From rp1-dev
Routes mid-stream feature edits like discoveries, pivots, or requirement changes to an agent for validation, documentation propagation, and interactive decision handling up to 3 rounds.
How this skill is triggered — by the user, by Claude, or both
Slash command
/rp1-dev:feature-editThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Route to feature-editor agent after param validation.
Route to feature-editor agent after param validation.
Extract these parameters from the user's input:
| Parameter | Required | Default | Description |
|---|---|---|---|
FEATURE_ID | Yes | - | Feature identifier (kebab-case, e.g., auth-flow) |
EDIT_DESCRIPTION | Yes | - | Freeform edit description text |
Environment values (resolve via shell):
RP1_ROOT: !rp1 agent-tools rp1-root-dir (extract data.root from JSON response)Missing FEATURE_ID:
Error: Missing feature-id parameter
Usage: /rp1-dev:feature-edit feature-id "edit description"
Example: /rp1-dev:feature-edit auth-flow "Discovery: OAuth library doesn't support refresh tokens"
Missing EDIT_DESCRIPTION:
Error: Missing edit description
Usage: /rp1-dev:feature-edit feature-id "edit description"
Edit types:
- Requirement changes: "Add rate limiting to login endpoint"
- Discoveries: "Discovery: API doesn't support pagination"
- Concerns: "Concern: Error handling for failed requests not specified"
- Assumption changes: "Assumption change: Users will authenticate via SSO, not password"
- Pivots: "Pivot: Focus on mobile-first instead of desktop"
{% dispatch_agent "rp1-dev:feature-editor" %} FEATURE_ID: {FEATURE_ID} EDIT_DESCRIPTION: {EDIT_DESCRIPTION} DECISIONS: {}
Analyze and process this edit. {% enddispatch_agent %}
Parse agent response:
If type: "needs_decision" (JSON w/ decision_key, question, options, context):
{% ask_user "{question from JSON}", options: "{options mapped from JSON}" %}
Re-invoke agent w/ accumulated decisions:
{% dispatch_agent "rp1-dev:feature-editor" %} FEATURE_ID: {FEATURE_ID} EDIT_DESCRIPTION: {EDIT_DESCRIPTION} DECISIONS: {"classification": "...", "scope_action": "...", ...} {% enddispatch_agent %}
If success: Display summary
If error/abort: Display message
npx claudepluginhub rp1-run/rp1Orchestrates changing an existing working feature to new desired behavior by updating tests first, then implementation, with review and gated commit.
Processes increment-request.json: orients on project state, elicits incremental EARS requirements with acceptance criteria, classifies changes, updates SRS/design docs, appends to feature-list.json.
Guides creation, editing, and verification of skills for AI coding agents using test-driven development with subagent scenarios. Use when authoring or debugging skills.