miaodx/intuitive-flow/intuitive-tests
Claude Code and agent skill by miaodx/intuitive-flow
- community
Checking that the SKILL.md file is still in the repository.
Audit or improve test-suite structure and signal when the user asks about redundancy, pruning, layout, fixtures, or parameterization.
Install
npx vskill@latest install miaodx/intuitive-flow/intuitive-testsSKILL.md
Intuitive Tests
Improve test-suite signal and maintainability. Keep proof of observable behavior, real failure modes, and supported contracts; consolidate duplicates and remove assertions that merely restate implementation shape. Keep at least one meaningful proof of every behavior. Runtime discovery and packaging checks can be valuable contracts even when they look structural.
For broad or ambiguous cleanup, audit then propose a decision-complete slice. For a precise implementation request, execute that slice and park unrelated ideas. Keep existing repo test conventions; pytest examples are not a required taxonomy.
Modes
| Mode | Use when | Output | Redirect when | |
|---|---|---|---|---|
| Audit / propose | Cleanup target is unclear | Evidence, candidates, bounded recommendation and proof plan | A slice is already approved | |
| Prune / consolidate | Tests duplicate proof or bind internals | Smaller suite with behavior coverage preserved | No redundant proof exists | |
| Marker / layout | Suite selection or paths need organization | Updated runners, consumers and collection proof | The issue is test value | |
| Fixture / parameterize | Repeated setup or cases obscure intent | Shared setup or cases with readable diagnostics | Reuse is speculative |
Read value and pruning for test admission or deletion decisions; read suite structure only for markers, moves, fixtures, or parameterization. An audit may recommend a route without loading every implementation procedure.
Verify the changed behavior and affected runner/collection paths. Derive any external-service, hardware, or credential limits from current user/repo policy. Report kept/merged/deleted/reclassified tests, remaining proof, affected commands, and skipped checks with their actual reason.
Security
- Security scanPassed, 100 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/intuitive-tests/SKILL.md
Popularity
- Repository stars
- 48
- Repository forks
- 3
- 7-day trend score
- 19
Stars and forks are for the whole GitHub repository, not this skill alone. 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/miaodx/intuitive-flow/intuitive-tests)