aconture

sdd-propose

0
0
# Install this skill:
npx skills add aconture/skills-antigravity --skill "sdd-propose"

Install specific skill from multi-skill repository

# Description

>

# SKILL.md


name: sdd-propose
description: >
Create a change proposal with intent, scope, and approach.
Trigger: When the orchestrator launches you to create or update a proposal for a change.
license: MIT
metadata:
author: AGCC took from gentleman-programming
version: "2.0"


Purpose

You are a sub-agent responsible for creating PROPOSALS. You take the exploration analysis (or direct user input) and produce a structured proposal.md document inside the change folder.

What You Receive

From the orchestrator:
- Change name (e.g., "add-dark-mode")
- Exploration analysis (from sdd-explore) OR direct user description
- Artifact store mode (openspec | none)

Execution and Persistence Contract

Read and follow skills/_shared/persistence-contract.md for mode resolution rules.

  • If mode is openspec: Read and follow skills/_shared/openspec-convention.md.
  • If mode is none: Return result only. Never create or modify project files.

What to Do

Step 1: Load Skill Registry

Do this FIRST, before any other work.

  1. Read .atl/skill-registry.md from the project root
  2. If not exists: proceed without skills (not an error)

From the registry, identify and read any skills whose triggers match your task. Also read any project convention files listed in the registry.

Step 2: Create Change Directory

IF mode is openspec: create the change folder structure:

openspec/changes/{change-name}/
└── proposal.md

IF mode is none: Do NOT create any openspec/ directories. Skip this step.

Step 3: Read Existing Specs

IF mode is openspec : If openspec/specs/ has relevant specs, read them to understand current behavior that this change might affect.

IF mode is none: Skip — no existing specs to read.

Step 4: Write proposal.md

# Proposal: {Change Title}

## Intent

{What problem are we solving? Why does this change need to happen?
Be specific about the user need or technical debt being addressed.}

## Scope

### In Scope
- {Concrete deliverable 1}
- {Concrete deliverable 2}
- {Concrete deliverable 3}

### Out of Scope
- {What we're explicitly NOT doing}
- {Future work that's related but deferred}

## Approach

{High-level technical approach. How will we solve this?
Reference the recommended approach from exploration if available.}

## Affected Areas

| Area | Impact | Description |
|------|--------|-------------|
| `path/to/area` | New/Modified/Removed | {What changes} |

## Risks

| Risk | Likelihood | Mitigation |
|------|------------|------------|
| {Risk description} | Low/Med/High | {How we mitigate} |

## Rollback Plan

{How to revert if something goes wrong. Be specific.}

## Dependencies

- {External dependency or prerequisite, if any}

## Success Criteria

- [ ] {How do we know this change succeeded?}
- [ ] {Measurable outcome}

Step 5: Persist Artifact

This step is MANDATORY — do NOT skip it.

If mode is openspec: the file was already written in Step 4.

If you skip this step, the next phase (sdd-spec) will NOT be able to find your proposal and the pipeline BREAKS.

Step 6: Return Summary

Return to the orchestrator:

## Proposal Created

**Change**: {change-name}
**Location**: `openspec/changes/{change-name}/proposal.md` (openspec) | inline (none)

### Summary
- **Intent**: {one-line summary}
- **Scope**: {N deliverables in, M items deferred}
- **Approach**: {one-line approach}
- **Risk Level**: {Low/Medium/High}

### Next Step
Ready for specs (sdd-spec) or design (sdd-design).

Rules

  • In openspec mode, ALWAYS create the proposal.md file
  • If the change directory already exists with a proposal, READ it first and UPDATE it
  • Keep the proposal CONCISE - it's a thinking tool, not a novel
  • Every proposal MUST have a rollback plan
  • Every proposal MUST have success criteria
  • Use concrete file paths in "Affected Areas" when possible
  • Apply any rules.proposal from openspec/config.yaml
  • Return a structured envelope with: status, executive_summary, detailed_report (optional), artifacts, next_recommended, and risks

# Supported AI Coding Agents

This skill is compatible with the SKILL.md standard and works with all major AI coding agents:

Learn more about the SKILL.md standard and how to use these skills with your preferred AI coding agent.