Library
85,762 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
specsfy
SkillsO Specsfy ajuda você a transformar uma ideia em software testado sem espalhar requisitos, planos e tarefas por vários arquivos.
git clone https://github.com/promovaweb/specsfy.git -
webapp-testing
SkillsToolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
/plugin marketplace add anthropics/skills -
repro-lens
SkillsStatic reproducibility checks, experiment replay, and verification for ML pipelines.
git clone https://github.com/00200200/repro-lens.git -
browser-debugger-cli
SkillsLet Claude Code and other coding agents drive and debug Chrome from the shell. DOM, network, console and raw CDP as short commands, no screenshots and no MCP needed.
git clone https://github.com/szymdzum/browser-debugger-cli.git -
founder-skill
SkillsEleven free Claude skills that test a business before you launch it: a board trained on Hormozi, Thiel and Jobs, a marketing director, a CFO, and a consumer panel of 100 buyer agents. Free, MIT.
git clone https://github.com/Jakeschincariol/founder-skill.git -
robotics-agent-skills
SkillsAgent skills that make AI coding assistants write production-grade robotics software. ROS1, ROS2, design patterns, SOLID principles, and testing — for Claude Code, Cursor, Copilot, and any SKILL.md-compatible agent.
git clone https://github.com/arpitg1304/robotics-agent-skills.git -
Claude-AD
SkillsActive Directory pentest methodology for Claude Code: skills, agents and slash commands for internal AD red-team work (Kerberoasting, ADCS ESC1-17, DCSync, ACL abuse, NTLM relay, delegation), with per-technique OPSEC/telemetry notes. Drives netexec, impacket, certipy, bloodyAD, BloodHound CE.
git clone https://github.com/ADScanPro/Claude-AD.git -
redteam-skill
SkillsRedteam / Pentest Skill Pack — semi-automated workflow + on-demand module selection + real-world attack chains | Kali + Claude Code 红队/渗透/技能包 - 半自动工作流 + 按需点选模块 + 实战利用链 | 基于 Kali 与 Claude Code
git clone https://github.com/pale-knight/redteam-skill.git -
claude-codex-settings
SkillsBattle-tested Claude Code, OpenAI Codex, Cursor configs, plugins, hooks and agents with Kimi, MiniMax and GLM API support.
git clone https://github.com/fcakyon/claude-codex-settings.git -
market-mirror
SkillsOpen-source marketing simulation for AI agents. Test ads, pricing, emails and pitches with synthetic buyers; inspect objections and plan real customer experiments. Self-hosted, MCP-ready, AGPL-3.0.
git clone https://github.com/DarkWorldCoder/market-mirror.git -
claude-skills
SkillsClaude Code plugin marketplace: AIDA, a spec-driven, test-first development process for AI coding agents, plus plugins for Drupal contribution, code quality audits, paper testing, plugin checks, brand content and dev guides.
git clone https://github.com/camoa/claude-skills.git -
oh-my-agent
SkillsAgent skills and specialist teams for Claude Code, Codex, Cursor and other coding agents. Load one skill or install domain presets, project hooks and parallel workflows with test gates.
git clone https://github.com/first-fluke/oh-my-agent.git -
done-is-a-claim
SkillsYour coding agent says done. Show the receipt. Evidence-first workflows, practical skills, and plugins for Claude Code and Codex.
git clone https://github.com/Grit-77/done-is-a-claim.git -
hermes-jailbench
SkillsZero-LLM deterministic jailbreak regression benchmark: runs a repeatable battery of known-pattern attacks against an LLM endpoint and scores refusal/partial/compliance across runs. Catch when a model or prompt update silently got weaker. Single-turn, responsible-use. pip install hermes-jailbench
git clone https://github.com/hermes-labs-ai/hermes-jailbench.git -
claude-night-market
Skills23 Claude Code plugins: TDD enforcement hooks, git/PR workflows, spec-driven development, code review, project lifecycle, fix-from-error, maintenance automation, context optimization, research, and multi-LLM delegation. 186 skills, 128 commands, 54 agents.
git clone https://github.com/athola/claude-night-market.git -
opencode-skill-creator
SkillsCreate, test, and optimize OpenCode skills. Supports OpenCode V2 and V1 ≥ 1.18.29. Adapted from Anthropic's skill-creator.
git clone https://github.com/antongulin/opencode-skill-creator.git -
tdd
SkillsTest-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.
-
pojun-skill
SkillsPojun 方法论蒸馏成的可移植 Agent Skill:三视角协议 + 三账本证据纪律 + L1-L4 证据分级 + 四层安全护栏 + SRC 打法速查,任意 AI Agent 即装即用 | Pojun pentest methodology as a portable Agent Skill
git clone https://github.com/chu0119/pojun-skill.git -
wicked-garden
SkillsThe skills your coding agent can't build alone: done re-checked from evidence, graph-aware refactor, 40 QE specialists, review panels from other models.
git clone https://github.com/mikeparcewski/wicked-garden.git -
han
SkillsHan: AI skills and agents for "Solo" product engineers and small teams
git clone https://github.com/testdouble/han.git -
skills
SkillsAgent skills that make coding agents show their work: read a Jam, prove a change, point at the problem, test a flow. Works with Claude Code, Cursor, Codex, Copilot and Gemini CLI.
git clone https://github.com/jamdotdev/skills.git -
migrate-to-shoehorn
SkillsMigrate test files from `as` type assertions to @total-typescript/shoehorn. Use when user mentions shoehorn, wants to replace `as` in tests, or needs partial test data.
-
disciplined-vibe-coding
SkillsA coding agent skill pack for non-engineers and vibe coders -- Define/Plan/Build/Verify discipline, plain language, stakes-aware guardrails.
git clone https://github.com/bmtrnavsky/disciplined-vibe-coding.git -
go-development-skill
SkillsAgent Skill: Enterprise Go development patterns - resilient services, testing | Claude Code compatible
git clone https://github.com/netresearch/go-development-skill.git
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.