dumb
Skill31 starsChanged 32 days agoMITView on GitHub
Corrects an immediately previous response or action that the user says was wrong, incomplete, lazy, or missed the point. Use for /dumb and corrections such as "that was dumb", "fix it", "that's not done", or "you skipped" directed at the previous work. Delivers the correction and records reusable lessons.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- leothesen/skillstheir own version, first seen Oct 1, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- leothesen/skills★ 2same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 10
If the intended correction remains unclear after reviewing the context, ask one focused question and continue any independent work.
- Distinctive: line 13
Keep the reply short. If prevention requires changing a workflow, use prevent.
≈ “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.
Files
Correct the previous work
- Re-read the user's actual request and identify the concrete failure in one line. Investigate disputed facts; do not defend the previous answer or invent a failure to agree.
- Complete the correction within the authorized scope. Read sources or artifacts first when needed. Give the corrected result, not a plan to fix it.
- If the intended correction remains unclear after reviewing the context, ask one focused question and continue any independent work.
- Record reusable findings in the owning project's existing lesson or lapse record. Separate an incident from a standing preference: do not turn a one-off correction into a new permanent rule without evidence of that intent.
Keep the reply short. If prevention requires changing a workflow, use prevent; if the issue is disputed claims, use prove.
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.