dead-horse
Skill1 starsChanged 4 months agoGPL-2.0View on GitHub
Probe the quality of your own confidence about a plan via `/dead-horse {plan-file?} {count:15} {instructions?}`. The inverse of a normal clarifying-question round: instead of asking what it is unsure about, the agent enumerates the things it is 100% CERTAIN of — the assumptions it filled in without noticing — states its answer to each, and makes the user confirm or correct them. Every correction is a confidence failure, and the report scores the miss rate and clusters the misses by category to show WHERE the agent's certainty is worthless. Resolves the plan file from the argument, else from context; exits with a notice if none is found. Every correction is researched, turned into a specific proposed plan change, and applied to the plan file once the user approves it. Each round ends with a spoken summary, then the agent offers another round — repeating as long as the user wants, since each plan update creates fresh assumptions to probe. Emits a cumulative `{plan-file}.dead-horse.md`. ACTIVATE when the user says "/dead-horse", "beat this to death", "what are you assuming", "check your assumptions", "probe your confidence", "what do you think you know", or asks for questions about things the agent is already sure of.
In this repository19 other files it gives its agents.
- better-technical-writingSkill
- create-skillSkill
- 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
- roast-my-planSkill
- sniff-my-planSkill
- ticket-fix-flowSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
22 rules. About 0 are common, 18 are distinctive, and 4 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈18
Distinctive · estimate
This author's own choices. Worth a look.
4
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.