One search for your own team's files and the public ecosystem. See how real projects write their agent instructions, and bring the good ideas home.
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
jovd83Skilljovd83/bug-fix-lifecycle/SKILL.md
Use when the agent must report a newly discovered defect, implement an approved bug fix, or harden regression coverage and documentation around a known bug. This skill enforces repository-aware bug intake, failing confirmation tests before fixes, scoped verification, documentation updates when warranted, and a structured resolution report.
jovd83Skilljovd83/codebase-context/SKILL.md
Analyze a repository before engineering work begins and produce a concise context bundle covering structure, entry points, dependencies, tests, conventions, and likely risk areas. Use when the user asks for a codebase overview, wants a Phase 0 understanding pass, or when another skill would benefit from a grounded map of an unfamiliar project before implementation, review, or refactoring.
jovd83Skilljovd83/context-density-optimizer/SKILL.md
Audit the active working context and remove token noise before deeper implementation, review, or planning work. Use when Codex has accumulated too many files, notes, logs, prior summaries, or reference documents and needs to decide what to keep, drop, condense, or defer. Especially useful after broad codebase sweeps, large documentation reads, debug-log dumps, multi-skill handoffs, or whenever context relevance, signal density, or token efficiency has become uncertain.
jovd83Skilljovd83/cypress-skill/analysis/SKILL.md
Requirements-analysis skill for Cypress planning and implementation. Use when the agent needs to extract testable behaviors, acceptance criteria, risks, dependencies, or open questions from tickets, specs, markdown docs, or other requirement sources before writing tests or coverage plans.
jovd83Skilljovd83/cypress-skill/ci/SKILL.md
CI and delivery skill for Cypress automation. Use when the agent needs to design, debug, or optimize Cypress execution in GitHub Actions, GitLab CI, CircleCI, Azure DevOps, Jenkins, Docker, sharded pipelines, artifact workflows, or shared setup and teardown.
jovd83Skilljovd83/cypress-skill/core/SKILL.md
Battle-tested Cypress patterns for E2E, API, component, visual, accessibility, and security testing. Covers selectors, assertions, hooks, intercepts, auth flows, debugging, and framework recipes for React, Next.js, Vue, and Angular.
jovd83Skilljovd83/cypress-skill/cypress-cli/SKILL.md
Automates browser interactions for web testing, form filling, screenshots, and data extraction using cypress-cli. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, extract information from web pages, mock network requests, manage browser sessions, or generate test code.
jovd83Skilljovd83/cypress-skill/migration/SKILL.md
Migration skill for moving existing UI automation to Cypress. Use when the agent needs to translate Playwright or Selenium/WebDriver patterns, plan incremental migration, preserve coverage during framework change, or explain architectural differences that affect the suite design.
jovd83Skilljovd83/cypress-skill/orchestrator/SKILL.md
Central entrypoint for broad or ambiguous Cypress requests. Use when the agent needs to classify the user's testing goal, choose the right Cypress subskill, and move from intent to implementation, planning, documentation, execution, or reporting without unnecessary menu-driven back-and-forth.
jovd83Skilljovd83/cypress-skill/pom/SKILL.md
Test-architecture skill for Cypress page objects, fixtures, helpers, and custom commands. Use when the agent needs to decide whether to introduce a Page Object Model, how to structure page objects, and how to separate browser state, UI behavior, and stateless utilities cleanly.
jovd83Skilljovd83/cypress-skill/SKILL.md
Flagship Cypress skill pack for planning, authoring, debugging, documenting, and operationalizing Cypress. Routes E2E, API, component, visual, accessibility, CI/CD, coverage, docs, CLI automation, and handoff workflows.
jovd83Skilljovd83/defensive-appsec-review-skill/SKILL.md
Use when you need an authorized, non-destructive security review of repos, APIs, and cloud apps. Trigger for OWASP reviews, dependency/secret audits, scanner consolidation, and security reports. Use for AppSec triage. Do NOT use for offensive exploitation or unauthorized testing.
jovd83Skilljovd83/diagram-generator/SKILL.md
Decide which diagrams to draw, what to put in them, and which tool fits — Mermaid, PlantUML, or draw.io. Plans content from code, requirements, schemas, or ADRs and hands off rendering to a sister skill (pretty-mermaid, PlantUML-skill, or drawio-skill). Do NOT render directly.
Often used withattack-chainpentest-toolsllm-security
jovd83Skilljovd83/eu-ai-act-hitl-monitor-skill/eu-ai-act-hitl-oversight-skill/SKILL.md
Design, review, and retrofit human-oversight controls for autonomous agent systems with pause, review, resume, reject, or halt behavior. Use for EU AI Act Article 12/14 logging, human handovers, typed review-decision contracts, reviewer reports, timeout/escalation rules, or critiques of unsafe approval flows.
jovd83Skilljovd83/junit5-skill/analysis/SKILL.md
Use when the agent needs to derive JUnit 5 test scenarios from requirements, code, or existing test case definitions such as TDD, BDD, and plain-text specifications.
jovd83Skilljovd83/junit5-skill/architecture/SKILL.md
Use when the agent needs to shape or refactor JUnit 5 suite architecture, test package structure, naming, fixture ownership, reuse patterns, or boundaries between component, integration, and service tests.
jovd83Skilljovd83/junit5-skill/ci/SKILL.md
Use when the agent needs to run JUnit 5 tests through Maven, Gradle, or the Console Launcher, configure CI pipelines, manage tags and reports, or debug environment-specific execution issues.
jovd83Skilljovd83/junit5-skill/core/SKILL.md
Use when the agent needs to create, run, debug, evaluate, refactor, or correct JUnit 5 tests across component, integration, slice, repository, service, smoke, or regression scenarios.
jovd83Skilljovd83/junit5-skill/extensions/SKILL.md
Use when the agent needs to create, review, or debug JUnit 5 extensions, custom annotations, lifecycle callbacks, parameter resolvers, or reusable execution hooks.
jovd83Skilljovd83/junit5-skill/migration/SKILL.md
Use when the agent needs to migrate tests from JUnit 3 or JUnit 4 to JUnit 5, replace runners and rules, reduce Vintage usage, and preserve behavioral compatibility during modernization.
Plain text files in a repository that tell a coding agent how the project works: commands to run, conventions to follow and things to avoid. CLAUDE.md, AGENTS.md, cursor rules and skills are the common kinds.
CLAUDE.md is read by Claude Code. AGENTS.md is an open format that Codex, Cursor and other agents read. Many projects keep one and point the other at it.
A folder with a SKILL.md that describes one capability, such as filling PDFs or reviewing code. The agent loads it only when the task calls for it.
Your agents already can, over MCP, limited to the files you're allowed to read. Searching them from this page is coming.
