fix: align skill template with official Anthropic guidance#14
Open
EthanJStark wants to merge 12 commits intoblader:mainfrom
Open
fix: align skill template with official Anthropic guidance#14EthanJStark wants to merge 12 commits intoblader:mainfrom
EthanJStark wants to merge 12 commits intoblader:mainfrom
Conversation
…olation - Remove author, version fields (not supported per Anthropic docs) - Rewrite description to contain only trigger conditions - Remove workflow summary from description (CSO violation) - Update TodoWrite to TaskCreate/TaskUpdate/TaskList Co-Authored-By: Claude <noreply@anthropic.com>
- Remove author/version/date from template (not supported) - Add CSO warning about description field - Rewrite description guidance to emphasize triggers only - Add When NOT to Use section to template - Add Common Mistakes section to template Co-Authored-By: Claude <noreply@anthropic.com>
- List explicit anti-patterns for skill extraction - Add red flags for over-extraction - Emphasize skills capture what docs don't cover Co-Authored-By: Claude <noreply@anthropic.com>
- Visual guide for should-I-extract decision - Covers investigation, docs check, reusability gates Co-Authored-By: Claude <noreply@anthropic.com>
- Explain description = triggers only rule - Add bad/good description comparison table - Include keyword coverage guidance - Add token efficiency recommendations Co-Authored-By: Claude <noreply@anthropic.com>
- Add specific mistake patterns with fixes - Add rationalization table for self-checking - Address frontmatter and CSO violations explicitly Co-Authored-By: Claude <noreply@anthropic.com>
- Remove unsupported frontmatter fields from example - Fix description to start with 'Use when:' - Add When NOT to Use section to example - Add Common Mistakes section to example Co-Authored-By: Claude <noreply@anthropic.com>
- Document testing approach and scenarios - Reference verify-technical-claims case study - Add ongoing validation guidance Co-Authored-By: Claude <noreply@anthropic.com>
Add CLAUDE.md with comprehensive guidance for working with this skill repository, including architecture overview, file format specifications, and quality criteria. Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Adds evaluation flow to determine whether extracted knowledge belongs in CLAUDE.md (cheap, always-loaded) or a skill (expensive, semantic-matched). Decision tree guides: figure-it-out → instruction → typical-stack checks. Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Step 7 now guides through placement decision tree before saving. Includes CLAUDE.md option and typical/unusual stack distinction. Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.5 <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.
Problem
Claudeception was teaching incorrect skill patterns that violated official Anthropic guidance:
Root cause: The skill template and examples propagated these violations to newly created skills.
Solution
Refactor claudeception to follow official Anthropic skill system specifications and writing-skills best practices.
Based on case study: verify-technical-claims skill review revealed these patterns, providing concrete evidence of what needed fixing.
Key Changes
Frontmatter compliance:
Enhanced guidance:
Template improvements:
Verification:
Impact
Skills created by claudeception will now follow official guidance, improving discoverability and usability.
Note: The skill uses "CSO (Claude Search Optimization)" as internal shorthand for "description optimization for skill discoverability" - this terminology is not from official docs but describes the principle accurately.
🤖 Generated with Claude Code