From raw data to board-ready insights, every step covered.

Find cloud waste before you deploy it. IaC cost audit for Terraform/CloudFormation - no AWS credentials, zero deps.

Secure Development — a Claude Code skill: 23 security reference domains + a phase-by-phase secure build lifecycle (secure-by-design).

Run Claude Code sessions that know their own context and can run themselves: real context self-check, armed-pane auto-catch-up, and a safe self-clear loop. Kijito-backed, works standalone.

Free agent skills for Claude Code and SKILL.md agents. Add with: /plugin marketplace add justhandledlabs/skills. Eleven focused tools by JustHandled Labs.

Claude Code skill: design and review prompts for external LLM services with 3-vendor integrated best practices (Anthropic/OpenAI/Edison)

2 Agent parallel deep-research skill for practical Chinese research reports

Scans AI-generated Next.js + Supabase code for the 21 most common security holes (exposed secrets, broken access control, injection) and blocks them in CI.

Anthropicの開発手法を参考にしたClaude Code / Codex向けDevLoop Skill

An agent skill that hardens npm packages before public release — catches shipped secrets, runtime-floor mismatches, and tarball junk. Works in any skills-compatible agent.

Stop writing better prompts — design the system that runs them. A cross-platform Agent Skill (Claude Code · Codex · Gemini · Cursor) that turns a vague goal into a reusable AI work system: Prompt, Context, Harness, Loop.

7 interconnected Claude Code skills: prompt polishing, engineering workflow, web research, knowledge ingestion, advisory board, and focus group simulation

🛒 Skill Bazaar — an all-in-one open collection of AI Agent Skills (SKILL.md), organized by category. Part of the Mega AI Bazaar.

Unified AI token usage telemetry — collect, store, and visualize token consumption across LiteLLM, OpenAI, Anthropic, GitHub Copilot, and flat-fee subscriptions

My dev identity as a Claude Code plugin — a full Laravel team in a box: SDLC pipeline, task board, coding agents, and audit skills.

Claude skill: 部署前 UI/UX 總體檢 — pre-deploy UI/UX review against 20 principles (Nielsen heuristics + interaction laws + accessibility), with severity-ranked issues and a go/no-go checklist

A Claude skill that clones a GitHub repo, reads its docs, fills the gaps in your local environment, installs it, and verifies it runs.

Skills for Claude Code & claude.ai — token-efficiency: measured 30-50% shorter responses at 100% assertion pass rate, with always-on hooks and an A/B eval harness

Agent Skills for QalamList self-hosted waitlist software — Cloudflare Workers deploy, D1, Turnstile, doctor checks

Claude Code plugin: author, explore, validate, and visualize Google's Open Knowledge Format (OKF) v0.1 bundles.

Claude Code plugin that takes a Linear ticket from spec to pull request: implements, loops until lint and tests pass, asks before pushing.

Keeps Claude's memory stores (CLAUDE.md, auto-memory, project memory) in sync — no more re-teaching the same thing twice.

Claude/agent skill: scrape Google Jobs listings billed per delivered result, with employer and board exclusion filters. Installs via npx skills add.

Evidence-backed UX and AI-agent case study skills for Codex and Claude

Nine Claude Code skills for Cisco network automation: backup, config gen, discovery, QoS testing, security audit.

An open source Claude Code skill and CLI that traces dbt pipeline failures back to root cause, distinguishing genuine breaks from downstream models skipped as collateral. No warehouse connection needed.

Skills I use with Claude Code every day

Claude/agent skill: track brand visibility inside Google AI Overviews. Installs via npx skills add.

Claude/agent skill: scrape Apple App Store reviews into structured JSON. Installs via npx skills add.

Claude skill: developer and engineering manager salary calculator. 15 skills, 5 pillars, level-weighted, 2026 Western-Europe market data. Standalone or via MCP.

A portable Claude skill: give it a goal, get back a reviewable design document for the harness around whatever LLM executes it — context, tools, guardrails, verification loop, and executor topology. It designs the scaffold; it never becomes the running system.

Debug any product by USING it (living the full user cycle, all features, like a picky user) instead of green tests. Start interview (Goal+Benchmark), two modes: Solo and Agentic+ (delegate fixes to agents). Claude Code skill.

Agent Skills for plori: teach any coding agent to create and drive plori agents (cloud computers for AI agents)

Coach for workplace reporting & business proposal content , PPT diagnosis , and Experience optimization.

A portable checklist for making a site usable by AI agents and legible to AI search (Claude, ChatGPT, Perplexity, Grok, Gemini, and browser agents). Based on Google's web.dev agent-friendliness guidance, the Lighthouse Agentic Browsing audit, and Google's generative-AI search guide (all 2026).

Progressive skill-loading orchestrator for Claude Code. Auto-routes multi-step tasks across connected skills without a slash command, with an optional keyword-based skill-hint hook and a one-command bootstrap installer for a known-good skill set.

Agent skills for integrating, routing, and generating media with RouterBase.

Claude/agent skill: routes, travel times, and turn-by-turn directions as structured JSON. Installs via npx skills add.

Claude/agent skill: scrape DuckDuckGo search results into structured JSON. Installs via npx skills add.

Claude/agent skill: turn App Store reviews into ASO and product feedback insight. Installs via npx skills add.

OWASP Top 10 (2025) security audit plugin for Claude Code and Cursor. Stack-aware scanning that produces a complete vulnerability report.

Training wheels for AI assisted coding. Seam aware protocols that make coding agents investigate first, gate irreversible actions, and prove their claims.

Agent skills for authoring HelpNest help-center content — installable via skills.sh (npx skills add).

Claude/agent skill: scheduled hotel rate snapshots for rate drop alerts and competitor watching. Installs via npx skills add.

Claude/agent skill: bulk Yandex SERP collection with predictable per-result billing. Installs via npx skills add.

Claude/agent skill: turn Google Jobs into a job search API feed for apps and AI agents. Installs via npx skills add.

AI Ready Software Template for Enterprise Multi-Model AI Context Architecture

上线前测试审计 Skill：用于发布前检查、回归测试规划、安全审计和 Go/No-Go 上线决策。

Turn any topic into an expert-level AI skill — for Claude, ChatGPT, Gemini, or any LLM. A meta-skill that researches a domain and writes the skill for you.

Claude Code Agent Skills for building, red-teaming and tuning agentic RL evaluation environments — a four-skill pattern (guardian, validation-debugger, score-tuner, iteration-loop) plus a 24-point adversarial reviewer.

Root-level Claude Code skill for Tree Ring Memory: local-first recall, capture, audit, consolidation, and forgetting workflows for AI agents.

Claude Code skill for safe, fast Cloudflare D1 + R2 operations on Windows - REST-based, immune to PowerShell BOM/encoding traps

Portable Agent Skills (SKILL.md) for Claude Code and compatible CLIs

Reusable Claude Skill and LLM agent framework inspired by Fable 5 reasoning workflows, prompt orchestration, tool simulation, validation, and project-level automation.

Offload Claude Code's heavy coding to Codex; keep judgment and verification on Claude.

iOS Liquid Glass Skill for Swift and React Native

Agent skill that systematically guides AI to analyze requirements and design comprehensive, traceable end-to-end test scenarios before scripting

Claude/agent skill: monitor news coverage and brand mentions on a schedule. Installs via npx skills add.