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

88%

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 highly actionable with complete JSON payloads and clear, validated multi-step routing workflows. Its weaknesses are repetition of nearly identical requester-report examples and a monolithic single-file structure with no progressive disclosure, which together cap conciseness and progressive_disclosure.

Suggestions

Consolidate the repeated DingTalk/Matrix requester-report JSON examples in the Requester Report Message section into one base payload plus a short table of the per-variant deltas (e.g. mentionSender, channel/target fields).

Move the catalogue of full message-tool payload variants into a referenced bundle file (e.g. references/payloads.md) and keep SKILL.md as a concise overview with one-level-deep links, improving progressive disclosure.

De-duplicate the recurring 'do not use the message tool for normal replies; answer directly' guidance into a single stated rule near the Message Tool Protocol section.

Dimension	Reasoning	Score
Conciseness	The content is operational and avoids explaining concepts Claude already knows, but the Requester Report Message section repeats near-identical DingTalk/Matrix replyRoute payloads (5+ examples) and restates 'answer directly instead of the message tool' multiple times, which could be consolidated.	2 / 3
Actionability	Provides complete, copy-paste-ready JSON message-tool payloads for every delivery scenario (PROJECT_REQUESTED self-trigger, cross-session/Matrix-DM/DingTalk requester reports, cross-room and external-channel sends) with exact field names and expected results.	3 / 3
Workflow Clarity	The Channel/Room Selection Protocol is a clear numbered sequence with explicit error checkpoints ('If the destination is missing or ambiguous, do not guess... ask'), and delivery flows include feedback loops (tool returns ok:false -> do not mark report sent; delivery.sent -> stop in source session).	3 / 3
Progressive Disclosure	The body is well-sectioned under clear headings but is a single monolithic document with no bundle files; the repeated requester-report payloads are inline content that could be split out or consolidated rather than carried in SKILL.md.	2 / 3
	Total	10 / 12 Passed

Description

100%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, complete, and distinctive: it enumerates concrete message-delivery actions, gives an explicit trigger condition, and sharply bounds the skill against sibling skills via a 'Do not use' clause. It is concise without fluff.

Dimension	Reasoning	Score
Specificity	Lists five concrete message-delivery actions ('current-session reply, NO_REPLY, cross-room/cross-channel message tool payloads, PROJECT_REQUESTED task-room handoff, and requester replyRoute reports') rather than vague language.	3 / 3
Completeness	Clearly answers both what (the five payload types) and when ('after a flow has decided a message must be sent'), reinforced by an explicit negative boundary ('Do not use to choose work mode, create rooms, delegate, check, or accept tasks').	3 / 3
Trigger Term Quality	Uses natural domain trigger terms a TeamHarness user would invoke ('message delivery', 'NO_REPLY', 'PROJECT_REQUESTED', 'replyRoute', 'cross-room/cross-channel') with an explicit 'Use for ... after a flow has decided a message must be sent' clause.	3 / 3
Distinctiveness Conflict Risk	The exclusion clause ('Do not use to choose work mode, create rooms, delegate, check, or accept tasks') carves a clear niche distinct from sibling skills, making wrong-skill triggering unlikely.	3 / 3
	Total	12 / 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: plugins/teamharness/skills/team/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.