Output-Driven Dev

Guides defining success criteria and verification before coding to ensure deliverables are proven complete through measurable, reproducible evidence.

Security Scan

The skill is an instruction-only checklist for output-driven development; its requirements and instructions match its stated purpose and it doesn’t request extra permissions or install anything.

Purpose & Capability

Name/description (define success criteria and verification) align with the SKILL.md. There are no requested env vars, binaries, or installs that would be unrelated to its stated goal.

Instruction Scope

Runtime instructions are limited to defining outputs, writing verification steps, and documenting evidence. Example verification items mention running commands, opening URLs, and checking files as illustrative verification actions — which are appropriate for a verification template. The SKILL.md does not instruct reading unrelated system files, collecting secrets, or sending data to external endpoints outside normal verification activities.

Install Mechanism

No install spec and no code files — nothing is written to disk or downloaded. This is the lowest-risk model for a skill of this type.

Credentials

The skill declares no environment variables, credentials, or config paths. That is proportionate to an instruction-only checklist that only guides how to define and run verification.

Persistence & Privilege

always is false and the skill is user-invocable with normal autonomous-invocation allowed. That is expected for a helper skill; it does not request permanent presence or modify other skills or system-wide settings.

Assessment

This skill is a benign, instruction-only template to help agents and humans define success criteria and verification steps. It doesn't request credentials or install anything. Practical considerations before installing: (1) verification steps may instruct the agent to run commands, access URLs, or read files — ensure the agent's runtime permissions and network access are appropriately limited so verification actions cannot access sensitive data or exfiltrate information; (2) review any concrete verification commands the agent intends to run before allowing autonomous invocation; (3) if you want to restrict automation, keep the skill user-invocable only or apply agent-level policies that require approval for actions that touch network, filesystem, or external services.

Output-Driven Development Skill

Trigger

Define success criteria and verification BEFORE coding. Agents prove their work.

Trigger phrases: "define success criteria", "output-driven", "verify before done", "prove it works", "acceptance criteria"

Process

1. Define output: What exactly should the result look like?
2. Write verification: How will we prove it works?
3. Build: Implement the solution
4. Verify: Run verification, show evidence
5. Ship: Only after verification passes

Template

# Task: [Description]

## Success Criteria
- [ ] [Specific, measurable criterion 1]
- [ ] [Specific, measurable criterion 2]
- [ ] [Specific, measurable criterion 3]

## Verification Plan
For each criterion, how to verify:
1. [Run command X, expect output Y]
2. [Open URL, see element Z]
3. [Check file, contains content W]

## Build Log
[What was implemented and how]

## Verification Results
- Criterion 1: ✅ PASS — [evidence]
- Criterion 2: ✅ PASS — [evidence]
- Criterion 3: ❌ FAIL — [what went wrong, fix plan]

Rules

• Never claim "done" without showing verification evidence
• "Should work" is not verification — run it and show the output
• If you can't define success criteria, you don't understand the task
• Verification should be reproducible by anyone
• Failed verification → fix → re-verify (don't skip)
• Screenshots, logs, test output > "I checked and it works"