team-coordination

Use before deciding how you should organize team work: DAG vs Loop, dependency shape, task waves, quality gates, acceptance criteria, interruption, replanning, or what to do after Worker results arrive. Always use this skill for team organization strategy before you call project-management or task-management.

Quality

81%

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

Quality

Content

77%Weight 40%Scale 1-3

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

The body is an actionable, well-sequenced strategy guide with explicit validation gates and named operations. Its weaker dimensions are progressive disclosure (everything inline, no reference files) and minor conciseness redundancy between sections.

Suggestions

Deduplicate the no-shared-write constraint: state it once in 'Design The Work' and have 'Patch Rules' cross-reference it instead of restating the full rule, to tighten conciseness.

Move the detailed DAG/Loop strategic flows or the hard-interruption checklist into one-level-deep reference files (e.g., DAG.md, INTERRUPTION.md) linked from SKILL.md, improving progressive disclosure for this >50-line skill.

Consolidate the repeated 'evaluate before advancing' guidance spread across DAG Strategy, Loop Strategy, and Result Decisions into a single shared acceptance-gate section to reduce redundancy.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and assumes Claude's competence (no explaining what a DAG is), but the no-shared-write rule is restated ("Parallelize only when tasks do not write the same result, directory, file..." in Design The Work vs "assign multiple Workers to write the same output, directory, file..." in Patch Rules), matching the score-2 anchor. Not 3 because of this redundancy; not 1 because there is no concept-padding fluff.	2 / 3
Actionability	It names concrete operations like "create or replace the DAG with `plan_dag`, then resolve ready nodes with `ready_nodes`" and "record each iteration decision with `record_loop_iteration`", matching the score-3 fully-executable-guidance anchor. Not 2 because the guidance references specific named commands rather than pseudocode.	3 / 3
Workflow Clarity	Both modes give explicit sequenced flows ("clarify goal -> design DAG -> delegate ready nodes -> collect results -> evaluate -> advance, verify, repair, replan, or complete") with validation gates ("Evaluate each iteration before creating or dispatching the next one", "confirm the impact before hard interruption"), matching the score-3 anchor. Not 2 because checkpoints are explicit.	3 / 3
Progressive Disclosure	It is well-sectioned but entirely inline at ~176 lines with no external references (and no bundle files exist), matching the score-2 anchor for content that could be separate being inline. Not 1 because sections are organized rather than a wall of text; not 3 because nothing is split into one-level-deep references.	2 / 3
	Total	10 / 12 Passed

Description

85%Weight 40%Scale 1-3

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 defines a distinct strategy niche, answers both what and when with an explicit trigger, and lists concrete decision areas. Its main weakness is trigger-term naturalness: several keywords are internal jargon a requester would not naturally say.

Dimension	Reasoning	Score
Specificity	"DAG vs Loop, dependency shape, task waves, quality gates, acceptance criteria, interruption, replanning, or what to do after Worker results arrive" lists multiple concrete decision areas, matching the score-3 anchor for listing multiple specific concrete actions. Not 2 because it is comprehensive across distinct decision types rather than merely naming a domain.	3 / 3
Completeness	"Use before deciding how you should organize team work" gives an explicit when, and the enumerated decisions answer what, matching the score-3 anchor for clearly answering both what AND when with explicit triggers. Not 2 because the trigger is explicit rather than merely implied.	3 / 3
Trigger Term Quality	Natural terms like "organize team work", "dependency", and "replanning" appear, but they are mixed with internal jargon ("DAG vs Loop", "task waves", "quality gates") a requester would rarely say, matching the score-2 anchor for some relevant keywords missing common variations. Not 3 because much of the trigger vocabulary is technical rather than natural user language.	2 / 3
Distinctiveness Conflict Risk	"Always use this skill for team organization strategy before you call project-management or task-management" explicitly positions it as a strategy layer distinct from sibling operation skills, matching the score-3 clear-niche anchor. Not 2 because it names and separates itself from the specific skills it could overlap.	3 / 3
	Total	11 / 12 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: agentscope-ai/AgentTeams
Path: manager/agent/team-leader-agent/skills/team-coordination/SKILL.md
Commit: 785c2db

Reviewed: 6 days 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.