improve-refinement
Skill1 starsChanged 33 days agoNo licenceView on GitHub
Walk the open entries in the current repo's IMPROVEMENTS.md that cannot be built as written — the ones whose own prose asks for a decision, the ones that read as already done but were never struck through, and the ones whose Build block still carries an unanswered Open: question — one at a time, ask the user the question each one is holding, and rewrite the entry in place so it states what to build instead of asking. Also runs a faster pre-build round over a named set of entries (or "the next wave"), batching just their open questions before a build starts. Use whenever the user wants to refine, sharpen, unblock, resolve or clear the open questions on this app's backlog: "which improvements need me", "let's go through the ones that need a decision", "refine the improvements list", "what's blocking these", "make these ready to build", "get the questions out of the way before we build these", "clear the questions on the next wave". Do not use it to add a new idea (that's improve-idea), to just see the backlog (that's improve-list), or to build any of it — this only ever writes IMPROVEMENTS.md.
In this repository4 other files it gives its agents.
- design-md-builderSkill
- improve-ideaSkill
- improve-listSkill
- like-im-5Skill
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 4 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
No licence file, so all rights are reserved — 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.