Agent Skills
› zereight/gitlab-mcp
› ralplan
ralplan
GitHubRalplan技能用于通过Planner、Architect和Critic多智能体迭代循环达成共识规划。它处理模糊需求，强制明确范围与测试标准，生成包含ADR的详细计划，为后续执行提供高质量决策依据。
Trigger Scenarios
用户发起共识规划请求
处理模糊或高风险的执行指令
Install
npx skills add zereight/gitlab-mcp --skill ralplan -g -y
SKILL.md
Frontmatter
{
"name": "ralplan",
"description": "Consensus planning with Planner\/Architect\/Critic iterative loop. Activate when user says: ralplan, consensus plan, consensus planning.\n",
"argument-hint": "[--deliberate] <task description>"
}
Ralplan (Consensus Planning)
Shorthand for /plan --consensus. Triggers iterative planning with Planner, Architect, and Critic agents until consensus is reached.
Flags
--deliberate: Forces deliberate mode for high-risk work. Adds pre-mortem (3 scenarios) and expanded test planning.
Workflow
- @planner creates initial plan with RALPLAN-DR summary:
- Principles (3-5)
- Decision Drivers (top 3)
- Viable Options (>=2) with pros/cons
- @architect reviews for architectural soundness
- @critic validates quality and testability
- Loop until critic approves (max 5 iterations)
- Final plan includes ADR (Decision, Drivers, Alternatives, Why chosen, Consequences)
Pre-Execution Gate
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.
After Approval
- Execute via
/team(parallel agents, recommended) or/ralph(sequential with verification)
Version History
- a8f5d4f Current 2026-07-25 10:04
