ak1ra-komj/reviewing-agents-md
skills/reviewing-agents-md/SKILL.md
Use when writing, reviewing, or refactoring AGENTS.md, writing an agent guide, documenting the project for AI agents, or orienting AI coding tools to a new repository.
$ install --global
skillsauthnpx skillsauth add ak1ra-komj/agents-skills reviewing-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 2, 2026, 7:41 PM60.5s1 file scanned
SKILL.md
- name:
- reviewing-agents-md
- description:
- Use when writing, reviewing, or refactoring AGENTS.md, writing an agent guide, documenting the project for AI agents, or orienting AI coding tools to a new repository.
reviewing-agents-md
Analyze the repository and write (or overwrite) an AGENTS.md file in the project
root. The file is a concise, prescriptive orientation guide for AI coding agents.
It must not duplicate README.md — link there for anything already covered.
Workflow
- Read
README.md,pyproject.toml/package.json/ equivalent manifest, and any existing config files to infer the tech stack and tooling. - Identify the environment manager, test runner, linter, and build tool in use.
- Write
AGENTS.mdfollowing the structure below. - Aim for under 80 lines total.
Required sections
1. What This Project Does (2–4 sentences)
State the project's purpose and technology stack category. Add a pointer to
README.md for full details.
2. Environment & Tooling — CRITICAL
Identify the exact tool that manages the environment and write explicit DO / DO NOT rules covering:
- The exact command to run the test suite
- How to install/sync dependencies
- How to lint and format
- Which alternatives are explicitly forbidden
Mark this section — CRITICAL so agents cannot miss it.
3. Conventions (non-obvious only)
Cover naming patterns and the canonical source-of-truth files agents must respect when adding new parameters or configuration keys.
4. Testing Guidelines
- Where tests live and how they map to source modules
- Whether external I/O must be mocked
- Rules about keeping tests in sync when function signatures change
5. Common Operations
One shell code block with one-liner comments for the 4–6 most frequent tasks (test, lint, build, deploy, docs preview, etc.).
Style rules
- Write in English.
- Be prescriptive ("ALWAYS", "NEVER", "Do NOT"), not descriptive.
- Omit content already in
README.md— link there instead. - Prefer bullet lists and short paragraphs over prose.
Related Skills
ak1ra-komj/commit-and-summarize
development
VerifiedTrustedCommunity
Use when the user asks to commit changes and/or summarize the current session - or when wrapping up a conversation that involved code or file edits.
1SKILL.mdUpdated Apr 29, 2026
ak1ra-komj/summarize-current-chat
development
VerifiedTrustedCommunity
Use when the user asks to summarize this session or chat — and the conversation is happening in a web chat interface (e.g. ChatGPT Pro) where no file system or terminal access is available.
1SKILL.mdUpdated Apr 2, 2026
ak1ra-komj/summarize-and-commit
development
VerifiedTrustedCommunity
Use when the user asks to commit changes and/or summarize the current session — or when wrapping up a conversation that involved code or file edits.
1SKILL.mdUpdated Apr 2, 2026
ak1ra-komj/keep-a-changelog
development
VerifiedTrustedCommunity
Use when the user mentions preparing or publishing a new release, or asks to review or refactor CHANGELOG.md, following Keep a Changelog format and Semantic Versioning.
1SKILL.mdUpdated Apr 2, 2026