roast-my-agents-md
Roast My AGENTS.md (Evidence Edition)
Most AGENTS.md roasts are vibes. This one brings receipts.
Phase 1 does a quick static roast — the jokes, the sins, the token tax. Phase 2 is where it gets real: we actually run your rules through A/B tests and prove which ones the model already knows without being told. Phase 3 delivers the verdict with hard numbers.
Tone: Senior dev advocate + tech Twitter snark + Gordon Ramsay energy. Not mean-spirited, not discouraging. Punch up at patterns, not people.
Phase 1: The Static Roast (fast, no evals)
Step 0: Gather Data
Scan all instruction files in the project — root and nested. Run the audit script for data-backed roasts:
node {this-skill-path}/scripts/roast-audit.js {project-root}
Key data: detectedSins, summary.totalInstructions vs ~100 budget, summary.estimatedMonthlyCost, files[].initDump, files[].anchoringTraps, files[].redundancy, files[].llmFingerprints.
More from vltansky/skills
simplify
Review changed code for reuse, quality, and efficiency, then fix any issues found. Use when the user says \"simplify\", \"simplify this\", \"review changes\", \"clean up my code\", \"check for duplicates\", \"code reuse review\", or wants a post-change quality sweep.
21what-i-did
Summarize your GitHub activity from the last 24 hours across all repos. Use when user says "what did I do", "my activity", "standup", "recap", "summarize my day", "what-i-did", "git activity", "daily summary".
5agents-md-evals
Evaluate and optimize AGENTS.md/CLAUDE.md instruction files through A/B testing. Use when the user says "eval my agents.md", "test my claude.md", "optimize my instructions", "which rules matter", "trim my agents file", or wants to know which instructions in their global config actually change model behavior vs. are dead weight.
4debug-mode
This skill should be used when debugging frontend/UI bugs that need runtime evidence. USE THIS SKILL (instead of adding console.log) when you''re about to say "add console.log and ask user to check", "open DevTools and tell me what you see", "reproduce the bug and share the output", "check the browser console". Triggers: "debug this", "fix this bug", "why isn''t this working", "investigate this issue", "trace the problem", "figure out why X happens", "UI not updating", "state is wrong", "value is null/undefined", "click doesn''t work", "modal not showing". Automates log collection server-side - you read logs directly, no user copy-paste needed.
2rfc-research
Research a technical topic and produce an RFC document backed by real code evidence from GitHub. Use when user says 'write an RFC', 'RFC research', 'create RFC for', 'technical proposal', 'design doc', 'investigate X', 'research X and write a proposal', 'architecture decision record', 'ADR', or needs a structured technical decision document with prior art analysis.
2batch
Parallel work orchestration — decompose large changes into 5-30 worktree agents that each open a PR. Use when the user says 'batch', 'do this in parallel', 'split into PRs', 'bulk change', 'mass refactor', or wants a sweeping mechanical change across many files.
1