Menu
Consensus planning with Planner/Architect/Critic iterative loop. Activate when user says: ralplan, consensus plan, consensus planning.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Use this skill when working with the GitLab MCP server tools for merge requests, issues, repositories, pipelines, work items, variables, dependency proxy, webhooks, search, CI catalog, and related GitLab workflows.
Clean AI-generated code slop with regression-safe workflow. Activate when user says: deslop, anti-slop, AI slop, cleanup slop, clean up this code, remove bloat.
Cancel any active OMG mode and clean up state. Activate when user says: cancel, stop, cancelomg, stopomg, abort, kill it, stop everything.
Claude-Codex-Gemini tri-model orchestration for multi-perspective analysis. Activate when user says: ccg, tri-model, three models, multi-model, cross-validate, get multiple opinions, compare models.
Canonical cross-language coding standards reference. Shared rules embedded by reviewer agents. Activate when: viewing coding standards, checking naming rules, reviewing style baseline, consulting style guide, what are the rules.
2-stage pipeline: trace (causal investigation) then deep-interview (requirements). Activate when user says: deep dive, deep-dive, investigate deeply, trace and interview.
| name | ralplan |
| description | Consensus planning with Planner/Architect/Critic iterative loop. Activate when user says: ralplan, consensus plan, consensus planning. |
| argument-hint | [--deliberate] <task description> |
Shorthand for /plan --consensus. Triggers iterative planning with Planner, Architect, and Critic agents until consensus is reached.
--deliberate: Forces deliberate mode for high-risk work. Adds pre-mortem (3 scenarios) and expanded test planning.Vague execution requests (e.g., "ralph improve the app") are redirected through ralplan first to ensure explicit scope, testable criteria, and multi-agent consensus.
Passes gate (specific enough): prompts with file paths, function names, issue numbers, numbered steps, or acceptance criteria.
Gated (needs scoping): prompts with only vague descriptions and no concrete anchors.
/team (parallel agents, recommended) or /ralph (sequential with verification)