메뉴
Dispatch a swarm of small agents to test docs, implementations, or designs. Two modes: 'review' (quick comprehension check with fix-and-iterate) and 'evaluate' (structured evaluation with scored results and recommendations).
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
| name | swarm-test |
| description | Dispatch a swarm of small agents to test docs, implementations, or designs. Two modes: 'review' (quick comprehension check with fix-and-iterate) and 'evaluate' (structured evaluation with scored results and recommendations). |
Two modes, one purpose: find gaps before users do.
Quick quality gate. Dispatches 8-12 haiku agents, each trying to accomplish a real task using the work product. Agents report where they got stuck. Gaps are identified, proposed to the user, and fixed. Use after completing a body of work.
Skill: swarm-test:review
Structured evaluation with an intelligent orchestrator. Assesses the target, designs a test plan mixing comprehension, factual, and counter-factual scenarios, proposes it for approval, dispatches agents, and synthesises scored results with findings and recommendations.
Skill: swarm-test:evaluate
swarm-test <target> → review (the quick default)swarm-test evaluate <target> → evaluateWhen a mode is selected, read and follow the full skill file for that subskill.
Identify changed code and dispatch reuse, quality, and efficiency reviewer agents in parallel; return the raw findings list.
Review changed code for reuse, quality, and efficiency, and produce a triaged list of findings (no edits). Use after writing code, for simpler code with fewer bugs and better performance.
Provides guidance on good software design principles, with trade-off calibration, examples, and common failure modes. Applies when making decisions while writing, designing, or refactoring code, or evaluating trivial code for clarity, maintainability, and common mistakes.
Reviews code with a team against established software design principles, and returns triaged findings (no edits). Use when evaluating code, or after writing or refactoring complex code, systems or technical designs: for code that is clearer, easier to maintain, and avoids common mistakes.
Shared setup for shaping sessions. Determines if an artefact exists or needs creating, creates it if needed, starts the transcript, reads the type taxonomy. Called by the parent router or by any sub-skill invoked directly.
Shape an artefact through structured Q&A. Routes to the right sub-skill: brainstorm (new/unclear artefacts), refine (open decisions), or discover (exploration-driven artefacts like People and Ideas).