roast-my-plan
Skill1 starsChanged 4 months agoGPL-2.0View on GitHub
Roast an EXISTING plan file for executability via `/roast-my-plan {plan-file} {instructions?}` — a pre-execution spec-quality gate, NOT a plan-authoring skill and NOT a code review. Reads the plan like a hostile principal engineer, hunting contradictions, blank spaces, ambiguity, bad architecture, and unnecessary complexity; reads the docs it references and greps the codebase to verify every anchor it names; then drives it to a checkable bar (references resolve, zero blocking questions, acceptance criteria executable, no internal contradictions). Asks the user every question needed to reach certainty — verifying anything the plan/docs/code already answer instead of asking — and lets the user close the rest with "accept residual risk". Runs in one of two modes chosen at entry: Report (writes `{plan}-roasted.md`, never touches the plan) or Fix-live (edits the plan in place as the user approves each finding). Client-generic. ACTIVATE on "/roast-my-plan <file>", "roast this plan", "roast my plan", or "tear this plan apart".
In this repository19 other files it gives its agents.
- better-technical-writingSkill
- create-skillSkill
- dead-horseSkill
- debug-codeSkill
- eat-the-frogSkill
- fetch-website-contentSkill
- git-commit-instructionsSkill
- git-push-prSkill
- git-summarySkill
- hunk-reviewSkill
- javascript-development-guidanceSkill
- javascript-jestSkill
- javascript/react-17-to-18Skill
- javascript-react-development-guidanceSkill
- javascript-ts-zod-guideSkill
- react-router-v7-best-practicesSkill
- roast-my-codeSkill
- sniff-my-planSkill
- ticket-fix-flowSkill
The file
We split this skill into the rules it gives an agent
11 rules. About 0 are common, 9 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈9
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
Licensed with conditions — read it at the source. We count its rules but don't quote them. Read them on GitHub.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
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.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.