CtrlK
BlogDocsLog inGet started
Tessl Logo

agent-team

统一管理多智能体角色的团队协作框架,支持智能体动态组合、灵活协作和扩展新角色。智能体本质上是"角色定义",可以根据任务需求灵活组建团队,实现从会议决策到系统构建的完整能力。智能体角色明确分工:有干活的、有指挥的、有挑毛病的,能实时看到沟通过程,共享数据库记忆,确保上下文一致。

47

Quality

51%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/agent-team/agent-team/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

42%

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

The skill is well-structured for progressive disclosure with a real, clearly-navigated reference bundle, but the body is far too verbose and offers mostly descriptive/illustrative guidance rather than executable instruction. Workflow sequencing is clear but lacks validation checkpoints.

Suggestions

Cut the repeated role-taxonomy explanations and the long illustrative meeting-dialogue transcripts; keep one concise example and defer the rest to a reference file.

Replace descriptive guidance ('选择合适的智能体') with concrete, executable steps or copy-paste-ready prompts/commands for forming and running a team.

Add explicit validation/verification checkpoints in the standard flow (e.g. confirm team roles are non-overlapping before execution, verify shared memory consistency after each step).

DimensionReasoningScore

Conciseness

The ~490-line body is verbose, restating the '干活的/指挥的/挑毛病的' taxonomy multiple times and including long illustrative meeting-dialogue transcripts and repeated checkmark lists that add bulk without new instruction, matching the verbose anchor.

1 / 3

Actionability

There is concrete structure (preset team configs, collaboration-mode diagrams, standard steps), but guidance is largely descriptive and illustrative rather than executable; the JSON memory snippets and dialogue transcripts are examples, not commands or code Claude would run.

2 / 3

Workflow Clarity

The standard flow (任务分析→团队组建→协作设计→任务执行→结果输出) is clearly sequenced with optional branches and degradation handling, but there are no explicit validation checkpoints or verify-then-proceed feedback loops.

2 / 3

Progressive Disclosure

The body acts as an overview pointing to real, confirmed one-level-deep reference files (meeting-agents.md, opc-agents.md, general-agents.md, collaboration-templates.md, agent-registry.md) and an asset template, each clearly signaled with '何时读取' navigation guidance in the resource index.

3 / 3

Total

8

/

12

Passed

Description

60%

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

The description clearly communicates what the skill does and names several concrete capabilities, but it lacks an explicit 'Use when...' trigger and leans on somewhat generic collaboration framing. It is solid but not exemplary on completeness and trigger quality.

Suggestions

Add an explicit 'Use when...' clause stating natural trigger phrases a user would say, e.g. 'Use when coordinating multiple agents on a task, designing a decision meeting, or building an OPC system.'

Include common natural keyword variations users might say (e.g. '多智能体协作', '组建AI团队', '开决策会议') to improve trigger coverage.

Tighten the niche framing so it is clearly distinguishable from generic teamwork/orchestration skills.

DimensionReasoningScore

Specificity

Lists multiple concrete actions such as '动态组合、灵活协作和扩展新角色', '组建团队', '共享数据库记忆', and '实时看到沟通过程', matching the anchor for several specific concrete actions.

3 / 3

Completeness

The 'what' is clearly stated (managing/composing agent teams), but there is no explicit 'Use when...' trigger clause for when to invoke it, which caps completeness at 2 per the guidelines.

2 / 3

Trigger Term Quality

Domain terms like '多智能体', '团队协作', '会议决策' and '系统构建' are relevant but there is no natural 'Use when...' phrasing or common variation users would actually say, so it only partially covers natural keywords.

2 / 3

Distinctiveness Conflict Risk

The '多智能体团队协作框架' niche is somewhat specific, but the generic '协作' framing could still overlap with other orchestration or teamwork skills, so it is not fully distinctive.

2 / 3

Total

9

/

12

Passed

Validation

87%

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

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 2 deeper-than-1-level

Warning

referenced_paths_exist

Referenced path issues: 4 deeper-than-1-level

Warning

Total

14

/

16

Passed

Repository
anbeime/skill
Reviewed

Table of Contents

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.