Coding & Development

Security Scanner for Agent Skills

Picks and Shovels for digging AI

self-improving skills. stay in the loop

Outcome driven agent development framework and runtime harness

Offline and security-first tool for syncing and managing agent skills

Portable skill lifecycle manager for AI coding agents — import, search, validate, remove. Works with skills.sh, Claude Code plugins, and any SKILL.md-compatible platform.

Portable 4-layer intelligence architecture skills. Turn any agent system into an AI-native organization with Capabilities, World Model, Intelligence & Interfaces layers.

Opinionated macOS development environment automation

Agent Skill: Native Google Sign-In for Capacitor mobile apps. Works with Claude Code, Codex CLI, and any AI tool supporting the Agent Skills standard.

Agent skill for deep philosophical and psychological conversations. Integrates Stoicism, Existentialism, CBT, ACT, Jungian psychology.

AI coding agent skill encapsulating all the kerfuffle needed to get a basic Cloudflare proejct going that I've used in past projects. D1 for storage, Workers, etc

OSINT Skill for AI agents (Claude Code, OpenClaw, Codex, OpenCode) — from a name to a scored dossier with psychoprofile, career map, and confidence grades. 55+ Apify actors, 7 search APIs, swarm mode. Early Beta.

One command to publish your agent skill to GitHub, ClawdHub, and skills.sh.

One command to diagnose your entire OpenClaw setup. Finds problems, explains impact, offers fixes.

Turn a one-line objective into a step-by-step plan any coding agent can execute cold — each step carries its own context, no prior session needed.

skills for OpenClaw: Geographic location query based on IP address

Evaluate, tune, and regression-check OpenClaw AgentSkills with bilingual docs.

skill for qrcode generate、decode

Adversarial risk gate for AI coding agents — blocks actions until you approve. Works with Copilot, Claude, Cursor, Windsurf & 40+ more.

pr-rules-sync is an agent skill for Claude Code, Cursor, and any SKILL.md-compatible AI coding agent. It scans your merged pull requests, finds patterns in what reviewers repeatedly flag, and writes those patterns as actionable rules into your AI instruction files — so your agent avoids the same mistakes your team keeps catching in code review.

Reusable Agent Skill for architecture-as-code with LikeC4: create/update C4-style models, validate, and export diagrams.

龙虾skill 查找新闻、查找资料

Safety-first OpenClaw skill for update audits, vetted skill updates, and explicit approval gates

mskills is a CLI tool to manage "Agent Skills" for various AI agents.