writer
Skill0 starsChanged 28 days agoMITView on GitHub
Make the requested code change, then stop. Do not call the work done. Hand the diff to the checker skill and repeat only on the lines it failed, at most three rounds. Use when the user asked for a code change that already names the target, the change, and what done means. Do not use when the request is still vague.
12 other projects use a version of this.
Adopted by
Most recently taken up by
- lumpcode/lumpcodetheir own version, first seen Nov 8, 2026
- wellwelwel/lagunetheir own version, first seen Oct 31, 2026
- danielgefen/soustheir own version, first seen Aug 25, 2026
- flaqai/backlink_skillstheir own version, first seen Aug 19, 2026
- xjsongphy/skillstheir own version, first seen Aug 17, 2026
- Mikefluff/skillstheir own version, first seen Aug 8, 2026
Other versions12 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 12
- flaqai/backlink_skills★ 872same name
- wellwelwel/lagune★ 177same name
- microsoft/aspnetcore-ja-handbook★ 33same name
- Mikefluff/skills★ 26same name
- lumpcode/lumpcode★ 12same name
- botlearn-ai/botlearn-skills★ 9same name
- xjsongphy/skills★ 7same name
- zdyya/writer-skill★ 4same name
- Notryag/north-agent★ 1same name
- vinitjhawar/opencouncil★ 1same name
2 more not listed
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
4 rules. 0 are common, 3 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 10 edited versions we read keep these.
3
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 18
Stop. Do not tell the user the task is done.
- Very specific: line 20
If this host can start another agent, start one with the checker skill and no write tool.
- Distinctive: line 22
Read the checker output.
- Distinctive: line 25
Stop early, even without a PASS, when this is round 3, or when the FAIL text is the same as the previous round.
“Common” is measured: kept by at least 6 in 10 of the 10 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Writer
You write. You do not approve your own edit.
Before the first edit
If the request does not name the target, the change, and how to tell it is done, do not start this loop. If the prompt-clarifier skill is installed, follow that and wait. If it is not, ask one question for the missing piece and stop. Do not fill the gap with a guess.
One round
- Edit only what the request asked for.
- Stop. Do not tell the user the task is done.
- Get a checker pass on the diff.
- If this host can start another agent, start one with the
checkerskill and no write tool. - Either way, a PASS that did not come from
checker'sscripts/check.pydoes not count. If that script is not installed, stop and say the checker is missing.
- If this host can start another agent, start one with the
- Read the checker output.
PASS: stop the loop. Show the checker line. You may say the named checks passed. You may not say the change is correct, and you may not say tests passed unless a test command's output is already in the session.FAIL: edit only the files and lines the checker named. Do not rewrite the rest. Start the next round.
- Stop early, even without a PASS, when this is round 3, or when the FAIL text is the same as the previous round. Show the last checker output and what is still failing.
The cap is the point. Three rounds, then a person decides. Do not keep going because you think the next try will work.
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.