AISP (AI Skill Protocol) — AISP packages executable, governable, distributable AI skills as self-contained skill folders. It is not another SKILL.md format. AISP defines the skill package; AISOP executes the program inside it.

Portable Agent Skill for safe, reliable jq CLI JSON filtering, validation, and shell-aware transformations.

三土沉淀的 AI Agent Skills 合集，包含中文 AI 科技口播视频生产等可复用工作流。

Local, cross-platform meeting transcription -> corrected transcript + Precision Pro HTML canvas + AI-insight summary. A Claude Code skill.

A Claude Code skill for authoring strong pull requests - titles, descriptions, scoping, reviewer selection, and responding to feedback

Free Claude Code skill: onboard an unfamiliar repo in one pass — stack, architecture, risks, smallest test gate — before any edits.

"Don Salvatore's AI crew finds the smarter route for every harvest · Agents League 2026"

账号创作、改写和润色中文微博与读书笔记，保留其从事实出发、分析机制与利益约束、承认不确定性、克制落下个人判断的表达方式。用户提到写微博、微博评论、转发语、热点观点、读书笔记、书评、阅读感想、把素材写成文章、模仿其既有账号风格或要求“按我的风格写”时使用。

CLI + skill so AI agents drive Ithildin (leads, dialer, planner, Argent²) — agent-ready via API→CLI→skill.

Boundary-guard mode for AI agents. Does this responsibility belong in this field?

Convert OpenCode shared sessions into reusable, publishable AI agent skills with TRACE validation, security checks, and ZIP packaging.

Workflow skills for AI coding agents: plan, execute, and maintain a persistent knowledge base across sessions.

Free, non-directive, first-principles thinking partner for hard, ambiguous health challenges & optimisation — runs in your own Claude Code, on your own data. Educational, not medical advice.

Claude/agent skill: safe deploys when multiple agent sessions share one working tree (wrong-project guard, foreign-edit check, multi-session merge, live provenance verify).

Open Agent Skill for generating polished, source-aware, self-contained HTML visuals

Public Hermes skill export prepared from a private Hermes skill.

Practical Solana/Anchor security audit workflow skill for the Solana AI Kit (static + manual + dynamic + report); fills the official seed. MIT.

Instruction-only Agent Skill for technical exploration before implementation.

This is a collection of a curated skills that AI agents can use to help you apply and tell your fundraising story better.

SEO / GEO / AEO website visibility audit -> client-ready HTML + PDF report. A reusable Claude skill (playbook + multi-agent measurement prompts + templates + scripts).

Index a whole repo (code + docs) into a navigable, AI-analyzed encyclopedia — map + per-module entries + typed link-graph — so an AI works in huge codebases without filling its context. One auto-routing skills.sh skill with grounded, citation-checked analysis and optional local (Ollama) semantic search.

Create reviewable launch videos and OSS promotion packets from repositories, products, briefs, and media.

Public Hermes skill export prepared from a private Hermes skill.

The complete operating system for posting on LinkedIn. What to post, when, how often, how to write it, and what top global + India creators do. Grounded in 2026 data. Zero AI slop.

Agent-first Kometa skill library for Codex and Claude: generate, review, and debug Plex automation YAML for configs, collections, overlays, metadata, playlists, defaults, operations, and reports.

团队共享的「一页纸周报」HTML 渲染规范 Agent Skill：把任意业务线本周数字渲染成风格统一、结论先行、可打印一页 A4 的经营周报。可被 Kiro / Claude Code 安装。

Read-only CLI + MCP + skill: AI agents read xXTrade (Hyperliquid perps) markets + positions. No trading.

Production-grade quality skills for AI coding agents: red-first TDD, quality gates, and golden benchmark uplift loops.

Thin core + domain sets for a fast, stack-aware project start. Cross-agent (Claude Code, Cursor, Codex, Gemini) via the SKILL.md standard. MIT.

Agent skills for Chinese, Japanese, and Korean text layout. 日本語組版 / 中文排版 / 한국어 텍스트 레이아웃 agent skills.

