multi-agent-meeting

项目管理专家与产品经理在做项目决策、技术评审或商业策略制定时，当需要多视角碰撞以打破思维局限，请用此技能模拟多智能体真实会议辩论，一键生成包含决策结论、核心论据与风险提示的完整会议记录，让复杂决策高效落地！

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/multi-agent-meeting/multi-agent-meeting/SKILL.md

Quality

Content

61%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, lean instruction-only skill with clear phases and good progressive disclosure into real reference files. Its main gaps are the absence of validation/feedback checkpoints in the workflow and framework-level rather than concrete actionability.

Suggestions

Add explicit validation or convergence checkpoints between phases (e.g., confirm all roles have spoken before moving to debate, verify consensus criteria before decision generation) to lift workflow clarity.

Provide a concrete agent-dialogue example or a sample prompt template showing how one agent should respond to another, making the guidance more directly executable.

Move the capability restatement in 任务目标 into the description and keep the body focused on procedure, trimming 注意事项 to skill-specific guardrails only.

Dimension	Reasoning	Score
Conciseness	The body is efficiently organized with bullet lists and does not explain concepts Claude already knows, but the 任务目标 section restates capabilities that overlap with the description and 注意事项 contains some generic advice, keeping it just below a 5.	4 / 5
Actionability	As an instruction-only skill it appropriately avoids scripts, and it gives a concrete framework (role fields, five meeting phases, output sections) with real reference files, but the guidance is structural/template-level rather than providing concrete agent-dialogue examples or prompt templates, so it sits at 3 rather than 4.	3 / 5
Workflow Clarity	There is a clear sequence (four setup steps plus five explicit phases: 开场→自由讨论→深入辩论→共识收敛→决策生成), but no validation or feedback checkpoints are defined between phases, matching the 3 anchor for a present sequence with missing checkpoints.	3 / 5
Progressive Disclosure	The body is a well-signaled overview pointing one level deep to real bundle files (references/agent-roles.md, references/meeting-record-format.md, assets/meeting-templates/) with a dedicated 资源索引 section, with only minor organization gaps keeping it from a 5.	4 / 5
	Total	14 / 20 Passed

Description

78%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description that clearly states both capability and trigger context with natural professional terms and a distinct niche. Its main weakness is the second-person invocation ("请用此技能"), which the rubric penalizes on specificity.

Suggestions

Rewrite in third person (e.g., 'Simulates multi-agent meeting debates...') instead of the second-person '请用此技能' to avoid the specificity penalty.

Trim marketing fluff ("一键", "高效落地！") to keep the description lean and concrete.

Add a couple of natural trigger synonyms (e.g., '头脑风暴', '方案评审', '团队讨论') to push trigger-term coverage toward comprehensive.

Dimension	Reasoning	Score
Specificity	The description names the domain and several concrete actions ("模拟多智能体真实会议辩论", "一键生成包含决策结论、核心论据与风险提示的完整会议记录"), which would anchor at 4, but it uses second-person voice ("请用此技能"), which the rubric penalizes by reducing specificity by 1.	3 / 5
Completeness	It explicitly answers both what (simulate multi-agent meeting debate and generate a meeting record with conclusions, arguments, and risk notes) and when ("当需要多视角碰撞以打破思维局限...做项目决策、技术评审或商业策略制定时") with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	It includes natural professional phrases users would say ("项目决策", "技术评审", "商业策略制定", "多视角碰撞", "会议辩论"), giving good keyword coverage, though a few natural synonyms/variants are missing so it is not a 5.	4 / 5
Distinctiveness Conflict Risk	It carves a clear niche (multi-agent meeting simulation for decision-making) that is mostly distinct from other skills, with only minor overlap risk against general brainstorming or discussion skills, fitting the 4 anchor rather than the fully distinct 5.	4 / 5
	Total	16 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: anbeime/skill
Path: skills/multi-agent-meeting/multi-agent-meeting/SKILL.md
Commit: d9e888d

Reviewed: ~19 hours ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.