feat(skills): add skill-creator assets and eval-viewer#758
Merged
JeremyDev87 merged 2 commits intomasterfrom Mar 21, 2026
Merged
feat(skills): add skill-creator assets and eval-viewer#758JeremyDev87 merged 2 commits intomasterfrom
JeremyDev87 merged 2 commits intomasterfrom
Conversation
- assets/eval_review.html: self-contained dark-mode trigger accuracy evaluation viewer with query cards, edit/add/delete UI, and eval_set.json download - assets/skill-template.md: SKILL.md template with codingbuddy pattern (Core principle, Iron Law, Phases, Red Flags) - eval-viewer/generate_review.py: benchmark result HTML viewer generator with side-by-side with_skill/baseline comparison, assertion pass/fail coloring, feedback collection, and delta comparison support
- skill-template.md: match exact issue template (TODO placeholders, "Use this ESPECIALLY when:", "The Process" header, Additional resources) - generate_review.py: add --benchmark flag for benchmark.json stats, summary section (pass_rate, tokens, time with mean±stddev), collapsible evidence display, per-scenario token/time metadata, pass_rate delta in previous iteration comparison
JeremyDev87
added
feat
sub-issue
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
assets/eval_review.html: self-contained dark-mode trigger accuracy evaluation viewer with query cards (color-coded byshould_trigger), edit/add/delete UI, andeval_set.jsondownload button. Placeholders:__EVAL_DATA_PLACEHOLDER__,__SKILL_NAME_PLACEHOLDER__,__SKILL_DESCRIPTION_PLACEHOLDER__assets/skill-template.md: default SKILL.md template matching codingbuddy pattern (Core principle, Iron Law, When to Use, When NOT to Use, The Process phases, Additional resources). Placeholders:{{SKILL_NAME}},{{SKILL_DISPLAY_NAME}}eval-viewer/generate_review.py: benchmark result HTML viewer generator with side-by-sidewith_skill/baselinecomparison,--benchmarkflag for stats summary (pass_rate, tokens, time mean±stddev), collapsible evidence display,--previous-workspacedelta comparison,--staticoutput option. Python 3.8+ standard library onlyTest plan
eval_review.htmlopens in browser with placeholder dataskill-template.mdplaceholders matchinit_skill.shexpectationspython generate_review.py --helpshows all argumentspython generate_review.pywith sample data generates valid HTML--benchmarkflag loads and displays summary stats--previous-workspaceshows delta comparison--staticwrites to fileCloses #743