check-version
Skill4 starsChanged 16 days agoApache-2.0View on GitHub
Use when the user asks whether the duolog version is consistent, what
In this repository10 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- bump-versionSkill
- check-changesSkill
- check-versionSkill
- crit-cliSkill
- critSkill
- crit-storySkill
- bump-versionSkill
- check-changesSkill
The file
We split this skill into the rules it gives an agent
6 rules. About 0 are common, 3 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 21
Write files, comments and reports in English, ASCII only.
- Distinctive: line 22
Use simple English: short sentences, common words, simple grammar.
- Very specific: line 30
Run uv --version. If it fails, stop and ask the user to install uv: https://docs.astral.sh/uv/getting-started/installation/
- Very specific: line 39
Run the check. Add --tag $tag only when the user gave a tag.
- Very specific: line 45
Read the JSON. version is what the repository states, consistent is the result, and problems names each place that is wrong.
- Distinctive: line 54
If a place is wrong, say that the bump-version skill sets every place.
≈ “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
Check the version
Arguments
$tag- a release tag such asv1.2.3. It is optional. Without it, the places are compared with each other.
Communication
- Reply in the language the user writes in.
- Write files, comments and reports in English, ASCII only.
- Use simple English: short sentences, common words, simple grammar.
Models
- The current model does all of it. The script decides, so a small model is enough.
Before you start
- Run
uv --version. If it fails, stop and ask the user to install uv: https://docs.astral.sh/uv/getting-started/installation/ - A sandbox can stop uv from writing its cache. If a later
uv runreports that, set the variableUV_CACHE_DIRto.cache/uv, which git ignores, and run it again. In a read-only sandbox, say that it needs write access and stop. Do not call Python directly, and do not read the files by hand instead.
Steps
Run the check. Add
--tag $tagonly when the user gave a tag.uv run scripts/version/version.py check --format json- Read the JSON.
versionis what the repository states,consistentis the result, andproblemsnames each place that is wrong. Report the version and the result in one line. List every problem as it is.
Example of a pass:
Version 1.0.0: every place agrees.Example of a failure:
Version 1.0.0: plugin/codex/plugin.json states 0.9.0.- If a place is wrong, say that the bump-version skill sets every place. Do not edit a file: this skill only reports.
Done when
- The script ran, and you reported its exit code truthfully: 0 means consistent, 1
means a place differs, 2 means a wrong call such as a tag with no
v.
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.