A Claude Code skill for graph-based discovery of open-source projects and contributors by crawling GitHub social graphs (stars, follows, contributions).

Framework & language expert skills for Claude Code — idiomatic best practices for TypeScript, React, Vue, Svelte, Solid, Angular, Astro

Crawlora Agent Skills — structured public web data (search, e-commerce, social, finance, app stores, media, reviews) via the Crawlora REST API. Installable in any agent with the skills CLI or as a Claude Code plugin marketplace.

Public Hermes skill export prepared from a private Hermes skill.

基于 CloakBrowser 与 Agent-in-the-Loop 的智能 Web 应用克隆复现工具，支持人机协作登录、深度优先遍历与本地离线 replay。

From-scratch agent runtime with task graphs, multi-index RAG, memory, typed tools, reusable skills, handoffs, traces, and smoke tests.

Skills for driving GlassFlow ETL pipelines from AI coding assistants

AI agent skill for implementing modular, robust software architecture with scoped codebase discovery, clean boundaries, contracts, validation, migration safety, and verification.

SEO toolkit for Cursor — technical SEO, E-E-A-T, Schema.org, GEO/AI search, local SEO, keyword clustering, drift monitoring & DataForSEO. 25 skills, 18 workflows.

Agent skill that discovers and installs the right skills for Codex, OpenClaw, and Hermes.

Cursor + Claude Code skill: turns boring sentences into cringe-maximalist LinkedIn thought leadership

A discipline for AI coding agents that keeps a codebase reading as a single authored work across many sessions, models, and thinking budgets. A Claude skill. MIT.

FinVerge Sales Skills — Claude Code plugin that automates sales/marketing collateral (proposals, product decks, content campaigns) with a dual public/internal knowledge-base architecture

A conversational Agent Skill that turns lived experience into confirmed source material, topic cards, and an evidence-grounded personal Persona.

A Claude Code skill that turns a hand-drawn, sketched, or scanned logo into clean, reproducible code - fitting smooth cubic Bezier curves to the real outline to generate an editable SVG, color/layout variants, and PNG/ICO/favicon exports.

Route an AI coding agent's mechanical sub-tasks (summarize, extract, classify, code) to cheap local or cloud models — save frontier tokens. Works with Claude Code, Codex, Cursor, opencode, and more.

Security & trust vetting for AgentSkills: mandatory open-source scanner gate (Cisco, NVIDIA SkillSpector, Snyk, sentry), OWASP Top 10 for Agentic Applications mapping, and tiered review reports.

Agent-native, self-hostable artifact hosting — publish HTML/Markdown to a shareable URL on your own Cloudflare Worker

Claude Code plugin: injects a capability self-awareness card at session start so Claude actually knows and uses its built-in capabilities — skills, subagents, dynamic workflows, hooks, MCP, plugins, GitHub Actions, the Agent SDK, and more.

Field-tested agent skills for building Snap Spectacles / Lens Studio projects via the Lens Studio MCP server (editing, custom shaders, SIK hand interaction, spatial UI, preview/verify, assets & FBX).

An agent skill for configuring user's guitar and amplifier to play a certain song

A compact agent skill for making smaller, cleaner, more maintainable changes by avoiding unnecessary code, abstractions, dependencies, and output.

Meta-skills for authoring, reviewing, researching, and migrating Agent Skills — conventions, lint, scaffolding, evals with auditable run logs. Vendor-neutral; bring your own org overlay.

TICK four-bird personality profiling skill for Claude — read a person's style (Peacock, Dove, Eagle, Owl) and adapt messaging, selling, and relationships

One skill for the entire i18n journey — internationalize your app from scratch. Creates i18n from scratch, migrates hardcoded strings, or refactors keys/namespaces safely with impact analysis.

Popperian reasoning agent skill for falsification, risky tests, and error elimination.

Free preview and trusted handoff templates for AI agents: AGENTS.md, SKILL.md, llms.txt, product.json.