improve(generate-agent-skills): improve description and add reference index table#46
Closed
srbouffard wants to merge 1 commit into
Closed
improve(generate-agent-skills): improve description and add reference index table#46srbouffard wants to merge 1 commit into
srbouffard wants to merge 1 commit into
Conversation
… index table - Rewrote frontmatter description to be more concrete and keyword-rich, adding explicit 'Use when...' triggers for better skill invocation - Replaced prose Knowledge Retrieval section with a concise Reference Index table for faster navigation Cherry-picked improvements from #45 by @yogesh-tessl. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Cherry-picks the two highest-value improvements from #45 by @yogesh-tessl.
Changes
descriptionfrontmatter — rewritten to be concrete and keyword-rich, with an explicit "Use when..." clause covering natural trigger terms (new agent skill,skill.md,skill definitions,skill templates). This improves skill invocation reliability.What was not cherry-picked
The broader rewrite from #45 (61% line reduction) was not included. While token efficiency is valuable, the removed content includes important LLM behavioral anchors: STOP CONDITIONS, explicit violation warnings, post-validation checklists, and the script-vs-checklist decision tree. We want to revisit those tradeoffs deliberately rather than wholesale.