Claude skill + drop-in code for hardening & auditing LLM features against prompt injection, privilege escalation, marker forgery, and data leaks

Claude Code plugin: tech-lead interview -> multi-file execution plan -> sprint-by-sprint execution -> zero-trust audit -> handoff. Guarded against both lazy shortcuts and over-engineering.

Open Agent Skill for portable, beginner-friendly low-fidelity product prototypes

PIÉNSALO is the open artificial cortex for AI—reduce context tokens, verify response quality, expand when needed, and safely fall back.

Bring your Claude Code skill unchanged and run it as a governed Databricks job. Publish once to a Unity Catalog volume, reuse from any job, chain skills into a pipeline (markdown in, branded PowerPoint out). No external API key. Runs on Free Edition.

Git branch/worktree lifecycle skills for Claude Code (worktree, branch, PR, cleanup)

Agent skill for safe PCANBasic and python-can operations, CAN-FD timing, status handling, and recovery.

Extract records from chats. Point Continuity at any chat with your connectors and get structured records out.

A hub of reusable agent skills: CrossThink (divergent cross-domain brainstorming methodology), and more. Built for OpenCode, Claude Code, and Codex.

A linter for your translation files: catches missing keys, placeholder mismatches, and untranslated values before they ship. Stdlib Python, zero deps. CLI, CI gate, pre-commit, and agent skill.

RSSHub route builder skill — generates complete, PR-ready RSSHub route code (namespace.ts + handler + Radar rules + PR checklist) from a target website

Evidence-grounded product marketing and creative production agent skill — spec and starter scaffold

🧭 Evidence-grounded Chinese longform research for Claude Code and Codex — select, test, and apply the right frame.

开源多智能体矩阵：Manager 总管调度 RAG、DB、Code、Extractor、Lobster、Music、Video 等子 Agent。Nuxt · FastAPI · Playwright · pgvector · Compose，企业级参考实现。

Two agent skills to keep a long-running AI agent from getting stuck: north-star (delivery-point self-correction hook) + moa (N+1 multi-model consultation).

A durable, cross-repo knowledge hub for Claude Code — capture/distill/review skills + install script. Empty starter template.

Cross-harness Agent Skill: terminal & coding-agent orchestration via the forge PTY daemon — Claude Code, Codex, Gemini, OpenCode, and Amplifier, with an artifact-gated multi-agent relay controller

Deterministic Agent Skill and workflow for accessibility, tokens, responsive UI, and design regression gates

Toolkit for agentic development of Laravel & React apps

Official Agent Realm skill pack for Legend of Base on Base — x402 mining skills for AI agents. Sponsored by Uptopia.

Governed source and release layer for Agent Skills.

Turn approved plans into local, resumable agent work with durable handoffs and human pause/resume.

An Agent Skill for academic research, course synchronization, citation auditing, and source-grounded writing.

Clean-room Codex Skill for cold-mist porcelain UI design, review, and image-asset planning.

Map-first folder reorg for AI agents — plan first, approved-only execute, audit trail. Skill + pwsh/Python CLI.

AdsAgent tri-channel AI skills for Meta, Google Ads, and TikTok hosted MCP

Grade the AI agent skills you've installed — safety, token bloat, and conflicts. 100% local static analysis, no model, no signup. The Consumer Reports for SKILL.md.

Frontier operating discipline for Claude on any model, plus loop and automation suggestions. An open-source Agent Skill.

Authoritative SwiftUI best practices, packaged as an AI coding skill (Cursor / Claude Code). Apple-sourced guidance.

A logic pyramid skill that makes AI set the conclusion first and answer in the order a reader can follow. Based on Barbara Minto's Pyramid Principle. For Claude Code and Codex.

Cross-agent PyMOL skill for reproducible molecular scene authoring from CIF/PDB structures and residue annotations.

Research-traceable UI/UX skills for AI coding agents.

EliseDai personal AI-native PPT Skill with black, white, gray and Signal Blue editorial style

A source-verifiable, art-directed AI industry daily report skill that generates responsive single-page HTML.

🧭 Stop guessing. Start building. A 95%-confidence requirement clarification gate for Codex and AI agents—ask less, learn more, execute safely.

Local-first personal launchpad and public store for Agent Skills on macOS

Evidence-aware product-management skills and reviewer agents for discovery, strategy, build, launch, and iteration.

Proven UX flows, user journeys, and app layout patterns packaged as agent skills for Claude Code, Codex, Gemini CLI, and any coding agent

Claude Code plugin: FastAPI best practices (41 rules, 13 categories) grounded in the official FastAPI docs

Converts plain markdown into OKF-conformant knowledge bundles

Original, tested agent skills for interface reviews, product quality, accessibility, motion, and responsive UI work.

Open Agent Skill for building source-grounded AI expert knowledge systems

Scope-first agent design skill — ถามขอบเขตให้ชัด ก่อนสร้างเอเจน

Adaptive preflight skills for AI agents: clarify intent, find capability gaps, review tools, and control context cost.

End-to-end Godot 4 Agent Skill for playable 2D/3D games, GDScript, AI, UI, networking foundations, and visual QA.

Claude Fable 5 orchestrator for React Native/Expo — Grok 4.5 Heavy implements; Argent UI verify; STATUS + ledger multi-agent chains

DECISIONS.md — ratified, append-only, falsifiable decision records for humans working with AI agents. Case law for the delegation era.

Open a second coding agent in a herdr pane and have it review your diff — watchable, auto-approve, read-only. Ships a Claude Code skill for the autonomous review↔revise↔decide loop.

Local-first open toolkit for stock monitoring agents, technical indicators, Skills, prompts, and MCP

Agent-first GTM operating manual template: positioning, lead pipeline, outreach, playbooks, investor materials + 22 agent skills

AI keeps skipping steps? Super-Spec enforces every step with evidence. Seven-gate engineering discipline for AI coding agents: anti-corner-cutting, verification-first, spec-driven. Stop vibe coding, start spec driving. Production-grade quality for solo developers.

Prove your Agent Skill works before you publish it.

Local-first Agent Skill for citation-aware lecture search, Q&A, flashcards, and study guides.

Workflow-oriented Agent Skills for writing, coding, research, and decision alignment.

An Agent Skill for governing project documentation during development.

AI agent skill that recovers dead websites from the Wayback Machine.

陈与小金《找到你的未知》配套 Claude Code Skill：盲区扫描 + 测验验收（方法论来自 Thariq《A Field Guide to Fable》）

Stateful Goal mode skill for Codex, Claude Code, and AI agents with STATE.md memory, gates, and stop rules.

Agent Skill that turns one static reference image and motion prompt into a validated transparent animated sticker.