BREAKING CHANGES: - Remove -cskill suffix from all skill names (use standard kebab-case) - Simplify marketplace.json to only official fields (fixes Issue #5) - SKILL.md body must be <500 lines (progressive disclosure via references/) New features: - Cross-platform support for 8+ platforms (Claude Code, Copilot, Cursor, Windsurf, Cline, Codex CLI, Gemini CLI) - scripts/install-template.sh: Auto-detect platform installer with --dry-run - scripts/validate.py: Spec compliance checker for generated skills - scripts/security_scan.py: Security scanner for hardcoded keys and dangerous patterns - MIGRATION.md: v3.x to v4.0 migration guide - 6 new reference files for progressive disclosure from lean SKILL.md Key changes: - SKILL.md: 4,116 → 272 lines with spec-compliant YAML frontmatter - marketplace.json: Stripped to {name, plugins} only - article-to-prototype-cskill/ → article-to-prototype/ - stock-analyzer-cskill/ → stock-analyzer/ - Export system integrates validation + security scanning - README.md rewritten for all supported platforms - Phase 5 pipeline outputs SKILL.md-first, spec-compliant skills Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
1.4 KiB
1.4 KiB
SC-039: Generated Skills Work Across Platforms Without Modification
Covers: FR-028, NFR-001 — Generated skills MUST work on any SKILL.md-standard platform without modification Type: Happy Path
Given
- A skill has been generated by the meta-skill for "code review automation"
- The skill uses only standard SKILL.md features (no platform-specific extensions)
When
- The generated skill directory is copied to:
~/.claude/skills/code-review-automation/.github/skills/code-review-automation/.cursor/rules/code-review-automation/
Then
- The SKILL.md is valid standard SKILL.md format readable by all platforms
- No platform-specific hacks or workarounds are present in the files
- The frontmatter uses only standard fields (name, description, license, compatibility, metadata, allowed-tools)
- No files reference platform-specific paths or configurations
Verification Method
Method: Automated test
Steps:
- Generate a skill using the meta-skill
- Parse SKILL.md frontmatter and verify all fields are standard spec fields
- Grep for platform-specific strings:
grep -r "claude-code\|copilot\|cursor" code-review-automation/SKILL.md - Verify no platform-specific conditional logic in SKILL.md body
Expected evidence: SKILL.md frontmatter contains only standard fields. No platform-specific strings in SKILL.md body. The skill is a pure standard SKILL.md that any compliant platform can read.