fix: address structural and quality gaps from project review#23
Merged
Conversation
- competitive-analysis: add WebFetch to allowed-tools and Step 1.5 to fetch competitor homepages and pricing pages before building profiles, so analysis is grounded in live public data rather than user recall - validate-skill.sh: replace loose '## How' grep with three targeted checks (trigger section, output section, process section) — now correctly flags prioritize, sprint-review, and write-product-strategy for missing structural sections - ci: add validate.yml workflow that runs validate-skill.sh on every push and PR; add validation as a release gate in release.yml before packaging - release.yml: include agents/ in the zip artifact alongside skills/; rename artifact from gambit-skills-$version to gambit-$version to reflect full content - skill-framework.md: remove stale 'Future Directions' section that listed agents as future work when they already exist - contributing.md: remove reference to non-existent CONTRIBUTORS file Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
…-review Both skills were flagged by validate-skill.sh for missing structural sections. Fixes: - prioritize: rename '## Step 3: Output' → '## Output Format' so the validator can locate it; add '## How to Trigger' with natural language phrase examples including the Agentic RICE use case - sprint-review: add '## Output Format' (summary of the 7-section report structure) and '## How to Trigger' with phrase examples; all content is additive — no existing text changed All 13 skills now pass validate-skill.sh with no warnings. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Replace Claude-specific language in all How to Trigger sections: - "Ask Claude to" → "Ask your assistant to" - "Claude will automatically invoke this skill" → "This skill will automatically" Affects all 12 skills that have a trigger section. No logic or behavior changed — phrasing only. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Rename references/gemini-tools.md → references/antigravity-tools.md; update content to say "Antigravity CLI" throughout - Update GEMINI.md @-include to point to renamed tool mapping file - Update README.md: section header and install/update commands (gemini → agy) gemini-extension.json and GEMINI.md filenames are unchanged — agy still uses both formats. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
agent SKILL.md files were nested in subdirectories (agents/<name>/SKILL.md), which is not the format expected by Claude Code or Gemini/agy. Both platforms expect agent definitions as flat .md files directly in agents/. Changes: - agents/<name>/SKILL.md → agents/<name>.md for all four agents - validate.yml: remove agents/*/SKILL.md from CI glob (agents are no longer SKILL.md format and don't need skill validation) - docs/getting-started.md: update manual install snippet to wrap each flat agent .md into the ~/.claude/skills/<name>/SKILL.md structure that Claude Code expects for manual installs - README.md: update directory tree Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.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
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
Why
Identified during a structural and value review of the project. The main issues were: competitive-analysis couldn't actually research competitors without web access; the validator produced no real signal; agents were silently excluded from the release artifact; and two docs contained stale or incorrect content.
Reviewer notes
🤖 Generated with Claude Code