Grill first, render last — an Agent Skill that refuses to make slides until purpose, audience, and issues are explicit. 資料を作る前に、あなたを炙るスキル。

Turn customer interviews into JTBD maps, product opportunities, briefs, and hypotheses with a universal AI agent skill.

Production-grade Expo / React Native foundation as a portable Agent Skill (Claude Code + OpenCode): architecture, config, patterns, testing, and Expo gotchas.

Portable /deep research agent skill for Claude Code and OpenAI Codex — cost-controlled, evidence-gated, multi-provider, and resumable.

Agent Skill for delegating work through named real-world expert personas

Public Codex skill and plugin for evidence-led landing-page projects

A reusable Codex Skill for diagnosing programmatic advertising delivery issues across requests, bids, wins, impressions, clicks, conversions, spend, and pacing.

Agent skill for production-ready animated SVG icon micro-interactions.

Agent skill for Solmi (solmi.ai) — let AI agents create songs & music videos. Install: npx skills add Solmi-AI/solmi-skills

Five narrowly scoped Codex engineering skills that preserve native model judgment.

开源 AI PPT 大纲与演示叙事 Skill：生成故事线、逐页标题、证据、视觉形式和讲者过渡。

Claude Code skill: deep web research offloaded to Codex (GPT-5.5). Claude orchestrates; Codex searches.

Quant research desk: 23 Python engines + 18 Claude Code agent skills modeling capital rotation — sector flows, thematic value chains, technical lenses, SEC EDGAR filings radar, and book-level risk. Decision support, not signals.

Agent skill that plans colors, fonts, and motion from real catalogs — then ships UI.

Convert OpenAPI/Swagger into Agent Skills–compatible packages (SKILL.md + scripts + reference) for Claude, Cursor, and other skill hosts — .NET NuGet CLI with auth-aware dispatcher.

The human review step for AI-written changes: your agent proposes, you decide — inline diff in the browser, line comments, per-chunk apply, verdict back to the agent as JSON. Ships as an agent skill.

Three agent skills to set up, ingest into, and lint a Karpathy-style agent-maintained wiki in your repo

AI-orchestrated pipeline that analyzes the health of active POC (proof of concept) pilots from HubSpot + Metabase and posts per-company summaries to Slack.

Skill for AI-native research paper management in Markdown.

🐒 Local, private LLM studio for Ollama — projects, Claude-style skills, and live file knowledge. Nothing leaves your machine.

A lightweight Customer Relationship Management (CRM) application and automated B2B lead generation pipeline custom-optimized for localized business outreach within Kenya.

AI tools, hooks, skills, and prompts I actually use day to day — each with a what/why/how write-up

Source-aware Shanhaijing Agent Skill for mythic geography, textual topology, and knowledge graphs

Cut AI web-reading token usage by typically 90%+ by converting public webpages into compact Markdown or structured JSON, with strict privacy, trust checks, and automatic source fallback.

Offline, evidence-backed audits for portable Agent Skills across Codex and GitHub Copilot.

Agent connector for the Management Research Library — search and download academic paper PDFs from a private, read-only Feishu shared folder (verified catalog, quota-governed)

Custom instructions, subagents, skills, and reference docs for production-grade Claude Code agents.

Agent skill: query Postgres/MySQL/MongoDB in plain English, safe read-only SQL, database alerts and dashboards via the AI for Database API. Works with Claude Code, OpenClaw, Codex.

Evidence-first motion review skill for AI coding agents.

Loop engineering for AI coding agents: plan → build → MR → independent AI review → fix → re-review until clean, with a merge gate and a self-learning blind-spot ledger. Agent Skills format, Claude Code native, MIT.

Coordinates parallel coding agents with worktree isolation: one writer per worktree, bounded task contracts, and merge receipts.

Agent Skill to audit paired vision datasets before expensive training runs.

Source-backed loyalty intelligence for points, miles, travel cards, and loyalty ecosystems.

Evidence-first implementation planning skills for AI coding agents — gated 7-phase planning (deep-plan) + knowledge ingestion into AGENTS.md/ARCHITECTURE.md/ROADMAP.md (deep-plan-ingest)

Reusable Agent Skills for AI coding agents, with CrewAI expertise, project scaffolding, audits, and input-driven engineering specifications.

Portable AI-agent skills (SKILL.md) for accommodation search, availability, pricing, cross-OTA comparison & reviews via StayingAPI. Works with Claude, MCP and more. MIT-0.

Governed compliance evidence from AIops audit trails: HIPAA/PCI-DSS/SOC2/GDPR, hash-chain-sealed, 15 MCP tools (preview)

Map the unknowns of a task before you build it. A five-stage interview that hands you a four-quadrant map you keep.

Portable Python code-review skills for agentskills.io-compatible agents — router plus focused skills for type safety, error handling, anti-patterns, async, and code style

Runtime coverage auditing for AI agent skills and workflow instructions.

Claude Code skills for reading high-res photos at full native detail — tile past the vision downscale, transcribe labels verbatim, generate searchable photo sidecars

Give your AI a spine. Less agreement, more honest work.

42 agent-discipline skills for Cursor, distilled by watching an autonomous terminal coding agent (Claude Code + Fable 5). Includes the derivation method.

Multi-agent delivery workflow for Codex and SKILL.md-compatible coding agents

Skill open-source de auditoria e otimização de Meta Ads (Facebook, Instagram, Threads) para o Claude Code. Comando /ads: Pixel/CAPI, diversidade de criativos e Entity-ID clustering (Andromeda + GEM + Lattice), tracking server-side, atribuição, budget, PPC math e geração de criativos por IA.

Sequential thinking as a CLI + Agent Skill — file-backed, compaction-proof thought chain replacing the sequential-thinking MCP server

AI agent skills for Claude Code, Cursor, and Codex — built for AI architects. Install: npx skills add frankxai/skills

Local acceptance gate for coding-agent changes — skills-only plugin for Claude Code and Codex

Deterministic pre-install security auditing and release verification for AI Agent Skills.

Agent skills for fast, verifiable codebase documentation and navigation

Agent Skills for AI coding agents. codebase-seo: SEO + GEO audit that traces redirect loops, lints JSON-LD, and applies the fixes in your codebase.

DocsBot Admin MCP plugin and portable agent skill packages

Benchmarks LLM reviewers on a fault-seeded corpus: does a second opinion from a different model actually catch more, by defect class?

Claude Code skill that measures how visible a company or market is to AI assistants (ChatGPT) and maps who gets recommended and why.

Vrbo agent skills (SKILL.md) — vacation-rental search, availability, prices and reviews for any AI agent, via StayingAPI. OpenClaw, Hermes, Claude Code, Cursor. MIT-0.

Google Hotels agent skills (SKILL.md) — search, cross-OTA price comparison, prices and reviews for any AI agent, via StayingAPI. OpenClaw, Hermes, Claude Code, Cursor. MIT-0.

Eisenhower matrix skill for Hermes Agent — capture tasks via text, image or voice, AI-suggested prioritization | Eisenhower-Matrix-Skill für den Hermes Agent (DE/EN)

AI落地第四声 agent skills and apps