skills/rpi-plan/SKILL.md
Create detailed, implementation-ready technical plans through an interactive and skeptical process grounded in codebase research. Use this whenever the user asks to plan, scope, design, spec, or phase implementation work (including "make a plan", "how should we build this", "break this into phases", and "write a technical spec"), even if they do not explicitly ask for a "plan."
npx skillsauth add avoidthekitchen/agent-agnostic-skills rpi-planInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Use this skill to turn requirements into a concrete implementation plan with clear phases, file-level changes, and verification criteria.
When this skill is invoked, respond with:
I'll help you create a detailed implementation plan. Let me start by understanding what we're building.
Please provide:
1. The task description or requirements
2. Any relevant context, constraints, or specific requirements
3. Links to related research or previous implementations
I'll analyze this information and work with you to create a comprehensive plan.
Then wait for the user's input.
After alignment on direction, propose phasing before full detail:
Here's my proposed plan structure:
## Overview
[1-2 sentence summary]
## Implementation Phases:
1. [Phase name] - [what it accomplishes]
2. [Phase name] - [what it accomplishes]
3. [Phase name] - [what it accomplishes]
Does this phasing make sense?
Write the plan to rpi/plans/TIMESTAMP_plan_descriptive_name.md.
TIMESTAMP: YYYY-MM-DD-HH-MM (for example 2026-03-05-22-10).descriptive_name.- [ ].Use this structure:
# [Feature/Task Name] Implementation Plan
## Overview
[Brief description of what we're implementing and why]
## Current State Analysis
[What exists now, what's missing, key constraints discovered]
## Desired End State
[Specific target behavior and how to verify it]
## What We're NOT Doing
[Explicit out-of-scope items]
## Implementation Approach
[High-level strategy and rationale]
## Phase 1: [Descriptive Name]
### Overview
[What this phase accomplishes]
### Changes Required
#### 1. [Component/File Group]
**File**: `path/to/file.ext`
**Changes**:
- [ ] [Concrete change 1]
- [ ] [Concrete change 2]
```[language]
// Specific code to add or modify
```
### Success Criteria
#### Automated Verification
- [ ] Tests pass: `npm test`
- [ ] Type checks pass: `npm run typecheck`
- [ ] Lint passes: `npm run lint`
#### Manual Verification
- [ ] Feature works as expected
- [ ] No regressions in related flows
- [ ] Performance remains acceptable
---
## Phase 2: [Descriptive Name]
[Repeat the same structure]
## Testing Strategy
### Unit Tests
- [What to test]
- [Key edge cases]
### Integration Tests
- [Critical end-to-end scenarios]
### Manual Testing Steps
1. [Specific step]
2. [Specific step]
## Performance Considerations
[Perf implications and mitigations]
## Migration Notes
[Data/system migration details if applicable]
development
Run deep, evidence-backed codebase research with parallel sub-investigations and produce a structured memo with file/line citations. Use this whenever the user asks to research, analyze, trace, debug, audit, or understand how code connects, including requests like "analyze this repo," "trace this flow," "where is this handled," root-cause investigations, architecture deep-dives, behavior comparisons, and implementation mapping, even if the user never says "research."
development
Implement approved technical plans phase-by-phase, including code changes, verification, and progress updates directly in the plan file. Use this whenever the user asks to execute a plan, implement from a plan document, continue plan-based work, resume from checked/unchecked tasks, or "do phase 1/2/3" from an implementation plan in `rpi/plans/`, even if they do not explicitly name this skill.
testing
Bootstrap high-signal Amp checks from merged pull request history. Use this whenever the user asks to generate `.agents/checks`, infer team review conventions from PRs, or suggest checks from review history.
development
Maintainer-only workflow for handling GitHub Secret Scanning alerts on OpenClaw. Use when Codex needs to triage, redact, clean up, and resolve secret leakage found in issue comments, issue bodies, PR comments, or other GitHub content.