fix-sphinx-docs
Skill830 starsChanged 10 days agoMITView on GitHub
Fix Sphinx source errors and warnings using supplied build output or CI logs, without building the documentation locally.
In this repository23 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- add-curatorSkill
- add-stablecoinSkill
- add-vault-abi-methodsSkill
- add-vault-noteSkill
- add-vault-protocolSkill
- categorise-vault-strategySkill
- check-stablecoinsSkill
- check-top-list-vaultsSkill
- check-vault-onchainSkill
- clean-up-for-prSkill
- document-curator-incidentSkill
- extract-project-logoSkill
- extract-test-setSkill
- extract-vault-protocol-logoSkill
- find-new-curatorsSkill
- get-block-numberSkill
- Identify vault protocolSkill
- maintain-curatorsSkill
- make-releaseSkill
- monthly-vault-reportSkill
- more-vaultsSkill
- post-process-logoSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 2 are distinctive, and 1 is 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.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 8
Use existing error output and source inspection to fix documentation issues.
- Distinctive: line 13
Read the supplied build output or the relevant CI job log.
- Very specific: line 19
Check the edited sources and their references.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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
Fix Sphinx source errors and warnings
Use existing error output and source inspection to fix documentation issues.
AGENTS.md excludes local Sphinx builds from development verification.
Steps
- Read the supplied build output or the relevant CI job log. Locate the affected source page, referenced API module and index entries. If no log is available, inspect the reported source problem directly.
- Correct the maintained RST, docstrings, links or index references. Do not
edit generated
_autosummary*files; trace their errors to the maintained source or autosummary declaration. - Check the edited sources and their references. Run focused Python checks
when API code changed. Do not run Sphinx,
make htmlor documentation build wrappers locally. - Finish with clean-up-for-pr at the outermost task's review handoff. Report the fixes and any build result that still needs CI confirmation. Open or update a PR only when the user requested it.
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.

