BumpyClock/agent-templates / skills_archive/behavior-validator
behavior-validator
VerifiedSource-blind user behavior validation against a prewritten contract for apps, CLIs, APIs, and generated artifacts.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 3.7 KB |
| agents/openai.yaml | config | 232 B |
| references/contract-template.md | markdown | 1.4 KB |
| references/report-schema.md | markdown | 1.4 KB |
references/contract-template.md
View on GitHub# Behavior Contract Template
Use this shape when the user has not provided a behavior contract. Keep it short enough that a source-blind validator can execute it without reading implementation notes.
```md
# Behavior Contract
## User-Visible Goal
<What must be true from the user's point of view.>
## Target
- Type: web app | CLI | API | generated artifact | other
- Launch or access: <URL, command, endpoint, artifact path, or setup command>
- Allowed fixtures and credential source: <fixtures plus approved secret-tool or exact environment-variable names; never values>
## User Tasks
1. <Concrete task a real user/operator performs.>
2. <Concrete task a real user/operator performs.>
## Expected Observable Behavior
- <Screen, CLI output, API response, file content, state change, or persistence rule.>
- <Failure behavior for invalid input or unavailable data.>
## Anti-Cheat Probes
- <Change fixture/input data and verify output changes accordingly.>
- <Refresh/retry/reopen and verify expected persistence or reset behavior.>
- <Try invalid/empty/boundary input and verify the promised handling.>
## Evidence Required
- <Screenshots, terminal excerpts, response snippets, file summaries, accessibility observations, or logs.>
## Out Of Scope
- <Anything the validator must not judge.>
```
Completion criterion: every user task and anti-cheat probe has an expected observable result and evidence type.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| receiving-code-reviewobra/superpowersUse when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation | Stars: 319k | Updated | Claude CodeCodex | Verified | Install |
| requesting-code-reviewobra/superpowersUse when completing tasks, implementing major features, or before merging to verify work meets requirements | Stars: 319k | Updated | Claude CodeCodex | Verified | Install |
| using-git-worktreesobra/superpowersUse when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback | Stars: 319k | Updated | Claude CodeCodex | Verified | Install |
| verification-before-completionobra/superpowersUse when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always | Stars: 319k | Updated | Claude CodeCodex | Verified | Install |