Test
10,858 rows, by stacks then stars
1,559 of these skill files have been read, by 1,201 distinct authors, and what they tell an agent counted. What Test authors agree on, and what they forbid
xAmirHamza77/PenKit51/skills/business-logic-testing Skill
no license2★ repoPenKit51 — Open-source AI penetration testing platform with 63 deep exploitation skills, multi-agent orchestration, PoC-validated findings, and native assistant skills for Claude, ChatGPT, and Grok. Authorized testing only.
xAmirHamza77/PenKit51/skills/command-injection-testing Skill
no license2★ repoPenKit51 — Open-source AI penetration testing platform with 63 deep exploitation skills, multi-agent orchestration, PoC-validated findings, and native assistant skills for Claude, ChatGPT, and Grok. Authorized testing only.
xAmirHamza77/PenKit51/skills/container-security-testing Skill
no license2★ repoPenKit51 — Open-source AI penetration testing platform with 63 deep exploitation skills, multi-agent orchestration, PoC-validated findings, and native assistant skills for Claude, ChatGPT, and Grok. Authorized testing only.
xAmirHamza77/PenKit51/skills/csrf-testing Skill
no license2★ repoPenKit51 — Open-source AI penetration testing platform with 63 deep exploitation skills, multi-agent orchestration, PoC-validated findings, and native assistant skills for Claude, ChatGPT, and Grok. Authorized testing only.
xAmirHamza77/PenKit51/skills/deserialization-testing Skill
no license2★ repoPenKit51 — Open-source AI penetration testing platform with 63 deep exploitation skills, multi-agent orchestration, PoC-validated findings, and native assistant skills for Claude, ChatGPT, and Grok. Authorized testing only.
xAmirHamza77/PenKit51/skills/django-security-testing Skill
no license2★ repoPenKit51 — Open-source AI penetration testing platform with 63 deep exploitation skills, multi-agent orchestration, PoC-validated findings, and native assistant skills for Claude, ChatGPT, and Grok. Authorized testing only.
xAmirHamza77/PenKit51/skills/fastapi-security-testing Skill
no license2★ repoPenKit51 — Open-source AI penetration testing platform with 63 deep exploitation skills, multi-agent orchestration, PoC-validated findings, and native assistant skills for Claude, ChatGPT, and Grok. Authorized testing only.
xAmirHamza77/PenKit51/skills/file-upload-testing Skill
no license2★ repoPenKit51 — Open-source AI penetration testing platform with 63 deep exploitation skills, multi-agent orchestration, PoC-validated findings, and native assistant skills for Claude, ChatGPT, and Grok. Authorized testing only.
Firebase firestore security testing
xAmirHamza77/PenKit51/skills/firebase-firestore-security-testing Skill
no license2★ repoPenKit51 — Open-source AI penetration testing platform with 63 deep exploitation skills, multi-agent orchestration, PoC-validated findings, and native assistant skills for Claude, ChatGPT, and Grok. Authorized testing only.
xAmirHamza77/PenKit51/skills/graphql-security-testing Skill
no license2★ repoPenKit51 — Open-source AI penetration testing platform with 63 deep exploitation skills, multi-agent orchestration, PoC-validated findings, and native assistant skills for Claude, ChatGPT, and Grok. Authorized testing only.
xAmirHamza77/PenKit51/skills/header-injection-testing Skill
no license2★ repoPenKit51 — Open-source AI penetration testing platform with 63 deep exploitation skills, multi-agent orchestration, PoC-validated findings, and native assistant skills for Claude, ChatGPT, and Grok. Authorized testing only.
Http request smuggling testing
xAmirHamza77/PenKit51/skills/http-request-smuggling-testing Skill
no license2★ repoPenKit51 — Open-source AI penetration testing platform with 63 deep exploitation skills, multi-agent orchestration, PoC-validated findings, and native assistant skills for Claude, ChatGPT, and Grok. Authorized testing only.
xAmirHamza77/PenKit51/skills/idor-testing Skill
no license2★ repoPenKit51 — Open-source AI penetration testing platform with 63 deep exploitation skills, multi-agent orchestration, PoC-validated findings, and native assistant skills for Claude, ChatGPT, and Grok. Authorized testing only.
