teamharness-file-sharing

Use for TeamHarness shared workspace paths, filesync, artifact publication, and Matrix room file boundaries, including artifact publish_file and task/project deliverables. Do not use for message routing or project state changes.

Quality

93%

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

87%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 lean, actionable, and well-organized, with concrete filesync payloads and exact paths. Its one weak spot is workflow clarity: sequencing is present but lacks an explicit validation/retry feedback loop for the consequential publish and push operations.

Suggestions

Add an explicit validation checkpoint for publish/push operations, e.g. 'After push, verify the file appears under the shared path before relying on it; if publish is refused, adjust the path/content and retry.'

For `artifact publish_file`, document the feedback loop: check `publishedArtifacts` status and on refusal fix the flagged path/content and re-publish.

Consider a short numbered checklist for the deliverable-publishing flow (write under shared/tasks/{task-id}/ → list in `taskflow submit_task` deliverables → verify publish status) to make the implicit checkpoints explicit.

Dimension	Reasoning	Score
Conciseness	The body is dense with platform-specific knowledge Claude does not already have (Matrix `m.file` events, DingTalk/Feishu/WeChat channel handling) and avoids explaining basic concepts or padding with fluff, matching the 'lean and efficient' anchor.	3 / 3
Actionability	Provides concrete executable filesync JSON payloads (list/pull/push), exact `shared/...` paths, and specific parameters (`target`/`roomId`, `parentEventId` from `messageId`), matching the 'fully executable, copy-paste ready' anchor.	3 / 3
Workflow Clarity	Sequencing is clear ('Pull before reading remote shared state,' 'Push after writing project-level files'), but for consequential publish/push operations there is no explicit validate→fix→retry feedback loop — checkpoints are left implicit via platform behavior, fitting the 'sequence present but checkpoints missing or implicit' anchor rather than the cap-2-violating 3.	2 / 3
Progressive Disclosure	No bundle files exist and the single cohesive topic is organized into clear sections (Shared Files vs Room Files, Shared Paths, Filesync) with no nested references, satisfying the 'well-organized, no need for external references' guidance.	3 / 3
	Total	11 / 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, trigger-rich, and well-scoped: it states concrete capabilities, an explicit 'Use for' trigger, and a negative trigger that disambiguates it from sibling skills. It satisfies all four anchors at the top of the scale.

Dimension	Reasoning	Score
Specificity	Names multiple concrete capabilities — 'filesync, artifact publication,' 'artifact publish_file,' and 'task/project deliverables' — rather than vague abstractions, matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	Pairs an explicit 'Use for…' trigger (the 'when') with the concrete capabilities (the 'what'), and adds an explicit negative trigger, satisfying the 'clearly answers both what AND when' anchor rather than capping at 2.	3 / 3
Trigger Term Quality	Covers the domain's natural terms a TeamHarness user would actually say — 'shared workspace paths,' 'filesync,' 'artifact publish_file,' 'Matrix room file boundaries,' and 'deliverables' — matching the good-coverage anchor.	3 / 3
Distinctiveness Conflict Risk	Niche TeamHarness-specific scope plus explicit disambiguation ('Do not use for message routing or project state changes') makes it clearly distinguishable and unlikely to trigger for the wrong skill.	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/file-sharing/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.