skills/agents-md-pro/SKILL.md
Create, optimize, update, and validate AGENTS.md files with maximum token efficiency. Use when the user asks to (1) create new AGENTS.md files for any repository, (2) optimize/condense existing AGENTS.md to reduce token count, (3) update/refresh AGENTS.md to sync with codebase changes, (4) validate AGENTS.md quality and completeness, or (5) improve AGENTS.md files to be more effective for AI agents. Always generates token-efficient, condensed output focused on actionable commands and patterns while maintaining model-agnostic language.
npx skillsauth add alexander-danilenko/ai-skills agents-md-proInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Create token-efficient AGENTS.md files that maximize clarity with minimal tokens.
.eslintrc, never duplicateRequired: Project directory path If missing: Request from user
Map user request to workflow:
Output template - Standard repo:
# [Project] | [Tech Stack]
## COMMANDS
- Dev: `cmd` | Build: `cmd` | Test: `cmd` | Lint: `cmd --fix`
## STRUCTURE
- `dir/` - purpose
## PATTERNS
[1-2 key patterns with minimal code]
## CODE STYLE
See `.eslintrc`, `.prettierrc`
## DOMAIN
| Term | Definition |
## SECURITY
[Auth/validation only]
## GIT
Format: `convention`
Line limits:
Target tokens:
Load as needed:
development
Apply these opinionated documentation conventions when adding docstrings, OpenAPI specs, or doc sites: Microsoft style (contract over implementation), language-specific docstrings (JSDoc, Google, NumPy), OpenAPI/Swagger, doc portals, tutorials, user guides.
tools
Apply these opinionated TypeScript conventions when writing TS in this codebase: branded types, advanced generics, conditional and utility types, type guards, discriminated unions, strict tsconfig, tRPC, monorepo setup.
tools
Apply these opinionated testing conventions when writing tests or test strategies: three modes (functional, performance, security), unit/integration/E2E patterns, coverage analysis, automation frameworks, defect tracking, accessibility and usability.
development
Apply this opinionated workflow when reverse-engineering legacy or undocumented systems: scope, explore with Glob/Grep/Read, trace data flows, document in EARS format, flag uncertainties. For code archaeology, onboarding, and requirements extraction.