multi-cli-review
Multi-CLI Review
Version History
- v2.3: Standardized task-level
reviewer-idhandling to coordinator-assigned letter IDs while keeping actual CLI identity insource-cli - v2.2: Clarified generic coordinator ownership so the paired contract is not tied to a specific workflow surface
- v2.1: Aligned reviewer-side report emission with
multi-cli-review-action, tightened task-level path rules, and clarified reviewer-only boundaries
Purpose
multi-cli-review is the reviewer-side skill paired with multi-cli-review-action.
It is the reviewer half of a generic paired protocol, not a workflow-specific review format.
It does one thing:
- inspect the assigned target conservatively
- write one structured reviewer report
- hand that report back to the current CLI for aggregation and decisioning
More from starforall/ai-coding-toolkit
demand-risk-assessment
Use when 需要对外包/项目/需求做“接/谈判后接/暂停/拒绝”的风险与收益判断，尤其在范围/验收/付款/合规/工期/依赖不清，或出现应急插队、续约变更、多需求排序、AI/LLM 等高不确定信号时。
38multi-cli-review-action
Use when the current CLI is the sole fixer for one or more `multi-cli-review` reports and must reconcile reviewer findings before any edits, especially after requests like "汇总审查报告", "处理 multi-cli-review 输出", or "按 reviewer 建议执行修复".
37collaborating-with-claude
Use the Claude Code CLI to consult Claude and delegate coding tasks for prototyping, debugging, and code review. Supports multi-turn sessions via SESSION_ID. Optimized for low-token, file/line-based handoff.
33example-skill
Minimal example skill template compatible with the Skills CLI (`npx skills add`).
1