Information disclosure testing
xAmirHamza77/PenKit51/skills/information-disclosure-testing Skill
no license2★ repoPenKit51 — Open-source AI penetration testing platform with 63 deep exploitation skills, multi-agent orchestration, PoC-validated findings, and native assistant skills for Claude, ChatGPT, and Grok. Authorized testing only.
xAmirHamza77/PenKit51/skills/kubernetes-security-testing Skill
no license2★ repoPenKit51 — Open-source AI penetration testing platform with 63 deep exploitation skills, multi-agent orchestration, PoC-validated findings, and native assistant skills for Claude, ChatGPT, and Grok. Authorized testing only.
xAmirHamza77/PenKit51/skills/ldap-injection-testing Skill
no license2★ repoPenKit51 — Open-source AI penetration testing platform with 63 deep exploitation skills, multi-agent orchestration, PoC-validated findings, and native assistant skills for Claude, ChatGPT, and Grok. Authorized testing only.
xAmirHamza77/PenKit51/skills/llm-prompt-injection-testing Skill
no license2★ repoPenKit51 — Open-source AI penetration testing platform with 63 deep exploitation skills, multi-agent orchestration, PoC-validated findings, and native assistant skills for Claude, ChatGPT, and Grok. Authorized testing only.
xAmirHamza77/PenKit51/skills/mass-assignment-testing Skill
no license2★ repoPenKit51 — Open-source AI penetration testing platform with 63 deep exploitation skills, multi-agent orchestration, PoC-validated findings, and native assistant skills for Claude, ChatGPT, and Grok. Authorized testing only.
xAmirHamza77/PenKit51/skills/mobile-app-security-testing Skill
no license2★ repoPenKit51 — Open-source AI penetration testing platform with 63 deep exploitation skills, multi-agent orchestration, PoC-validated findings, and native assistant skills for Claude, ChatGPT, and Grok. Authorized testing only.
xAmirHamza77/PenKit51/skills/nestjs-security-testing Skill
no license2★ repoPenKit51 — Open-source AI penetration testing platform with 63 deep exploitation skills, multi-agent orchestration, PoC-validated findings, and native assistant skills for Claude, ChatGPT, and Grok. Authorized testing only.
xAmirHamza77/PenKit51/skills/network-penetration-testing Skill
no license2★ repoPenKit51 — Open-source AI penetration testing platform with 63 deep exploitation skills, multi-agent orchestration, PoC-validated findings, and native assistant skills for Claude, ChatGPT, and Grok. Authorized testing only.
xAmirHamza77/PenKit51/skills/nextjs-security-testing Skill
no license2★ repoPenKit51 — Open-source AI penetration testing platform with 63 deep exploitation skills, multi-agent orchestration, PoC-validated findings, and native assistant skills for Claude, ChatGPT, and Grok. Authorized testing only.
xAmirHamza77/PenKit51/skills/nosql-injection-testing Skill
no license2★ repoPenKit51 — Open-source AI penetration testing platform with 63 deep exploitation skills, multi-agent orchestration, PoC-validated findings, and native assistant skills for Claude, ChatGPT, and Grok. Authorized testing only.
xAmirHamza77/PenKit51/skills/oauth-security-testing Skill
no license2★ repoPenKit51 — Open-source AI penetration testing platform with 63 deep exploitation skills, multi-agent orchestration, PoC-validated findings, and native assistant skills for Claude, ChatGPT, and Grok. Authorized testing only.
xAmirHamza77/PenKit51/skills/open-redirect-testing Skill
no license2★ repoPenKit51 — Open-source AI penetration testing platform with 63 deep exploitation skills, multi-agent orchestration, PoC-validated findings, and native assistant skills for Claude, ChatGPT, and Grok. Authorized testing only.
