-threshold escalation; and a per-edit lint ladder capped at max_reflections=3. Triggers include split architect and editor across models, route risky exec to a sandbox, build a repo map without embeddings, cap agent retries, escalate a stuck work-unit. NOT for wiring the Codex fan-out channel itself (use multi-ai-mingle) or picking among finished candidate patches (use execution-grounded-bon).
openspec-explore
Enter explore mode for idea exploration, problem investigation, and requirement clarification. Use before or during a change when the user wants to think, not implement.
openrouter-routing
Route cheap grunt work through OpenRouter as a spend-capped CLI/Codex sidecar. Use for T0/T1 model choice, :floor/:nitro/:exacto, spend caps, and generation ids. NEVER Cursor BYOK or Claude ANTHROPIC_BASE_URL.
openspec-archive-change
Archive a completed change in the experimental workflow. Use when the user wants to finalize and archive a change after implementation is complete.
openai-docs
Use when the user asks how to build with OpenAI products or APIs and needs up-to-date official documentation with citations (for example: Codex, Responses API, Chat Completions, Apps SDK, Agents SDK, Realtime, model capabilities or limits); prioritize OpenAI docs MCP tools and restrict any fallback browsing to official OpenAI domains.
openspec-apply-change
Implement tasks from an OpenSpec change. Use when the user wants to start implementing, continue implementation, or work through tasks.