Skip to content

JordanGunn/nunchuck / skills/prompt/prompt-exec

prompt-exec

Verified

Execute the forged prompt exactly as written. Requires explicit consent and a ready artifact. Deletes artifact after successful execution.

assets/prompt-artifact-schema.md

View on GitHub
# Prompt Artifact Schema

Defines the canonical structure for prompt artifacts in the ASI-compliant prompt skills.

## Version: 1.0

### Required Fields

- `version`: string - Schema version (must be "1")
- `status`: enum - Artifact status ("drafting", "ready", "executed")
- `created_at`: string - RFC3339 timestamp of creation
- `updated_at`: string - RFC3339 timestamp of last update

### Intent Object (required)

- `objective`: string - Clear statement of what the prompt aims to achieve
- `constraints`: array of strings - List of constraints and limitations
- `assumptions`: array of strings - Explicit assumptions being made
- `open_questions`: array of strings - Unresolved questions that block readiness

### Content Fields

- `prompt`: string - The actual prompt text
- `quality`: object | null - Quality metrics when present

### Quality Object (optional)

- `clarity_score`: number (0-1) - Subjective clarity rating
- `completeness_score`: number (0-1) - Subjective completeness rating
- `validated_at`: string - RFC3339 timestamp when quality was assessed

### Validation Rules

1. All required fields must be present
2. All timestamps must be valid RFC3339 format
3. Status must be one of the allowed enum values
4. When status is "ready", open_questions must be empty
5. When status is "executed", prompt must not be empty
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 323kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 323kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 323kUpdated Claude CodeCodexVerifiedInstall