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
bc-drive
Deterministic ON-DEMAND driver for a LIVE Battle Cats (jp.co.ponos.battlecatsen, EN 15.4.1) on rooted BlueStacks. Reads engine state (scene/metrics) via crash-safe one-shot Frida NativeFunction calls (NO per-frame Interceptor) and actuates via OS-level `adb shell input tap` in device px. BC is a CUSTOM PONOS C++/GLES engine (not cocos2d-x). Use to script/inspect BC menus or read scene state.
bc-drive-plus
Use when driving a LIVE Battle Cats (jp.co.ponos.battlecatsen, EN 15.4.1) on rooted BlueStacks beyond bc-drive. Adds bounded one-shot touch-dispatch capture to resolve the stripped NewButton ctor RVA, OmniParser V2 set-of-mark grounding for the DOM-less GLES canvas, minitouch/evdev low-latency input, and a save-snapshot ring with auto-rollback. Needs adb + frida-server; builds on bc-drive and bcsfe-save-roundtrip.
battlecats-event-unlock
Use when working on Battle Cats (EN 15.4.1, rooted BlueStacks) special/event/tower stage visibility or on-demand unlock RE - gives the proven dual-dependency model (tree-admission + valid schedule row), the decisive 15.4.1 offsets, the Event Summoner tool, the full event atlas cross-links, and the approaches already proven DEAD. Earlier-version offsets in a changelog.
autonomous-loops
Patterns and architectures for autonomous Claude Code loops — from simple sequential pipelines to RFC-driven multi-agent DAG systems.
autofix-bot-api
Use when scanning a repository or code change for security vulnerabilities, leaked secrets, or dependency issues via the Autofix Bot API (api.autofix.bot) and auto-applying detected fixes; requires AUTOFIX_BOT_API_KEY ; do NOT use for general code review without an Autofix Bot account ; returns findings report and applied-fix summary.
audio-extract-mix
Use when you need to EXTRACT, MIX, REPLACE, DUCK, or LOUDNESS-NORMALIZE audio on a video/clip with ffmpeg — e.g. pull a wav out of a clip, lay a music bed or VO UNDER a speaker so it auto-dips when they talk (sidechain ducking), normalize an export to a per-platform LUFS target (-14 for TikTok/Reels/Shorts/YouTube, -23 EBU R128 broadcast, -24 ATSC), mux/replace/strip an audio track while preserving all other streams, or turn the soundtrack into laughter/applause/ music/loudness saliency signals. The exact filter graphs, argv lists, codec/map choices, and the pitfalls that actually bite (amix auto-attenuation, -shortest duration, stream-index = list-order coupling, mono/32k decode for PANNs, loudnorm single-pass drift) come from the real media_studio source cited below. Do NOT use for: per-word transcription/alignment (use ASR/CTC modules), TTS dub GENERATION (this only muxes a finished dub), pitch/tempo time-stretch, or pure visual edits. Do NOT use as a generic "run ffmpeg" reference — it is scoped to these audio ops with the project's frozen wire surface.
aspnet-core
Build, review, refactor, or architect ASP.NET Core web applications using current official guidance for .NET web development. Use when working on Blazor Web Apps, Razor Pages, MVC, Minimal APIs, controller-based Web APIs, SignalR, gRPC, middleware, dependency injection, configuration, authentication, authorization, testing, performance, deployment, or ASP.NET Core upgrades.
apply-callee-type-ex
Use when IDA Pro decompiler output suffers from missing or bad indirect-call types and you need ApplyCalleeTypeEx to improve call prototypes and downstream analysis quality.
apa-citation-discipline
Use when writing or repairing APA-style academic prose, references, in-text citations, and attribution discipline without citation laundering.
angr
Use when symbolic execution, path exploration, constraint solving, or programmatic reasoning about binary behavior is needed beyond manual reversing.
ai-regression-testing
Regression testing strategies for AI-assisted development. Sandbox-mode API testing without database dependencies, automated bug-check workflows, and patterns to catch AI blind spots where the same model writes and reviews code.
agentic-os
Build persistent multi-agent operating systems on Claude Code. Covers kernel architecture, specialist agents, slash commands, file-based memory, scheduled automation, and state management without external databases.
agentic-humanizer
Use when the user invokes /agentic-humanizer or asks to humanize AI-generated text via a 5-pass rewrite with optional voice-matching and (when Slop or Not Pro is available) detector scoring and readability checks ; do NOT use for mere AI-detection without rewriting (use slop-check) ; returns humanized text with optional readability stats.
agent-sort
Build an evidence-backed ECC install plan for a specific repo by sorting skills, commands, rules, hooks, and extras into DAILY vs LIBRARY buckets using parallel repo-aware review passes. Use when ECC should be trimmed to what a project actually needs instead of loading the full bundle.
agent-introspection-debugging
Structured self-debugging workflow for AI agent failures using capture, diagnosis, contained recovery, and introspection reports.
agent-harness-construction
Design and optimize AI agent action spaces, tool definitions, and observation formatting for higher completion rates.
agent-as-judge
Advisory, evidence-citing Agent-as-a-Judge. Use for a second opinion on whether a completion meets its Definition of Done AFTER the deterministic verification cluster (typed receipts, fail-first, execution-consensus, golden-journey oracle) ran - decomposes the DoD into falsifiable YES/NO items, cites evidence per item, scores on ICD-203. 100% ADVISORY/SHADOW, never blocks. NOT a done-gate.
agent-architecture-audit
Use when agent architecture audit is needed. Full-stack diagnostic for agent and LLM applications. Audits the 12-layer agent stack for wrapper regression, memory pollution, tool discipline failures, hidden repair loops, and rendering corruption. Produces severity-ranked findings with code-first.