agent-skill-creator/scenarios/SC-040-name-exceeds-64-chars.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

1.2 KiB

SC-040: Skill Name Exceeds 64 Characters Is Truncated

Covers: FR-001, Edge case 2.3 — Skill name exceeds 64 chars: truncate intelligently, warn user, suggest alternative Type: Edge Case

Given

  • The meta-skill is invoked with a very long workflow name
  • Input: "Create a skill for automatically processing and analyzing extremely long complex multi-step data transformation pipelines with validation"

When

  • Phase 3 derives the skill name from the description

Then

  • The generated name field is <=64 characters
  • The name is truncated at a word boundary (not mid-word)
  • The user receives a warning that the name was truncated
  • An alternative shorter name is suggested

Verification Method

Method: Automated test

Steps:

  1. Run the meta-skill with the long workflow description
  2. Parse the generated SKILL.md frontmatter
  3. Assert len(name) <= 64
  4. Assert the name does not end with a partial word fragment
  5. Verify meta-skill output contains a truncation warning

Expected evidence: name is <=64 chars. Output includes a message like "Name truncated from 78 to 64 characters" and suggests an alternative. Name ends at a clean word boundary.