Agent skill
openapi-toolkit-googleai-dart
Stars
163
Forks
31
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/testing/openapi-toolkit-googleai-dart
SKILL.md
OpenAPI Toolkit (googleai_dart)
Uses shared scripts from openapi-toolkit with googleai_dart-specific configuration.
Prerequisites
GEMINI_API_KEYorGOOGLE_AI_API_KEYenvironment variable set- Working directory: Repository root
- Python 3
Spec Registry
| Spec | Description | Auth Required |
|---|---|---|
main |
Core Gemini API (generation, embeddings, files, models, etc.) | Yes |
interactions |
Experimental Interactions API (server-side state, agents) | No |
Workflow
1. Fetch Latest Specs
bash
# Fetch all specs + auto-discover new ones
python3 .claude/shared/openapi-toolkit/scripts/fetch_spec.py \
--config-dir .claude/skills/openapi-toolkit-googleai-dart/config
# Fetch specific spec only
python3 .claude/shared/openapi-toolkit/scripts/fetch_spec.py \
--config-dir .claude/skills/openapi-toolkit-googleai-dart/config --spec main
Output: /tmp/openapi-toolkit-googleai-dart/latest-main.json, /tmp/openapi-toolkit-googleai-dart/latest-interactions.json
2. Analyze Changes
bash
python3 .claude/shared/openapi-toolkit/scripts/analyze_changes.py \
--config-dir .claude/skills/openapi-toolkit-googleai-dart/config \
packages/googleai_dart/specs/openapi.json /tmp/openapi-toolkit-googleai-dart/latest-main.json \
--format all \
--changelog-out /tmp/openapi-toolkit-googleai-dart/changelog-main.md \
--plan-out /tmp/openapi-toolkit-googleai-dart/plan-main.md
Generates:
changelog-main.md- Human-readable change summaryplan-main.md- Prioritized implementation plan (P0-P4)
3. Implement Changes
Before implementing, read references/implementation-patterns.md for:
- Model class structure and conventions
- Enum naming patterns
- JSON serialization patterns
- Test patterns and PR templates
Use templates from ../../shared/openapi-toolkit/assets/:
model_template.dart- Model class structureenum_template.dart- Enum type structuretest_template.dart- Unit test structureexample_template.dart- Example file structure
3.5 Update Documentation (MANDATORY)
Before running the review checklist, update all documentation:
-
README.md - Add/update:
- New resources to Features section
- New resources to API Coverage section
- New example references in Examples section
-
example/ - Create/update:
{feature}_example.dartfor each new resource
-
CHANGELOG.md - Add entry for new features/changes
4. Review & Validate (MANDATORY)
Perform the four-pass review documented in references/REVIEW_CHECKLIST.md:
bash
# Pass 2: Barrel file verification
python3 .claude/shared/openapi-toolkit/scripts/verify_exports.py \
--config-dir .claude/skills/openapi-toolkit-googleai-dart/config
# Pass 3: Documentation completeness
python3 .claude/shared/openapi-toolkit/scripts/verify_readme.py \
--config-dir .claude/skills/openapi-toolkit-googleai-dart/config
python3 .claude/shared/openapi-toolkit/scripts/verify_examples.py \
--config-dir .claude/skills/openapi-toolkit-googleai-dart/config
python3 .claude/shared/openapi-toolkit/scripts/verify_readme_code.py \
--config-dir .claude/skills/openapi-toolkit-googleai-dart/config
# Pass 4: Property-level verification
python3 .claude/shared/openapi-toolkit/scripts/verify_model_properties.py \
--config-dir .claude/skills/openapi-toolkit-googleai-dart/config
# Dart quality checks (run from packages/googleai_dart)
cd packages/googleai_dart && dart analyze --fatal-infos && dart format --set-exit-if-changed . && dart test test/unit/
Pass 4 is critical - catches missing properties in parent models (e.g., Tool, Candidate).
5. Finalize
bash
# Copy fetched specs to persisted locations
cp /tmp/openapi-toolkit-googleai-dart/latest-main.json packages/googleai_dart/specs/openapi.json
cp /tmp/openapi-toolkit-googleai-dart/latest-interactions.json packages/googleai_dart/specs/openapi-interactions.json
# Run quality checks (from packages/googleai_dart)
cd packages/googleai_dart && dart test && dart analyze && dart format --set-exit-if-changed .
Package-Specific References
- Package Guide - Package structure, naming conventions
- Implementation Patterns - Model conventions, serialization patterns
- Review Checklist - Four-pass validation process
Troubleshooting
- API key error: Export
GEMINI_API_KEYorGOOGLE_AI_API_KEY - Network errors: Check connectivity; retry after a few seconds
- No changes detected: Summary shows all zeros; no action needed
- New specs discovered: Add them to
config/specs.jsonand re-run
Didn't find tool you were looking for?