Read finalized specs and generate a detailed implementation plan. Updates the plans markdown with actionable steps. Use when user has reviewed specs and wants to generate an implementation plan.
Generates detailed implementation plans from finalized specifications with actionable steps and codebase analysis.
/plugin marketplace add datamaker-kr/synapse-claude-marketplace/plugin install sdd-helper@synapse-marketplaceThis skill is limited to using the following tools:
Part of the spec-manager agent. This skill generates detailed, actionable implementation plans from finalized specifications.
The user provides a task slug (or task title) as arguments: $ARGUMENTS
If no arguments are provided:
*/specs.md files in specs/ directoryIf a task title (not slug) is provided, convert it to a slug to find the matching files.
specs/{slug}/requirements.md - for original context and goalsspecs/{slug}/specs.md - for technical specificationsCheck that specs are sufficiently detailed for planning:
If specs have unresolved open questions, warn the user and ask whether to proceed or resolve them first.
Before generating the plan:
Update specs/{slug}/plans.md with the implementation plan:
# Plans: {Original Task Title}
> Created: {original date}
> Updated: {YYYY-MM-DD}
> Status: Ready
> Requirements: [requirements.md](./requirements.md)
> Specs: [specs.md](./specs.md)
## Overview
{Brief summary of what will be implemented and the approach}
## Prerequisites
- {Any setup, dependencies, or preparatory work needed before starting}
## Implementation Steps
### Step 1: {Step Name}
- **Goal**: {What this step achieves}
- **Specs Reference**: TS-{X}
- **Files**:
- `{path/to/file}` - {Create | Modify} - {What changes}
- **Details**:
{Detailed implementation instructions}
- **Validation**:
- {How to verify this step is complete}
- **Complexity**: Simple | Medium | Complex
### Step 2: {Step Name}
{Same structure}
{Continue for all steps...}
## Task Breakdown
Ordered checklist for tracking progress:
- [ ] **Step 1**: {Brief description}
- [ ] **Step 2**: {Brief description}
- [ ] ...
- [ ] **Final**: Verify all acceptance criteria
## File Change Summary
| File | Action | Step | Description |
|------|--------|------|-------------|
| `path/to/file` | Create/Modify/Delete | Step N | Brief description |
## Dependencies Between Steps
{Describe which steps depend on others and which can be parallelized}
Step 1 ─── Step 2 ─── Step 4 │ Step 3 ─── Step 5
## Testing Strategy
### Unit Tests
- {What to test and where}
### Integration Tests
- {What to test and where}
### Manual Verification
- {Steps to manually verify the feature works}
## Rollback Plan
{How to safely undo changes at each major checkpoint}
1. **After Step N**: {How to rollback}
2. **After Step M**: {How to rollback}
## Risk Assessment
| Risk | Likelihood | Impact | Mitigation |
|------|------------|--------|------------|
| {Risk} | Low/Medium/High | Low/Medium/High | {How to mitigate} |
## Progress Tracking
| Step | Status | Started | Completed | Notes |
|------|--------|---------|-----------|-------|
| Step 1 | Pending | | | |
| Step 2 | Pending | | | |
## Acceptance Criteria Checklist
From requirements:
- [ ] {Criterion from FR-1}
- [ ] {Criterion from FR-2}
- [ ] ...
After generating the plan, display a summary:
Implementation plan generated for: "{Original Task Title}"
Updated: specs/{slug}/plans.md
Summary:
- {N} implementation steps
- {X} files to create, {Y} files to modify
- Estimated complexity: {overall assessment}
- {Z} risks identified
Please review the plan in specs/{slug}/plans.md
When ready to start implementation:
1. Follow the steps in order
2. Check off tasks as you complete them
3. Update the Progress Tracking table
When the user is implementing and discusses progress or issues:
specs/{slug}/requirements.md with new/changed requirementsspecs/{slug}/specs.md to reflect changesspecs/{slug}/plans.mdspecs/{slug}/specs.md with the changesspecs/{slug}/plans.mdspecs/{slug}/specs.md if neededSearch, retrieve, and install Agent Skills from the prompts.chat registry using MCP tools. Use when the user asks to find skills, browse skill catalogs, install a skill for Claude, or extend Claude's capabilities with reusable AI agent components.
Activates when the user asks about AI prompts, needs prompt templates, wants to search for prompts, or mentions prompts.chat. Use for discovering, retrieving, and improving prompts.
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.