Path traversal lfi rfi testing
xAmirHamza77/PenKit51/skills/path-traversal-lfi-rfi-testing Skill
no license2★ repoPenKit51 — Open-source AI penetration testing platform with 63 deep exploitation skills, multi-agent orchestration, PoC-validated findings, and native assistant skills for Claude, ChatGPT, and Grok. Authorized testing only.
xAmirHamza77/PenKit51/skills/prototype-pollution-testing Skill
no license2★ repoPenKit51 — Open-source AI penetration testing platform with 63 deep exploitation skills, multi-agent orchestration, PoC-validated findings, and native assistant skills for Claude, ChatGPT, and Grok. Authorized testing only.
xAmirHamza77/PenKit51/skills/race-conditions-testing Skill
no license2★ repoPenKit51 — Open-source AI penetration testing platform with 63 deep exploitation skills, multi-agent orchestration, PoC-validated findings, and native assistant skills for Claude, ChatGPT, and Grok. Authorized testing only.
xAmirHamza77/PenKit51/skills/source-aware-whitebox-testing Skill
no license2★ repoPenKit51 — Open-source AI penetration testing platform with 63 deep exploitation skills, multi-agent orchestration, PoC-validated findings, and native assistant skills for Claude, ChatGPT, and Grok. Authorized testing only.
xAmirHamza77/PenKit51/skills/sql-injection-testing Skill
no license2★ repoPenKit51 — Open-source AI penetration testing platform with 63 deep exploitation skills, multi-agent orchestration, PoC-validated findings, and native assistant skills for Claude, ChatGPT, and Grok. Authorized testing only.
xAmirHamza77/PenKit51/skills/ssrf-testing Skill
no license2★ repoPenKit51 — Open-source AI penetration testing platform with 63 deep exploitation skills, multi-agent orchestration, PoC-validated findings, and native assistant skills for Claude, ChatGPT, and Grok. Authorized testing only.
xAmirHamza77/PenKit51/skills/ssti-testing Skill
no license2★ repoPenKit51 — Open-source AI penetration testing platform with 63 deep exploitation skills, multi-agent orchestration, PoC-validated findings, and native assistant skills for Claude, ChatGPT, and Grok. Authorized testing only.
xAmirHamza77/PenKit51/skills/subdomain-takeover-testing Skill
no license2★ repoPenKit51 — Open-source AI penetration testing platform with 63 deep exploitation skills, multi-agent orchestration, PoC-validated findings, and native assistant skills for Claude, ChatGPT, and Grok. Authorized testing only.
xAmirHamza77/PenKit51/skills/supabase-security-testing Skill
no license2★ repoPenKit51 — Open-source AI penetration testing platform with 63 deep exploitation skills, multi-agent orchestration, PoC-validated findings, and native assistant skills for Claude, ChatGPT, and Grok. Authorized testing only.
xAmirHamza77/PenKit51/skills/xpath-injection-testing Skill
no license2★ repoPenKit51 — Open-source AI penetration testing platform with 63 deep exploitation skills, multi-agent orchestration, PoC-validated findings, and native assistant skills for Claude, ChatGPT, and Grok. Authorized testing only.
xAmirHamza77/PenKit51/skills/xss-testing Skill
no license2★ repoPenKit51 — Open-source AI penetration testing platform with 63 deep exploitation skills, multi-agent orchestration, PoC-validated findings, and native assistant skills for Claude, ChatGPT, and Grok. Authorized testing only.
xAmirHamza77/PenKit51/skills/xxe-testing Skill
no license2★ repoPenKit51 — Open-source AI penetration testing platform with 63 deep exploitation skills, multi-agent orchestration, PoC-validated findings, and native assistant skills for Claude, ChatGPT, and Grok. Authorized testing only.
anoopsg/agent_rules/src/exclusive/skills/create-test Skill
2★ repoBehavioral blueprints for agents.
anoopsg/agent_rules/src/exclusive/skills/flutter-golden-testing Skill
2★ repoBehavioral blueprints for agents.
