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>
35 lines
982 B
Markdown
35 lines
982 B
Markdown
# SC-054: Validate Existing Skill Flow
|
|
|
|
> Covers: FR-011, Section 2.2 — Secondary flow: Validate existing skill
|
|
> Type: Happy Path
|
|
|
|
## Given
|
|
- An existing skill directory `my-tool/` with:
|
|
- Valid SKILL.md with proper frontmatter
|
|
- `scripts/main.py` (clean, no secrets)
|
|
- `references/guide.md`
|
|
- No `.env` files
|
|
|
|
## When
|
|
- The user invokes: "Validate this skill: my-tool/"
|
|
|
|
## Then
|
|
- The meta-skill runs spec validation (frontmatter, naming, structure)
|
|
- The meta-skill runs security scan
|
|
- The meta-skill reports pass/fail with specific issues
|
|
- For this valid skill, both validation and security pass
|
|
|
|
## Verification Method
|
|
|
|
**Method**: Manual test
|
|
|
|
**Steps**:
|
|
1. Create a valid skill directory `my-tool/` with all proper files
|
|
2. Invoke the meta-skill with: "Validate this skill: my-tool/"
|
|
3. Observe the validation and security scan output
|
|
|
|
**Expected evidence**: Output shows:
|
|
```
|
|
Spec Validation: PASSED (0 errors, 0 warnings)
|
|
Security Scan: PASSED (0 findings)
|
|
```
|