Skip to content

Strip execution fields from public skillshelf.yaml sidecars#82

Merged
timctfl merged 1 commit intomainfrom
strip-public-sidecars
Apr 8, 2026
Merged

Strip execution fields from public skillshelf.yaml sidecars#82
timctfl merged 1 commit intomainfrom
strip-public-sidecars

Conversation

@timctfl
Copy link
Copy Markdown
Owner

@timctfl timctfl commented Apr 8, 2026

Summary

  • Strips conversation_starter, faq, consumes, input_schema, and output_schema from all 19 public skillshelf.yaml files
  • Updates the CI validator to stop checking removed fields
  • Updates benchmark/loader.py to stop reading conversation_starter from the sidecar
  • Rewrites CONTRIBUTING.md field tables and example to reflect catalog-only metadata
  • Removes the Conversation Starter and Consumes sections from skillshelf-yaml-reference.md (both write-skill and adapt-skill copies)
  • Replaces conversation_starter guidance in skill-authoring-guide.md
  • Removes the faq checkbox from conventions-checklist.md

Why

The sidecar was accumulating fields that duplicate information already in the SKILL.md body or that are better managed by the website. Stripping it to catalog-only metadata keeps the contributor surface simple: category, level, platforms, tags, author, version.

Test plan

  • python scripts/validate_skillshelf_metadata.py skills/*/ passes (19 skills, exit 0)
  • Site builds successfully with stripped sidecars
  • GitHub Actions CI passes

🤖 Generated with Claude Code

The execution layer (inputs, runtime, output, faq) has moved to private
configs in the site repo as part of the public/private sidecar split.
Public sidecars now contain only catalog metadata: version, category,
level, primitive, platforms, tags, author, dates, and certified.

Fields removed from all 19 skills:
- conversation_starter (moved to SKILL.md conversation flow)
- faq (moved to private execution config)
- consumes (replaced by skill_output inputs in execution config)
- input_schema (replaced by inputs in execution config)
- output_schema (replaced by output in execution config)

Also updates:
- validate_skillshelf_metadata.py: remove consumes/conversation_starter validation
- benchmark/loader.py: remove conversation_starter reading from sidecar
- CONTRIBUTING.md: rewrite field tables to catalog-only fields
- skillshelf-yaml-reference.md: remove Conversation Starter and Consumes sections
- skill-authoring-guide.md: replace conversation_starter guidance
- conventions-checklist.md: remove faq checkbox

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
@timctfl timctfl merged commit 8e7ca5d into main Apr 8, 2026
1 check passed
@timctfl timctfl deleted the strip-public-sidecars branch April 8, 2026 18:42
timctfl added a commit that referenced this pull request Apr 8, 2026
The sidecar was accumulating fields that duplicate information already
in the SKILL.md body or that are better managed by the website. This
strips it to catalog-only metadata: version, category, level, primitive,
platforms, tags, author, dates, and certified.

Fields removed from all 19 skills:
- conversation_starter (defined in the SKILL.md conversation flow)
- faq (managed by the website)
- consumes (managed by the website)
- input_schema (removed, loosely typed and unused)
- output_schema (removed, loosely typed and unused)

Also updates:
- validate_skillshelf_metadata.py: remove consumes/conversation_starter validation
- benchmark/loader.py: remove conversation_starter reading from sidecar
- CONTRIBUTING.md: rewrite field tables to catalog-only fields
- skillshelf-yaml-reference.md: remove Conversation Starter and Consumes sections
- skill-authoring-guide.md: replace conversation_starter guidance
- conventions-checklist.md: remove faq checkbox

Co-authored-by: Tim Petrella <tpetrella@gmail.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants