erikstmartin/agents-md
skills/global/.agents/skills/agents-md/SKILL.md
Use when asked to write or review AGENTS.md/CLAUDE.md/LLMs.md context files.
$ install --global
skillsauthnpx skillsauth add erikstmartin/dotfiles agents-mdInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 17, 2026, 12:19 PM70.7s1 file scanned
SKILL.md
- name:
- agents-md
- description:
- Use when asked to write or review AGENTS.md/CLAUDE.md/LLMs.md context files.
AGENTS.md Guidance (Minimal)
Overview
Keep AGENTS.md short and only include non-discoverable constraints. Extra requirements reduce agent performance.
When to Use
- Create, review, or trim AGENTS.md / CLAUDE.md / LLMs.md
- Decide whether a requirement belongs in a context file
What to Include (Only)
- Non-obvious test/lint/build commands
- Required tooling or environment constraints the agent cannot infer
- Hard safety rules (e.g., no commit/push, ask before destructive commands)
What to Exclude
- Repo structure overviews
- Style guides or “nice to know” conventions
- Generic best practices or “always run X” rules
- Anything already in README/docs
- Auto-generated context files (/init outputs)
Value Test
Include a line only if:
- It changes agent behavior on this repo, and
- It cannot be discovered by reading the code/docs.
If unsure, ask.
Minimal Template
# AGENTS.md
## Minimal Requirements
- [Non-obvious test/lint/build command]
- [Non-obvious tooling/env constraint]
## Git & Destructive
- Never commit/push without explicit request.
- Ask before destructive/privileged commands.
Related Skills
erikstmartin/writing-skills
testing
VerifiedTrustedCommunity
Use when creating new skills, editing existing skills, or verifying skills work before deployment
15SKILL.mdUpdated Apr 17, 2026
erikstmartin/writing-plans
development
VerifiedTrustedCommunity
Use when you have a spec or requirements for a multi-step task, before touching code
15SKILL.mdUpdated Apr 17, 2026
erikstmartin/verification-before-completion
data-ai
VerifiedTrustedCommunity
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always
15SKILL.mdUpdated Apr 17, 2026
erikstmartin/using-superpowers
tools
VerifiedTrustedCommunity
Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions
15SKILL.mdUpdated Apr 17, 2026