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.

references/06_PROCEDURE.md

View on GitHub
---
description: Canonical execution path for this skill.
index:
  - Preconditions
  - "Step 1: Verify Preconditions"
  - "Step 2: Quote Before Execute"
  - "Step 3: Execute and Emit Prompt"
  - "Step 4: Perform the Prompt"
  - "Step 5: Confirm Completion"
---

# Procedure

## Preconditions

All must be satisfied before execution:

1. **Artifact exists**: `.prompt/active.yaml` must exist
2. **Status is ready**: `status: ready` in artifact
3. **User consent**: explicit and unambiguous confirmation

## Step 1: Verify Preconditions

```bash
./scripts/exec.sh --dry-run
```

If preconditions are not met, stop and return the error output.

## Step 2: Quote Before Execute

Display the exact prompt text to the user before execution.

Ask: "Execute this prompt now?"

## Step 3: Execute and Emit Prompt

Run the deterministic execution script:

```bash
./scripts/exec.sh
```

On success, this script will:

1. Write an execution receipt
2. Delete the active artifact
3. Print the exact prompt text to execute

## Step 4: Perform the Prompt

Perform the printed prompt exactly as written (no reinterpretation).

## Step 5: Confirm Completion

After execution, the system returns to "no active prompt" state.
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: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated 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: 322kUpdated Claude CodeCodexVerifiedInstall