admin-valentin/agent-skill-creator
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
agent-skill-creator/scenarios/SC-050-nfr-context-consumption.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
Raw Blame History

SC-050: Meta-Skill SKILL.md Context Consumption Under 5000 Tokens

Covers: NFR-002 — Meta-skill SKILL.md context consumption <5,000 tokens for body Type: Performance

Given

  • The meta-skill's own SKILL.md has been restructured for v4.0
  • The file is at /Users/francylisboacharuto/agent-skill-creator/SKILL.md

When

  • The token count of the SKILL.md body (excluding frontmatter) is estimated

Then

  • The body content consumes fewer than 5,000 tokens
  • Using the heuristic of ~4 chars per token, the body is <20,000 characters
  • Detailed content is in references/ and loaded on demand

Verification Method

Method: CLI command

Steps:

  1. Extract the body (everything after the second ---): sed -n '/^---$/,/^---$/!p' SKILL.md | tail -n +1
  2. Count characters: wc -c on the body
  3. Assert character count <20,000 (conservative ~4 chars/token estimate for 5,000 token limit)
  4. Alternatively, use tiktoken if available: python3 -c "import tiktoken; enc=tiktoken.get_encoding('cl100k_base'); print(len(enc.encode(open('SKILL.md').read())))"

Expected evidence: Body character count is <20,000 characters. Estimated token count is <5,000 tokens.