This package follows the Skill Package Workflow Template methodology. Read BOOTSTRAP-RUNBOOK.md before contributing.
Open an issue using the bug-report template. Include :
- Skill name that misfires
- Exact user prompt
- Expected vs actual output
Open an issue using the feature-request template. Include :
- Proposed
tailwind-{cat}-{topic}name - Category (core / syntax / impl / errors / agents)
- Trigger scenarios ("Use when...")
- Why existing skills do not cover it
Branch convention : feat/, fix/, docs/, refactor/.
Before opening PR :
- Run validators locally :
node /path/to/Skill-Package-Workflow-Template/scripts/validate-frontmatter.js . node /path/to/Skill-Package-Workflow-Template/scripts/validate-line-count.js . node /path/to/Skill-Package-Workflow-Template/scripts/validate-structure.js . node /path/to/Skill-Package-Workflow-Template/scripts/validate-language.js . node /path/to/Skill-Package-Workflow-Template/scripts/validate-emdash.js .
- All must exit 0.
- Regenerate discovery manifests :
node scripts/generate-manifest.js . - Regenerate INDEX :
node scripts/generate-index.js . - Update CHANGELOG.md (Keep a Changelog format)
- Commit per skill (
feat(skill): tailwind-{cat}-{topic})
- English-only in skill content
- Deterministic language : ALWAYS / NEVER, no "you might consider"
- SKILL.md < 500 lines, overflow to
references/ - Section headings use
:not em-dash - YAML folded scalar
>for description, NEVER quoted strings - 3 reference files per skill :
methods.md,examples.md,anti-patterns.md - NO
README.mdinside a skill folder - Verify ALL code-snippets via WebFetch against official docs
This package was built using the 7-phase research-first methodology. New skills follow the same phases : research first, then create, then validate.
PRs that lower the compliance audit score below 90% will be requested for revision. Run :
node /path/to/Skill-Package-Workflow-Template/scripts/generate-audit-report.js .By contributing, you agree your work is licensed under the same MIT terms as the repository.