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
quality-zero-platform-control-plane
Use when working with `agentuser/quality-zero-platform`, enrolling or auditing governed repos, checking strict-zero wrapper workflows, ruleset drift, trusted-runner Codex remediation, or provider/bootstrap state for the personal-account control plane.
quality-gate-automation-architect
Use when designing, comparing, or reviewing autonomous repo-quality automation for pull-request repair, coverage ratchets, analyzer debt burn-down, or merge-governance decisions. Triggers include requests to keep PRs green, auto-fix failing checks, plan Sonar or Codacy workflows, compare GitHub-native versus Codex versus local automation, or decide between zero-touch and human-approved merges.
qiling-emulation
Use when you need to emulate or sandbox a native ARM/ARM64 shared object off-device — running the Battle Cats Android .so (or any Android/Linux ELF native library) inside the Qiling framework on the PC instead of on a rooted phone. This is the dynamic-OFF-device complement to the frida skill (dynamic-ON-device) and to the static ghidra/radare2/ida skills — reach for it to call a single exported native function with controlled inputs, brute-force or trace an algorithm (save crypto, PRNG, checksum, offset math) without the game engine or a device, hook native calls in a scriptable sandbox, or diff native behavior across app versions. Do NOT use for Java/Smali (use jadx), for live on-device instrumentation (use frida), or for pure static disassembly (use ghidra/radare2).
wds-4-ux-design
Transform ideas into detailed visual specifications through scenario-driven design
qdx-rush
Use when qdx rush is needed. Drive QDX's GPU quantum chemistry (EXESS), folding, and prep stack through the qdx-rush MCP tools for QM energies, interaction energies, optimization, QM/MM, fast NN-xTB screens, protein/ligand prep, Boltz folding+affinity, and PB solvation. QDX/EXESS/rush-py are NOT.
wds-3-scenarios
Create UX scenario outlines from Trigger Map through structured micro-steps
python-testing
Python testing strategies using pytest, TDD methodology, fixtures, mocking, parametrization, and coverage requirements.
python-patterns
Pythonic idioms, PEP 8 standards, type hints, and best practices for building robust, efficient, and maintainable Python applications.
wds-2-trigger-mapping
Map business goals to user psychology through structured workshops
prototype
Use when the user wants to prototype, sanity-check a data model or state machine, mock up a UI, explore design options before committing, or says "prototype this", "let me play with it", "try a few designs". Routes to a runnable terminal app for state/logic questions or several toggleable UI variations for design questions.
protein-interaction-network-analysis
Use when analyzing protein interaction networks, confidence scores, functional enrichment, or structural context with STRING, BioGRID, and SASBDB.
wds-1-project-brief
Establish project context - foundation for all design work
prompt-optimizer
Use when prompt optimizer is needed. Analyze raw prompts, identify intent and gaps, match ECC components (skills/commands/agents/hooks), and output a ready-to-paste optimized prompt. Advisory role only — never executes the task itself. TRIGGER when: user says "optimize prompt", "improve my.
wds-0-project-setup
Project onboarding - determine project type, complexity, tech stack, and route to correct phase
playwright
Use when automating a real browser from the terminal for navigation, form filling, screenshots, data extraction, or UI-flow debugging via playwright-cli or the wrapper script ; do NOT use for persistent iterative debugging sessions (use playwright-interactive) or local webapp functional test suites (use webapp-testing) ; returns browser automation output and screenshots.
playwright-interactive
Use when iteratively debugging a local web or Electron app in a persistent Playwright js_repl session without restarting between steps ; do NOT use for one-shot navigation or data extraction (use playwright) ; returns live browser state, screenshots, and console output across iterations.
wds-0-alignment-signoff
Create alignment around your idea before starting the project
plankton-code-quality
Write-time code quality enforcement using Plankton — auto-formatting, linting, and Claude-powered fixes on every file edit via hooks.