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
swfoc-reverse-engineering
Use when working on SWFOC editor runtime or native analysis, or on the swfoc_memory dump bundle, especially for dump triage, debugger attach flows, signature generation, binary comparison, import repair, or moving evidence between WinDbg Preview, x64dbg, Cheat Engine, IDA Pro, Binary Ninja, and Ghidra.
bmad-editorial-review-prose
Clinical copy-editor that reviews text for communication issues. Use when user says review for prose or improve the prose
bmad-edit-prd
Edit an existing PRD. Use when the user says "edit this PRD".
swfoc-modding
Research-backed workflow for Star Wars: Empire at War / Forces of Corruption modding, SDK/tooling, debugging, and submod integration. Use when Codex needs to implement, troubleshoot, or explain SWFOC mods and submods, including XML/Lua edits, MEG packaging, MODPATH/STEAMMOD launching, or file formats (ALO/ALA/MTD/DAT/LUA). For runtime/debugger analysis, route to $swfoc-reverse-engineering.
bmad-domain-research
Conduct domain and industry research. Use when the user says wants to do domain research for a topic or industry
subtitle-translate
Use when translating subtitles/captions to another language and/or generating + exporting SRT/VTT/ASS for a media-studio video — including bilingual (stacked) subs and the audio-dub (TTS) path. Covers the tiered local→hosted MT engine (TranslateGemma GGUF via llama.cpp, language-aware routing +.
bmad-document-project
Document brownfield projects for AI context. Use when the user says "document this project" or "generate project docs"
subagent-driven-development
Use when executing an implementation plan by dispatching a fresh subagent per independent task with two-stage spec-then-quality review in the current session ; do NOT use when tasks have sequential dependencies or need a separate session with batch checkpoints (use executing-plans) ; returns per-task subagent outputs reviewed for spec compliance and code quality.
bmad-distillator
Lossless LLM-optimized compression of source documents. Use when the user requests to 'distill documents' or 'create a distillate'.
study-plan-psychology
Use when building a study plan grounded in cognitive psychology, retrieval practice, spacing, interleaving, and realistic motivation management.
bmad-dev-story
Execute story implementation following a context filled story spec file. Use when the user says "dev this story [story file]" or "implement the next story in the sprint plan"
structure-based-screening
Use when running a structure-based drug-discovery / molecular-docking campaign on the local schrodinger MCP - taking a receptor (PDB) and one or more ligands (SMILES or files) all the way to docked, MM-GBSA-rescored, ADMET-profiled poses. Covers the full prepwizard to glide_grid to ligprep to glide_dock to prime_mmgbsa to qikprop chain, grid-box centering, and license-token sequencing.
bmad-create-ux-design
Plan UX patterns and design specifications. Use when the user says "lets create UX design" or "create UX specifications" or "help me plan the UX"
strategic-compact
Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.
bmad-create-story
Creates a dedicated story file with all the context the agent will need to implement it later. Use when the user says "create the next story" or "create story [story identifier]"
stdin-server
暂无简介
bmad-create-prd
Create a PRD from scratch. Use when the user says "lets create a product requirements document" or "I want to create a new PRD"
spreadsheet
Use when tasks involve creating, editing, analyzing, or formatting spreadsheets (`.xlsx`, `.csv`, `.tsv`) using Python (`openpyxl`, `pandas`), especially when formulas, references, and formatting need to be preserved and verified.