A Claude skill for implementing changes on a git repo (or a bare set of files) and delivering the result as verified `git format-patch` files you apply with `git am`.

An advisory board of real, well-documented experts you choose. Quorum audits your launched business and returns a prioritized backlog, roadmap, and prioritization framework. Works in Claude Code, Codex, and any LLM.

Clear instead of compact — two Claude Code skills: /handoff distills a session to disk, /resume reads it back into a fresh context.

Point-and-click feedback from your running app to your AI coding agent. Dev-only overlay for React/Next, install as Claude skill.

Claude Code skill: pause the agent, rate 50-100 artifacts by gut feel in 15 minutes, hand it a personalized scorer instead of a lying proxy metric.

Interactive docs for coding agents. Agents publish research as readable sessions; humans read, annotate, and decide, then send answers back as one prompt.

Zero-trust security design for the frontier, the garage, and the lone cowboy. / SNS運用・開発・科学・映像/美術制作といった複数職能を一人で回すワンオペラボ特有の非対称性リスク(得意領域の裏で必ず生じる手薄な領域の歪み)を鑑定するスキル。サードパーティ/ライブラリの選定判断や、マーケティング物量投下の射程・優先度を管理する場面で使う。辺境で戦う一人ラボ・小規模MADサイエンティストなど、資本力で殴れない側(弱者)がリソース配分を見誤らないための、通称ペインスカウター/ラバーバンドアライメント鑑定ツール。

Clone a Claude Code brain — package/redact/distribute memory, skills, agents & rules; one-click install others' brains; export to Codex/Gemini/Cursor/OpenCode.

Claude/agent skill: analyze LinkedIn post engagement and find top-performing posts. Installs via npx skills add.

Selected agent skills

Claude Skill for professional harness engineering — audits your repo like a senior engineer, finds gaps, and installs an adapted harness so AI agents work reliably across sessions.

A localized Claude Code skill that automatically parses asset portfolios, fetches live market data in EUR, and generates an executive HTML/PDF net worth dashboard with zero token bloat.

A workshop of personal Claude Code skills — design, build, and writing craft

Score a spec's autonomous-build readiness before any code exists — a portable Agent Skill that red-teams your PLAN/SPEC from a zero-context builder's seat. Works in Claude Code & opencode.

Security review skill for Claude Code. Vet any skill before you install it, because a skill is executable code and the risky part is rarely in the SKILL.md.

Six Claude Code skills for running a research lab: grant writing, manuscript revision, literature scouting, file triage, reimbursement tracking, and PI operations. Install into ~/.claude/skills/.

Bizer's open AI agent skills library — portable SKILL.md bundles backed by published research and evaluations. Works in any agent, best in Bizer.

Answer Engine Optimization plugin for Claude. 12 skills (1 orchestrator + 11 specialists) that get brands cited by ChatGPT, Perplexity, Claude, and Google AI Overviews: client-ready AI visibility audits with dollar figures, citation testing, AEO content restructuring, JSON-LD schema, E-E-A-T scoring & More.

Created to support my ADHD, probably useful for everyone. Always-on Claude Code working-mode skill that helps you stay in-flow, action-first, one step at a time. Transparent by default.

A collection of AI agent skills for optimizing political campaign websites for AI search (GEO). Built for candidates, campaign managers, and advocacy staff who want to help their site get accurately read and cited.

Portable Agent Skills (SKILL.md) for Claude Code, OpenAI Codex, and other AI coding agents

A Claude Code skill that triages your support inbox and drafts replies for human review. Works with any support tool that ships an MCP server.

Five Claude Code skills distilled from a solo consultant's daily practice: plain-language explanations, PRD planning and execution, project bootstrap, safe copy-paste.

A reusable meta-prompt that turns any use case into a high-quality, ready-to-use LLM prompt — Claude-first, with Gemini/GPT fallbacks.

Spec-first skills for Claude Code. Turns a rough idea into a technical spec precise enough to build from.

Time-boxed pre-launch security playbook for MVPs and SaaS shipped fast.

