tdd-typescript
Default test workflow. RED-GREEN-REFACTOR cycle for all new TypeScript code.
Third-Party Agent Skill: Review the code before installing. Agent skills execute in your AI assistant's environment and can access your files. Learn more about security
Installation for Agentic Skill
View all platforms →skilz install settlemint/agent-marketplace/tdd-typescript skilz install settlemint/agent-marketplace/tdd-typescript --agent opencode skilz install settlemint/agent-marketplace/tdd-typescript --agent codex skilz install settlemint/agent-marketplace/tdd-typescript --agent gemini
First time? Install Skilz: pip install skilz
Works with 22+ AI coding agents
Cursor, Aider, Copilot, Windsurf, Qwen, Kimi, and more...
Extract and copy to ~/.claude/skills/ then restart Claude Desktop
git clone https://github.com/settlemint/agent-marketplace cp -r agent-marketplace/devtools/skills/tdd-typescript ~/.claude/skills/ Need detailed installation help? Check our platform-specific guides:
Related Agentic Skills
automating-mail
by SpillwaveSolutionsAutomates Apple Mail via JXA with AppleScript dictionary discovery. Use when asked to "automate email", "send mail via script", "JXA Mail automation",...
automating-reminders
by SpillwaveSolutionsAutomates Apple Reminders using JavaScript for Automation (JXA). Use when asked to "create reminders programmatically", "automate reminder lists", "JX...
mastering-postgresql
by SpillwaveSolutionsPostgreSQL development for Python with full-text search (tsvector, tsquery, BM25 via pg_search), vector similarity (pgvector with HNSW/IVFFlat), JSONB...
automating-contacts
by SpillwaveSolutionsAutomates macOS Contacts via JXA with AppleScript dictionary discovery. Use when asked to "automate contacts", "JXA contacts automation", "macOS addre...
Agentic Skill Details
- Owner
- settlemint (GitHub)
- Repository
- agent-marketplace
- Type
- Other
- Meta-Domain
- N/A
- Primary Domain
- N/A
- Market Score
- 87.0
Agent Skill Grade
B
Score: 87/100
Click to see breakdown
Score Breakdown
Areas to Improve
- The enforcement_patterns section (60+ lines) repeats coverage gates and anti-patterns already in test-strategy-checklist.md
- 63-line section with detailed examples belongs in a reference file, not main SKILL.md
- No end-to-end example showing test → failure output → implementation → pass output → refactor
Recommendations
- Add trigger phrases to description for discoverability
- Add table of contents for files over 100 lines
Graded: 1/18/2026
Developer Feedback
I took a look at your tdd-typescript skill and wanted to share some thoughts.
Links:
The TL;DR
You're at 87/100, which is solid B-grade territory. This is based on Anthropic's skill best practices framework. Your strongest pillar is Spec Compliance (14/15)—the metadata and frontmatter are clean. The main drag is Progressive Disclosure Architecture (26/30)—you've got content that could be tightened up, and that's costing you points on token efficiency.
What's Working Well
- Spec compliance is nearly perfect (14/15). Your YAML frontmatter is valid, naming conventions are spot-on (hyphen-case), and your description captures 32 trigger patterns covering real TDD vocabulary (RED/GREEN, Kent Beck, coverage gates). That's comprehensive.
- Your reference structure is smart. Five references, one workflow, all one level deep from SKILL.md. Clean navigation with
<workflow_index>and<reference_index>tables. Developers can find what they need. - Phase gates and verification are explicit. Your tdd-cycle.md workflow shows clear RED→GREEN→REFACTOR steps with actual verification commands. That's practical.
The Big One: Token Bloat in SKILL.md
Here's what's holding you back. Your main SKILL.md file is ~310 lines, and you've got two sections that really belong in references:
enforcement_patterns(60+ lines) duplicates content already intest-strategy-checklist.md. Coverage gates, anti-patterns—it's all there twice.plan_mode_integration(63 lines) has detailed worker preambles and validation patterns that should live in a separate reference file likereferences/plan-mode-tdd.md.
Why this matters: Token economy is 40% of your PDA score. You're burning tokens repeating yourself. Move those sections out, keep a 5-line summary in SKILL.md pointing to the references, and you gain +4 points on PDA easy.
Other Things Worth Fixing
Missing end-to-end example – You show individual RED, GREEN, and REFACTOR phases separately, but no complete trace showing a single feature flowing through all three phases with actual terminal output. Add a
<complete_example>section to tdd-cycle.md. That's worth +1 Utility point.Occasional second-person voice – Lines like "when you need" and "you should" slip into the documentation. Stick to imperative: "Search GitHub for TDD patterns when blocked" instead of "Find TDD patterns on GitHub when stuck." One more point in Writing Style.
Minor penalty on XML tags – You're using XML-style tags in your metadata (
<enforcement_patterns>, etc.) which triggered a small penalty. Not critical, but keep that in mind for future skills.
Quick Wins
- Extract enforcement_patterns and plan_mode_integration to references → +4 PDA points
- Add complete RED-GREEN-REFACTOR example with terminal output → +1 Utility
- Audit for second-person voice, switch to imperative → +1 Writing Style
- These three moves get you to 93/100, solid A territory
Checkout your skill here: SkillzWave.ai | SpillWave We have an agentic skill installer that install skills in 14+ coding agent platforms. Check out this guide on how to improve your agentic skills.
AI-Detected Topics
Extracted using NLP analysis
Report Security Issue
Found a security vulnerability in this agent skill?