agentleFS
RussBrown00RussBrown00/agent-skills/eat-the-frog/SKILL.md

eat-the-frog

Skill1 starsChanged 4 months agoGPL-2.0View on GitHub

Work a list of review findings one issue at a time via `/eat-the-frog {optional-instructions}`. Runs AFTER a code/plan/PR review has produced a list of issues or concerns. Creates an untracked, restart-safe tracker file in the project's hidden temp dir, snapshots the git baseline, dedupes and ranks the issues hardest-first (severity × blast radius), then walks them ONE AT A TIME: re-verify current state → restate the full issue and context → propose a fix and WAIT for approval → implement → verify → both parties must agree it is 100% resolved before moving on. Handles code, plan-file, and doc findings. Newly discovered issues are logged and re-ranked into the queue. Never batches issues, never advances unilaterally, never commits unless asked at the agreement gate. ACTIVATE when the user says "/eat-the-frog", "eat the frog", "step through these", "work through these one at a time", "hardest first", "let's go through the review findings", or "resume eat-the-frog". ALSO OFFER THIS SKILL PROACTIVELY, unprompted, whenever a review, audit, QA pass, security scan, type-check, test run, or CI failure has just produced TWO OR MORE unresolved findings and the user has not said what to do next: say in ONE line that the findings can be worked one at a time, hardest first, with approval before each edit — then STOP and WAIT. The offer is a single sentence, made once; never repeat it, never start the workflow unprompted, and never make it when the findings are already resolved, number fewer than two, or the user has already chosen a next step.

The file

Show its rules and text

We split this skill into the rules it gives an agent

40 rules. About 0 are common, 31 are distinctive, and 9 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈31

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 9

    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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.