Apply framework-agnostic coding standards to your Roblox projects for cleaner, secure, and efficient Luau scripts.

Preview listings for 22 compliance/ops Claude Code skills — full skills sold on Agensi

Claude/agent skill: track keyword rankings on Yandex by region over time. Installs via npx skills add.

把 PDF 课件/讲义/教材整理成结构化复习笔记 — Claude Code / agent skill

Standalone proof that six Claude Code skills develop a Godot 4.6 feature end-to-end: from an Excel backlog to a runnable SmartThings home view (shaders, animation, UI, integration). Includes one-step Linux/Windows setup.

For small-nonprofit leaders: win grants, keep donors, and run a board that engages.

Everything was going great - until a key subagent process died silently, your custom agent moved to a worktree but never came back, and you accidentally spawned a session in the wrong project cwd (again). This pack of atomic, independent skills/hooks/tests forces some discipline on the rowdy fleet. Targeting VSCode/Gitflow workflows.

Free, keyless, liveness-verified APIs for real data - Claude executes instead of deliberating.

Humanizer skill for Claude: rebuild AI text in a human voice while freezing every fact. Benchmarked: beat the raw baseline on blind preference 8-4 (after publishing 3 honest failures).

Recommend life insurance policy for users in Singapore

Read books with Claude, one question at a time — a Claude Code skill that plans your read, sends one short prompt per chunk, gives feedback on your answers, and keeps all notes as local Markdown. 对话式读书

A review-gated shipping pipeline for Claude Code: fresh-context spec & diff review, gated auto-merge, a PR merge-tail babysitter, and an honest deploy ceremony.

Battle-tested agent skills on judgment before action, distilled from real OSS work

Claude will tell you your idea is great. This skill makes it try to kill it first.

Claude skills for the hard parts of building, now that ai made the building easy

15 gate-style skills that give Claude Code the discipline of a senior engineer — observable preconditions, not advice. Survives model downgrades.

Working Claude Code skills from a real agency. Token tracking, plan-limit gauges, burn optimization. Stdlib-only Python, 100% local, no telemetry.

Two open-source Claude skills: build interactive HTML books that teach any topic, and forge raw ideas into workable plans.

Optimized GitHub skill for coding agents: fewer tool calls, less context burned, lower cost, faster answers. One bounded call each for PR state, review threads, and CI failures.

13 agent skills distilled from Wheeler & Meyerson's Designing Brand Identity (6e) — fundamentals, the 10 ideals, brandmark taxonomy, the 5-phase process, case studies, and a /brand router.

Claude skill: removes AI writing tells and enforces honest claims. 63 patterns from Wikipedia's Signs of AI Writing + detector research

Claude/agent skill: use Google Flights as an API, structured flight results by route and date. Installs via npx skills add.

精读并拆解学术论文（PDF），按类型自动适配模板 — Claude Code / agent skill

Claude/agent skill: Google News articles as structured JSON. Installs via npx skills add.

Goldilocks：精简的 Superpowers 替代方案｜v0.4.1 Direct 对照 114/114 通过，处理 token −11.5%、耗时 −10.9%、官方成本 −6.3%。Lean, token-efficient AI agent workflow for Codex & Claude Code.

🧠 Original Claude Agent Skills for AI-native digital marketing — GEO/AEO, paid ads, SEO, and content systems. Built by Archit Shah. All rights reserved.

Claude/agent skill: scrape hotel prices from Google Hotels into structured JSON. Installs via npx skills add.

Color-agnostic Stripe design system skill for Claude Code

实战沉淀的 Claude 技能合集：说人话/代码升级/开源项目研究/项目开源/Obsidian维护 | Battle-tested Claude Code skills: humanized writing, code renovation, safe OSS research & publishing, vault maintenance

Local-first WeChat public-account and Weibo archiver for verified Markdown/JSONL knowledge bases and AI agents.

An advanced, universal developer plugin for the **Antigravity** coding environment. **dyy-plugin** packages dynamic developer rules, modular agent personas (subagents), and optimized conventional workflow scripts for seamless frontend, backend, and Linux window manager (ricing) customization.