Convert vetted authoritative sources (standards, handbooks, guidebooks) into licence-clean, citable knowledge packs — vets the licence first, refuses non-redistributable sources.

CLI to validate, scaffold, and install Agent Skills for Cursor and agentskills.io-compatible agents

SoulSkill packages native AISP skill packages as a local skill library plus Codex and Claude Code plugin adapters. It gives agents and developers a self-contained way to discover, inspect, validate, hash, and distribute AISP skills.

把模糊的项目目标,通过一个问题一个问题的无限循环追问,逼成任何人读完即可开工的分层设计上下文包。一个 AI agent skill,npx skills add 安装。

🛡️ Production guardrail skills for AI-assisted Laravel — stop cross-tenant leaks, N+1, destructive migrations before your AI agent ships them. For Claude Code, Cursor & 40+ agents.

Claude Code skill for safe Solana program upgrades and on-chain account migrations: versioning, realloc/resize, fork simulation, multisig authority, rollback.

Quill - Deterministic, risk-governed multi-agent trading engine for US equities. A strategy swarm proposes orders; an independent risk guardian has final say. Paper mode by default, gated live Robinhood MCP execution.

AI Agent Council POC: OpenRouter Fusion panel review synthesizing a portable CX sentiment agent skill.

Public repository for Agent Skills

YLF agent skills for disciplined coding tasks and persistent project instructions

Comment.io engineering-workflow skills for any AI coding agent (Claude Code, Codex, Cursor) — plan, prototype, build, review, ship. npx skills add comment-hq/skills

Various agent skills I wrote (co-wrote?) to make my apps more dependable

BrevetAB-Agent-Skills

着相.skill — 治 AI '太听话'的病：接需求时反推目标，收反馈时举一反三，听断言时先验证前提

Turn a local web project into an installable app on your phone, tablet, or desktop — one command from Claude Code or Codex. PWA build, deploy anywhere, QR or zero-touch MDM install.

Universal cross-platform installer and adapter layer for Academic Research Skills across Codex, Claude Code, Cursor, VS Code, Aider, and other coding agents.

Agent skill for demo iteration: archive first, change only what you asked, report & rollback. For designers using Cursor, Claude Code, or Codex.

Agent skills that make smaller coding-agent models reason like a frontier model: interrogate, decompose, compete candidates, adversarial self-review, verify, insight pass. Plus persistent codebase memory.

Your frontend second opinion: three developers debate, you get the verdict

Agent skill for safe, evidence-driven coding-agent fleet orchestration

Agent skill: teach any subject as a concept ladder, rendered as a self-contained HTML page

Curated, compile-tested LaTeX templates for AI agents: Chinese official documents, statutes, IPO prospectus, law-firm and litigation filings, resume, academic papers — one-command PDF build

Claude Code の docx / pptx / xlsx (Agent Skills) を Windows で動かすための依存環境セットアップ (uv/pandoc/LibreOffice/Poppler/npm)。冪等な PowerShell スクリプト付き。

Errors as values for TypeScript with ESM, CommonJS, and an installable agent skill.

Agent skill for managing Fundus assets in Svelte mobile app projects

Senior-level .NET review rules for AI coding agents - Claude Code skills, Cursor rules, and Copilot instructions from one source

Agent Skill for safer Mac-to-Mac migrations with rollback and validation

Portable playbook for coding agents: always-on principles, user rules, and triggered skills.

Portable AI-agent skills for auditing and improving Git history

Reusable Codex skills and agent workflows

A desktop app to install agent skills across Claude Code, Codex, Gemini, Cursor, GitHub Copilot, and Windsurf — without a terminal.

Mematrix — Multi-dimensional Memory Matrix

Claude Code の /goal 完了条件を作成・添削・修復するスキル。公式ドキュメント準拠で出所ラベル付き（MIT）。

Disease-agnostic methodology stack for computational target discovery and antigen-specific therapeutic design in inflammatory/immune disorders (EGIDs, celiac, IBD, autoimmune).

A dowager editor who puts your copy on trial. An Agent Skill that catches formula, AI slop, borrowed brand voice, and hollow marketing copy before you publish.

AI development governance for people who build software with AI.

Aurelia v2 MVVM SPA expertise skill package — 5 router-routed skills (foundation, runtime, largespa, migration) for AI coding agents.

Portable Codex and Claude skill for cross-functional delivery, independent review, and evidence-backed acceptance.

Open-source agent skills from Optimizer (optimizer.team) for getting local & home-service businesses found by AI. Includes the AI Presence Auditor (AEO/GEO).

Claude/Agent skill that audits a GitHub repo for AI discoverability. Checks AGENTS.md, README structure, topics, description, and produces a 0-100 score with prioritized fixes.,

Bilingual AI market-intelligence radar with one-command Agent self-install, MCP, OpenClaw/Hermes skills, lead pipeline and sales follow-up | 中英文商机雷达与 Agent 自安装

A Codex skill for turning Figma frames, screenshots, and UI designs into verified React prototypes.

Guardrails and craft for coding agents: portable skills, Claude Code plugins, and zero-dependency CLI checks for design tokens, supply-chain safety, evidence-backed writing, UI verification, and agent-tooling workflows.

开源 AI UI/UX 评审 Skill：检查用户任务、信息层级、交互状态、响应式和可访问性。

Senso Agent Skills for Claude Code, Codex, Cursor, and compatible agents

A fast, scriptable CLI for logging time in Tempo Cloud—built for people, scripts, and AI agents.

A personal Claude Code skills library built around one deliberate, gated workflow: /spec → /plan → /build → /test → /review → /ship

Monorepo of @getpipher/* pi-packages and framework-agnostic Agent Skills — git workflows, quality, workspace, Solana, infra playbooks.

Run nanoodle workflows from JavaScript — zero-dependency executor for saved noodle-graph.json files

Unofficial, read-only CLI for your own Norwegian tax data from Skatteetaten's Min skatt (skattekort, skattemelding, skatteoppgjør). BankID login. Designed for AI agents.

A skill family for evidence-bounded SCI manuscript workflows: literature vetting, claim-evidence alignment, paper revision, reviewer preflight, LaTeX editing, and submission packaging.

J-Lens-informed reasoning observability skill for OpenClaw, Claude, Codex, and AI harnesses

Codex skill for reviewing agent failures, avoiding rule bloat, and choosing the smallest verified improvement.

Turn agent session insights into codemem entries, SOP docs, and reusable agent skills — your AI's institutional memory.

Eval harness for groundwork agent skills: deterministic scoring + LLM-as-judge, hallucination traps, regression gate across Codex/Claude/custom CLIs

11 个品牌社交媒体运营 AI Agent Skills：平台流量机制、反漏斗投放、达人筛选、种草战役、数据诊断、评论区运营、合规审查、高客经营与危机预案。原创方法论，合规优先。

Grok Imagine agent skill — xAI image generation, image edit, image-to-video & text-to-video for Claude Code, Cursor, Codex (SKILL.md + stdlib CLI)