TeamDzX/myllm-skills/skills/unit-tests Skill
2★ repoCurated open Agent-Skill format skills for MyLLM (the on-device iOS AI agent). Install with /skill add teamdzx/myllm-skills.
kimgoetzke/coding-agent-configs/skills/review-pr Skill
2★ repoMy personal skills, agents, and other configuration files for agentic coding.
kimgoetzke/coding-agent-configs/skills/rust-bevy-test-conventions Skill
2★ repoMy personal skills, agents, and other configuration files for agentic coding.
kimgoetzke/coding-agent-configs/skills/tdd Skill
2★ repoMy personal skills, agents, and other configuration files for agentic coding.
maurigre/mgr-method/skills/junit-clean Skill
no license2★ repoMGR — Método Governado por Rastreabilidade (Traceability-Governed Method): spec-driven development framework for coding agents, portable between Claude Code and GitHub Copilot
oscarqjh/super-agent-skills/plugins/super-agent-skills/skills/browser-testing-with-devtools Skill
no license2★ repoFull-lifecycle engineering plugin for Claude Code — brainstorm → plan → build → review → ship, with production-grade standards at every step.
oscarqjh/super-agent-skills/plugins/super-agent-skills/skills/test-driven-development Skill
no license2★ repoFull-lifecycle engineering plugin for Claude Code — brainstorm → plan → build → review → ship, with production-grade standards at every step.
3awny/qship/templates/skills/qbug Skill
2★ repoTicket → production-PR pipeline for Claude Code & Codex CLI, enforced by hooks. 21-skill pipeline, one configurator, adapts to any codebase.
3awny/qship/templates/skills/qcheckt Skill
2★ repoTicket → production-PR pipeline for Claude Code & Codex CLI, enforced by hooks. 21-skill pipeline, one configurator, adapts to any codebase.
vignesh2027/AI-AGENT-SKILLS/skills/test-driven-development Skill
2★ repoTurn your ai agent into senior engineer..The result is fast code that fails slowly. AI Agent Skills solves this by giving agents the same disciplined workflows senior engineers use
jvalin17/agent-toolkit/skills/evaluate Skill
2★ repoProduction-ready skills for AI coding agents. 13 skills, 9 agents, harness hooks & quality gates (signed optional for long sessions). Plan, build, test, debug, ship. Any repo, any language. Claude Code native, universal LLM compatible.
jvalin17/agent-toolkit/skills/reviewer Skill
2★ repoProduction-ready skills for AI coding agents. 13 skills, 9 agents, harness hooks & quality gates (signed optional for long sessions). Plan, build, test, debug, ship. Any repo, any language. Claude Code native, universal LLM compatible.
AllanWessels/Bratan/docs/build-skills/audit-then-fanout-fix Skill
no license2★ repoBratan is a self-improving Retrieval-Augmented Generation framework built on an adversarial three-agent loop
AllanWessels/Bratan/docs/build-skills/fix-first-then-test Skill
no license2★ repoBratan is a self-improving Retrieval-Augmented Generation framework built on an adversarial three-agent loop
Observable outcome tests over mocks
AllanWessels/Bratan/docs/build-skills/observable-outcome-tests-over-mocks Skill
no license2★ repoBratan is a self-improving Retrieval-Augmented Generation framework built on an adversarial three-agent loop
angad-kandhari/deliberate/skills/pentest Skill
2★ repoEngineering discipline for AI harnesses. Drop-in skill library for LLM coding agents.
angad-kandhari/deliberate/skills/test Skill
2★ repoEngineering discipline for AI harnesses. Drop-in skill library for LLM coding agents.
maxkle1nz/deviance-skills/claude/pr00f Skill
2★ repoOperational doctrine as installable skills for Claude Code and Codex — the DEViance Intelligence method pack.
kimtth/agent-skill-100-lines-or-less/skills/load-testing Skill
no license2★ repo🧿 Minimal but effective AI agent skill definitions in 100 lines or less.
kimtth/agent-skill-100-lines-or-less/skills/mocking Skill
no license2★ repo🧿 Minimal but effective AI agent skill definitions in 100 lines or less.
kimtth/agent-skill-100-lines-or-less/skills/playwright-best-practices Skill
no license2★ repo🧿 Minimal but effective AI agent skill definitions in 100 lines or less.