Resolve doc source
Use when adding a documentation source to the dq doc pipeline or asking the best way to ingest a library or site's docs - e.g. 'add docs for X', 'what's the right recipe for <docs-url>', 'resolve doc source'. Resolves the optimal ingest strategy by measurement and adds the recipe to config/doc_sets.toml.From its SKILL.md
npx -y skills add Magic-Man-us/dq-toolkit --skill resolve-doc-sourceAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 2 stars2 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
SKILL.md
2.0 KB, as published. Nobody here has run it
Resolve Doc Source
Add this documentation source to the dq doc pipeline: $ARGUMENTS
Resolve the optimal ingest recipe for it - decide by measurement (sample-ingest
each candidate, compare coverage and stub-ratio), apply the validated
[[sets.ingest]] block to config/doc_sets.toml, and return the JSON report.
The resolution methodology and the exact JSON output shape are in your agent
system prompt. If no source was given above, return {"error": "no source provided"}.
Once it finishes, the caller runs make refresh to ingest and index the new set.
References
- references/recipes.md - the
[[sets.ingest]]shape, the four ingest kinds, url_style, and the base_url rule - references/resolution.md - finding candidates, the sample-ingest + audit rubric, the lessons
- references/quality-gates.md - normalize, validate, quality, refresh, and the apply sequence
- examples/recipes.md - a concrete recipe block per kind (url / git / pkg / local)
- examples/commands.md - candidate discovery, sample-ingest, gate, refresh sequences