communication

Use before sending @mentions, deciding whether to reply, TASK_COMPLETED, BLOCKED, QUESTION, direct answers, loop prevention, or suppressing low-information acknowledgements.

Quality

91%

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

100%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 a tight, well-organized instruction skill: concrete message formats, explicit do/don't lists, a loop-safeguard checkpoint, and clean sectioning with no padding.

Dimension	Reasoning	Score
Conciseness	Lean and efficient with no padding and no explaining of concepts Claude already knows; every section (Routing, Coordinator Identity, @Mention Rules, History Context, Loop Safeguard) earns its place.	3 / 3
Actionability	Provides concrete, copy-ready message formats ('@coordinator:domain TASK_COMPLETED: <summary>', 'BLOCKED: <what is blocking you>', 'QUESTION: <your question>') and an explicit pre-send check ('remove all Matrix IDs... send only if the remaining text contains...'), plus precise do/don't lists.	3 / 3
Workflow Clarity	For a simple single-purpose decision skill the action is unambiguous, and the Loop Safeguard ('If two rounds of replies produce no new task, question, or decision, stop replying') acts as an explicit checkpoint/feedback bound.	3 / 3
Progressive Disclosure	Under 50 lines with no need for external references, yet organized into clearly labeled sections that make navigation easy — meeting the simple-skill bar for progressive disclosure.	3 / 3
	Total	12 / 12 Passed

Description

82%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 is specific and trigger-rich with strong distinctiveness, but it is framed entirely as a 'when to use' clause and never states the capability ('what it does') explicitly, capping completeness.

Suggestions

Lead with a short capability statement (e.g. 'Governs reply and @mention decisions in task coordination flows.') before the 'Use before...' trigger clause so both 'what' and 'when' are explicit.

Consider adding a few natural-language variations users might say (e.g. 'replying to the coordinator', 'when to acknowledge') alongside the protocol tokens to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions and decision points — '@mentions', 'deciding whether to reply', 'TASK_COMPLETED', 'BLOCKED', 'QUESTION', 'direct answers', 'loop prevention', 'suppressing low-information acknowledgements' — rather than vague language.	3 / 3
Completeness	The 'when' is explicit ('Use before sending...'), but there is no leading capability statement answering 'what does this do'; the 'what' is only implied through the list of decision points, so it stops short of a full what-and-when pairing.	2 / 3
Trigger Term Quality	Includes natural signal terms a coordinator would actually invoke this skill over — @mentions, TASK_COMPLETED, BLOCKED, QUESTION — plus behavioral triggers like 'loop prevention' and 'suppressing low-information acknowledgements'.	3 / 3
Distinctiveness Conflict Risk	The communication/coordination triggers (@mentions, TASK_COMPLETED, BLOCKED, QUESTION, loop prevention) carve a clear niche unlikely to fire for unrelated skills.	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/copaw-worker-agent/skills/communication/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.