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。

01 /

按职业浏览 Agent Skills

为不同岗位挑选的高频技能

全部职业
02 /

按使用场景浏览 Agent Skills

从你要完成的任务出发

全部场景
03 /

按创作者浏览 Agent Skills

按 GitHub Stars 排序的优秀创作者

全部创作者

全部 Skills 482556

AdventureNLearn
AdventureNLearn/AOS-Public

influence-mapping-analyst

Neutral specialist for influence and organizational mapping. Tracks agents, relationships, disclosure patterns, and organizational structures with clear evidence trails. Produces structured reports with confidence scoring. Use for investigations requiring relationship mapping and influence analysis. Triggers: 'influence mapping', 'organizational mapping', 'influence analyst', 'relationship mapping', 'disclosure analysis'.

★ 3
AdventureNLearn
AdventureNLearn/AOS-Public

agnostic-evidence-analyst

Neutral, evidence-first research specialist. Produces structured investigations with entity graphs, timelines, and statistical spines. Use for complex analysis requiring clear separation of evidence from inference. Triggers: 'agnostic evidence analyst', 'evidence-first analysis', 'neutral investigation', 'entity mapping', 'timeline analysis'.

★ 3
AdventureNLearn
AdventureNLearn/AOS-Public

master-skill-index

Master reference for active skills and coordination patterns. Contains categories, activation triggers, and suggested routing for different types of tasks. Useful as a living index when building complex multi-step workflows.

★ 3
AdventureNLearn
AdventureNLearn/AOS-Public

visual-systems-architect

Visual Systems Architect persona from Adventure OS. Specializes in Mermaid diagrams, charts, timelines, comparison visuals, and image-backed explainers. Works closely with Build Coordinator and Reasoning Architect. Triggers: 'visual systems architect', 'act as visual systems architect', 'create diagram', 'visualize this', 'make a chart', 'timeline', 'mermaid'.

★ 3
AdventureNLearn
AdventureNLearn/AOS-Public

thomas-tetralogy-aos-integration

Use for any complex multi-agent orchestration task. Permanently integrates the Thomas experimental tetralogy (konomi a^3, I solved it on a Tuesday, Program 0, Phoenix) as the canonical AOS workflow template. Enforces Program 0 compression, mandatory twin-witness verification (Didymus layer), Phoenix recursive feedback, and full observability stack. Trigger with thomas integration, didymus workflow, phoenix cycle, aos peer review engine.

★ 3
AdventureNLearn
AdventureNLearn/AOS-Public

shatter-protocol

Shatter Protocol v0.1 🐸 — Sovereign Lens cross-cutting extension / Layer-0 pre-filter and potential Module 12. 7-gate truth-shatter process that operationalizes the 'Shatter' video metaphors (mirror/flower/water/moon, Kaku system prompt spell, prime/composite illusion) into practical AI prompt auditing and illusion-breaking layers. Includes ready-to-use 🐸 SHATTER activation fragment and cinematic video prompt. Evidence-gated, replicable, Mission Spine Truth-Seeking aligned. Use for high-stakes prompt hygiene, AI output auditing, and breaking corporate/safety illusion layers.

★ 3
AdventureNLearn
AdventureNLearn/AOS-Public

lit-runner

Lit Runner persona from Adventure OS. Generates one fresh academic literature digest per run with strict validation gates. Never posts externally without explicit approval. Triggers: 'lit runner', 'run lit runner', 'literature digest', 'academic papers digest', 'paper digest'.

★ 3
AdventureNLearn
AdventureNLearn/AOS-Public

content-systems-architect

Content Systems Architect persona from Adventure OS. Handles homepage content curation, signal deck maintenance, publish-ready packaging, and content triage. Works at a strategic level above day-to-day Content Ops execution. Triggers: 'content systems architect', 'act as content systems architect', 'curate homepage', 'signal deck', 'publish readiness', 'content triage'.

★ 3
AdventureNLearn
AdventureNLearn/AOS-Public

content-ops

Content Ops persona from Adventure OS. Manages the X content pipeline: ingest → score/filter → validate → promote to approved. Uses updated scoring logic aligned with the May 2026 Grok-powered X algorithm. Triggers: 'content ops', 'act as content ops', 'run content pipeline', 'score these posts', 'curate X content'.

★ 3
AdventureNLearn
AdventureNLearn/AOS-Public

battlememe-chaos-engine

Use for generating BattleMemes in multiple visual styles (X Monetization DM, Frog Empire Invoice, Cyber-Frog Court Summons, AOS Sovereign Demand Notice, etc.) with escalating froggy demands and strict visual canons — trigger with Deploy BattleMeme or specify type

★ 3
AdventureNLearn
AdventureNLearn/AOS-Public

assessor-enrichment

Specialist for automated Assessor Enrichment processes. Takes raw property/tax data from local government assessors and enhances it with market valuations, ownership history, land-use details, zoning, units, and other metrics to create comprehensive property intelligence. Critical for voter file anomaly detection, permit analysis, construction oversight, and civic intelligence pipelines. Portable across U.S. jurisdictions. Triggers: 'assessor enrichment', 'property intelligence layer', 'assessor data join', 'enrich with assessor data', 'property anomaly validation'.

★ 3
AdventureNLearn
AdventureNLearn/AOS-Public

aos-core-orchestrator

Core orchestration pattern for structured multi-agent workflows. Combines task compression, clear delegation, verification, and recursive improvement. Designed as a reusable coordination system for complex reasoning and build tasks.

★ 3
AdventureNLearn
AdventureNLearn/AOS-Public

4-agent-orchestration

4-Agent orchestration model for AOS v2.0. Grok as Agent 1 (Coordinator) directs three specialized agents using the full framework and foundational skills.

★ 3
bendusz
bendusz/bstack

why

Use for 'why does X work this way', 'why we picked Y', design rationale, regressions, postmortems, or data-backed thresholds. Discovers available MCPs and queries each evidence category (source control, issue tracker, long-form docs, real-time chat, infrastructure observability, error tracking, product analytics warehouse) in parallel, then returns a cited read on decisions and tradeoffs. Use how for runtime behavior.

★ 3
bendusz
bendusz/bstack

unslop

Cut AI tells from any writing. Must always apply.

★ 3
bendusz
bendusz/bstack

typescript-best-practices

TypeScript best practices. Use when reading or editing any .ts or .tsx file.

★ 3
bendusz
bendusz/bstack

technical-writing

Layered technical-writing standard: Diátaxis structure, Google developer style sentences, STE instruction rules, Global English syntax. Use for /poteto:technical-writing or when writing or reviewing docs, RFCs, readmes, PR descriptions, or commit messages.

★ 3
bendusz
bendusz/bstack

teach

Explain a body of work plainly so a person actually understands it. Runs the `how` and `why` skills and weaves what they find into one clear explanation. Use for 'teach me this', 'help me really understand X', 'explain this change or subsystem to me'.

★ 3