teamharness-communication

Use for TeamHarness message delivery details after a flow has decided a message must be sent: current-session reply, NO_REPLY, cross-room/cross-channel message tool payloads, PROJECT_REQUESTED task-room handoff, and requester replyRoute reports. Do not use to choose work mode, create rooms, delegate, check, or accept tasks.

Quality

85%

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 1-5

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

The body is highly actionable and clearly sequenced with strong validation checkpoints, but it is hurt by repeated near-duplicate JSON examples and a monolithic structure that inlines content which could live in separate reference files.

Suggestions

Dedupe the requester-report JSON blocks: show one canonical DingTalk example and one Matrix example, then note only the differing fields (e.g. mentionSender) for the variants.

Move the large PROJECT_REQUESTED and requester-report payload catalogs into a references/ file (e.g. PAYLOADS.md) and link to it from SKILL.md to improve progressive disclosure.

Consolidate the repeated 'use the message tool only for cross-room/cross-session sends; answer directly otherwise' guidance into a single stated-once rule.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and free of generic-concept padding, but near-duplicate JSON payloads repeat across scenarios (e.g. the DingTalk requester-report block appears three times, the Matrix DM route twice) and several 'do not use the message tool for normal replies' statements are restated.	3 / 5
Actionability	Provides copy-paste-ready JSON payloads with exact field names for every scenario, expected result objects, and explicit failure handling ('tool returns ok: false ... Do not mark the requester report as sent after that failure').	5 / 5
Workflow Clarity	Protocols are numbered and sequenced (Channel/Room Selection steps 1-5) with explicit checkpoints tied to tool return values ('After the tool returns delivery.sent: matrix_self_trigger, stop') and feedback loops for missing-metadata failures.	5 / 5
Progressive Disclosure	Well-organized into section headers but is a ~310-line monolith with no bundle files and no external references; the large payload catalogs are inlined rather than split into a reference file.	3 / 5
	Total	16 / 20 Passed

Description

92%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.

The description is specific, complete, and well-bounded, clearly stating what it does, when to use it, and when not to. Its only weakness is that trigger terms are system-protocol vocabulary rather than natural user phrasing.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete delivery actions — 'current-session reply, NO_REPLY, cross-room/cross-channel message tool payloads, PROJECT_REQUESTED task-room handoff, and requester replyRoute reports' — with comprehensive domain coverage.	5 / 5
Completeness	Explicitly answers both what (the listed delivery actions) and when ('Use for ... after a flow has decided a message must be sent'), with concrete trigger phrases and an explicit anti-trigger list.	5 / 5
Trigger Term Quality	Good keyword coverage with trigger vocabulary ('message delivery', 'reply', 'NO_REPLY', 'cross-room/cross-channel', 'PROJECT_REQUESTED', 'replyRoute reports') plus a 'Use for' clause, but terms are protocol-internal rather than natural user synonyms.	4 / 5
Distinctiveness Conflict Risk	Clear niche (message delivery only) reinforced by an explicit negative boundary — 'Do not use to choose work mode, create rooms, delegate, check, or accept tasks' — minimizing overlap with sibling skills.	5 / 5
	Total	19 / 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: agentscope-ai/AgentTeams
Path: plugins/teamharness/skills/team/communication/SKILL.md
Commit: 223ddc2

Reviewed: 5 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.