organization

Use only when you need to look up team topology, worker phase, runtime state, or identity that is NOT available from the current message context. Do not use for standard task flows — the coordinator is the message sender, and the task room is in meta.json.room_id.

Quality

79%

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

Fix and improve this skill with Tessl

tessl review fix ./manager/agent/copaw-worker-agent/skills/organization/SKILL.md

Quality

Content

78%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 content is a tight, actionable reference for a simple read-only lookup skill, with real CLI commands and sensible error-recovery guidance. The main improvement opportunity is de-duplicating the repeated 'do not infer/guess' warnings.

Suggestions

Consolidate the three repeated anti-drift warnings (lines on memory/old chat/task files, teamName source, and 'do not guess') into a single concise 'Do not infer state from memory, old chat, or task files; if metadata is missing or queries are denied, ask your coordinator' statement.

Add a brief example of expected `agt get workers` JSON output so the jq extraction target (`.team`) is verifiable without a live run.

Optionally label the command block's three-step intent (1. fetch your worker, 2. extract Team CR, 3. list team workers) so the workflow sequence is explicit rather than implied by the shell snippet.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence, but the anti-drift warnings ('Do not infer from memory/old chat/task files', 'Do not use teamName from prompts/task files/old chat', 'Do not guess') repeat the same caution three times and could be consolidated.	4 / 5
Actionability	Provides a concrete, copy-paste-ready bash block using the real `agt` CLI with env-var fallback and jq extraction; minor gap is the absence of example output or a second common-case example.	4 / 5
Workflow Clarity	The read-only lookup sequence (get worker -> derive TEAM_CR -> get all workers) is clear and includes error-recovery fallbacks ('If team-scoped queries are denied, ask your coordinator'; 'If required identity... is missing, ask your coordinator'), though validation is fallback-based rather than output-checking.	4 / 5
Progressive Disclosure	Under 50 lines with no need for external references, organized into well-labeled sections ('Source Of Truth', 'What To Use It For'); per the simple-skill exception this earns full marks.	5 / 5
	Total	17 / 20 Passed

Description

80%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 highly complete and distinctive, with an explicit trigger clause and clear boundary guidance. It is slightly held back by jargon-heavy trigger terms and actions that all reduce to a single 'look up' verb.

Dimension	Reasoning	Score
Specificity	Lists several concrete look-up targets ('team topology, worker phase, runtime state, or identity'), giving specific actions beyond a single generic verb; not quite comprehensive coverage of all organizational queries.	4 / 5
Completeness	Explicitly answers both 'what' (look up topology/phase/state/identity) and 'when' ('Use only when you need to look up... that is NOT available from the current message context'), plus an explicit exclusion ('Do not use for standard task flows').	5 / 5
Trigger Term Quality	Keywords ('team topology', 'worker phase', 'runtime state', 'coordinator') are relevant to the domain but lean on technical jargon rather than natural user phrasing, with no synonyms or common variations.	3 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (AgentTeams runtime/identity lookup) with distinct triggers and an explicit 'Do not use for standard task flows' boundary, minimizing conflict risk.	5 / 5
	Total	17 / 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: manager/agent/copaw-worker-agent/skills/organization/SKILL.md
Commit: acaed25

Reviewed: 2 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.