admin-valentin/agent-skill-creator
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
agent-skill-creator/scenarios/SC-055-validate-existing-skill-with-issues.scenario.md
francylisboacharuto bac2b27bb8 feat: v4.0 Cross-Platform Modernization — Agent Skills Open Standard compliance 
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>
2026-02-26 14:52:09 -03:00

1.4 KiB
Raw Blame History

SC-055: Validate Existing Skill Reports Specific Issues

Covers: FR-011, FR-012, Section 2.2 — Secondary flow: Validate existing skill with issues Type: Failure

Given

  • An existing skill directory broken-tool/ with:
    • SKILL.md with name: Broken_Tool (invalid format)
    • Description of 1500 characters (exceeds 1024 limit)
    • scripts/main.py containing API_KEY = "sk-secret123"
    • A .env file with database credentials

When

  • The user invokes: "Validate this skill: broken-tool/"

Then

  • Spec validation fails with specific errors:
    • Invalid name format (uppercase, underscore)
    • Description exceeds 1024 characters
    • Name does not match directory name
  • Security scan reports findings:
    • Hardcoded API key in scripts/main.py
    • .env file with credentials
  • Fix suggestions are provided for each issue

Verification Method

Method: Automated test

Steps:

  1. Create broken-tool/ with the described invalid files
  2. Call validate_skill("broken-tool/")
  3. Assert result.valid is False
  4. Assert result.errors has >=3 entries (name format, description length, directory mismatch)
  5. Assert result.security has >=2 entries (hardcoded key, .env file)

Expected evidence: valid: False. Errors list includes name format, description length, and directory mismatch issues. Security list includes hardcoded key and .env file findings. Each finding includes a fix suggestion.