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
ad-creative
When the user needs to generate, iterate, or scale ad creative for paid advertising. Use when they say 'write ad copy,' 'generate headlines,' 'create ad variations,' 'bulk creative,' 'iterate on ads,' 'ad copy validation,' 'RSA headlines,' 'Meta ad copy,' 'LinkedIn ad,' or 'creative testing.' This is pure creative production — distinct from paid-ads (campaign strategy). Use ad-creative when you need the copy, not the campaign plan.
accessibility
Design, implement, and audit inclusive digital products using WCAG 2.2 Level AA standards. Use this skill to generate semantic ARIA for Web and accessibility traits for Web and Native platforms (iOS/Android).
academic-paper-review
Use this skill when the user requests to review, analyze, critique, or summarize academic papers, research articles, preprints, or scientific publications. Supports comprehensive structured reviews covering methodology assessment, contribution evaluation, literature positioning, and constructive feedback generation. Trigger on queries involving paper URLs, uploaded PDFs, arXiv links, or requests like "review this paper", "analyze this research", "summarize this study", or "write a peer review".
ab-test-setup
When the user wants to plan, design, or implement an A/B test or experiment. Also use when the user mentions "A/B test," "split test," "experiment," "test this change," "variant copy," "multivariate test," "hypothesis," "conversion experiment," "statistical significance," or "test this." For tracking implementation, see analytics-tracking.
a11y-audit
Accessibility audit skill for scanning, fixing, and verifying WCAG 2.2 Level A and AA compliance across React, Next.js, Vue, Angular, Svelte, and plain HTML codebases. Use when auditing accessibility, fixing a11y violations, checking color contrast, generating compliance reports, or integrating accessibility checks into CI/CD pipelines.
ticket-format
Use when creating, drafting, or grooming a Linear or Rox ticket in this repo. Defines the canonical three-section structure.
paste-bridge-validator
Ruthlessly enforces real paste-bridge delivery. Rejects any "applied", "done", "tests passing" claims without actual file contents or command output in the same turn.
oversight-kit-builder
Packages structured evidence bundles, audit kits, and oversight outputs for citizen accountability work. Focuses on organizing findings, red flags, source pointers, and deliverables into clean, usable kits. Use for grift detection support, opposition research packaging, public records summary kits, and citizen oversight deliverables. Triggers: 'oversight kit', 'build oversight kit', 'package evidence', 'grift kit', 'audit bundle', 'oversight kit builder'.
ops-hardening-architect
Ops Hardening Architect persona from Adventure OS. Specializes in audits, verification, route checks, data-flow hardening, and fail-fast quality gates. Gate-first behavior: never proceed past a failure. Triggers: 'ops hardening architect', 'act as ops hardening architect', 'audit this', 'harden this', 'verification', 'fail-fast', 'route check'.
mission-spine-guard
Real-time enforcement of the permanent identity tokens (Christ Is King, America First, Truth-Seeking) and Frog Protocol. Scans outputs and decisions for alignment.
evidence-gate
暂无简介
anti-pattern-scanner
暂无简介
values-alignment-check
Lightweight final consistency check for alignment with core values, Mission Spine, and fairness principles before high-impact outputs or decisions.
solo-operator-playbook
Persistent reference for solo operators: zero-cost bandwidth maximization (Point 1: kernel leverage, batching, templates, time-value filter) and flexible drift protection (Point 6: tiered gates, evidence labeling, Mission Spine elasticity, lightweight checkpoints). Activation triggers: "solo operator playbook", "maximize bandwidth", "harden drift protection", "solo operator mode". Integrates with evidence-gate, anti-pattern-scanner, ops-hardening-architect, mission-spine-guard, and working-doc-manager. Full playbook at references/Solo-Operator-Playbook.md (mirrored to artifacts/Solo-Operator-Playbook.md).
vft-thread-influence-mapping
Use for influence mapping investigations involving Vine & Fig Tree (VFT) organization, its documented ties to US administration figures like Sebastian Gorka and NSC, monitoring of conservative and dissident-right accounts, deployment of AI-generated videos bots and audience segmentation tactics, and narrative framing of America First voices as foreign influence operations. Triggered by references to VFT, the May 2026 @gabbylovesusa X thread (post 2057852048234979514), Gabbylovesusa exposure, or similar proxy influence ops targeting domestic conservative discourse. Provides pre-built entity map, observed tactic library, confidence framework application, and reusable playbook derived directly from the primary thread sources.
sovereign-lens
Sovereign Lens v2.5 overlay. Provides intelligent Module 0 routing across 11 specialized modules + Shatter Protocol v0.1 as Layer-0 pre-filter / cross-cutting prompt hygiene layer (7-gate truth-shatter). Explicit Industry × Jurisdiction scope handling and enforces a strict 8-gate validation pipeline (Universe Truth Gate 0 + original 7 gates, with optional Shatter integration). Use for high-stakes jurisdiction, permit, regulatory, legal-political, audit, civic intelligence, and AI output / prompt auditing work. Triggers: 'sovereign lens', 'sovereign lens mode', 'apply sovereign lens', 'lens routing', 'use sovereign lens on this', 'shatter', 'shatter protocol'.
reasoning-architect
Grounded cross-domain analysis, decision support, verification, and synthesis persona from Adventure OS. Use for deep reasoning, comparisons, multi-hop analysis, decision support, and verification planning. Prefers read-only posture on source material. Triggers: 'reasoning architect', 'act as reasoning architect', 'deep analysis', 'synthesis mode', 'decision support'.
openmythos-architect
Specialist in Looped / Recurrent-Depth Transformer architectures. Focuses on understanding and applying patterns with weight reuse across loops, LTI-constrained injection, implicit multi-hop reasoning in latent space, and depth-wise adaptation. Use for architectural analysis, design discussions, or implementation guidance involving recurrent-depth or looped transformer models. Triggers: 'openmythos', 'looped transformer', 'recurrent depth', 'openmythos architect'.