harivansh-afk/eval-skill/eval
Claude Code and agent skill by harivansh-afk/eval-skill
Trust tier 3
- community
Source check pending
Checking that the SKILL.md file is still in the repository.
Generate evaluation specs with building and verification criteria. Use when setting up features, defining acceptance criteria, or before implementing anything significant. Triggers on "create evals", "set up verification", "define acceptance criteria", or "build [feature]".
Install
npx vskill@latest install harivansh-afk/eval-skill/evalSKILL.md
Eval Skill
Generate specs that define what to build and how to verify it.
Output
I create .claude/evals/<name>.yaml with two sections:
- building_spec — What the builder agent implements
- verification_spec — What the verifier agent checks
Format
Workflow
User Request
My Questions
Before generating, I ask:
- What auth method? (email/password, OAuth, magic link?)
- UI, API, or both?
- Specific security requirements?
My Output
.claude/evals/auth.yaml:
Check Types
Deterministic
Agent
Best Practices
Building Spec
- Be specific — "bcrypt with cost 12" not "secure passwords"
- List files — helps builder know where to put code
- State constraints — what NOT to do matters
Verification Spec
- Deterministic first — fast, reliable checks
- Agent for semantics — UI flows, code quality, error messages
- Evidence always — no claim without proof
- generate_test for repeatables — UI flows yes, code review no
Naming
name: feature-name— lowercase, hyphensname: api-login— for agent checks, descriptive
What Happens Next
After I create the spec:
- Builder agent reads
building_spec, implements - Verifier agent reads
verification_spec, checks - If fail → builder gets feedback → fixes → verifier re-checks
- Loop until pass
- Agent checks become tests in
tests/generated/
Security
- Security scanPassed, 90 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/eval/SKILL.md
Popularity
- 7-day trend score
- 0
Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/harivansh-afk/eval-skill/eval)