Refactor skill package into a compact router with modular DWS references#4
Merged
Refactor skill package into a compact router with modular DWS references#4
Conversation
Align the skill package with Codex-style packaging and turn the top-level skill into a compact router. Split the old monolithic reference into focused DWS cookbooks and add explicit coverage for generation, PDF/A, PDF/UA, optimization, and linearization so the skill stays broad without bloating invocation cost.
Document the merge, split, rotate, flatten, and page-range workflows that the top-level skill already advertises. Add setup assumptions and anti-pattern guidance to the router, and keep the README plus Codex metadata aligned with the broader document-processing surface.
Contributor
Author
|
Follow-up pass pushed in Addressed a real coverage gap in the package by documenting the PDF assembly and page-ops workflows that the top-level skill already advertised: merge, split, page ranges, rotation, and flattening. I also tightened the router with setup assumptions and anti-pattern guidance, then aligned the README and |
Resolve the PR conflict by adopting the Python plugin structure merged in #3 while preserving the broader document-processing guidance, modular references, Codex metadata, and expanded capability coverage from this branch. Add a lightweight validation workflow so packaging drift and unresolved markers are caught automatically in future PRs.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What
This PR reshapes the Nutrient agent skill into a more Codex-friendly package and expands the documented DWS surface area without bloating the top-level skill.
Main changes
agents/openai.yamlLICENSEtoLICENSE.txtnutrient-document-processing/SKILL.mdinto a compact router skillWhy
The previous skill worked, but it had two problems:
SKILL.mdwas acting as a long tutorial instead of a compact operator guide.This PR keeps the one-umbrella-skill model, but uses progressive disclosure:
That should improve both agent usability and token efficiency.
Validation
agents/openai.yamlparses successfullySKILL.mdis compact and the detailed material lives inreferences/Notes
This PR is documentation and package-structure only. It does not change the underlying DWS API or MCP server behavior.