task-coordination

Coordinate access to shared task directories using .processing marker files. Use before accessing a Worker's workspace to prevent conflicts when both Manager and Worker might modify files simultaneously.

Quality

73%

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/skills/task-coordination/SKILL.md

Quality

Content

75%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 with a clear sequenced protocol and real backing scripts, losing points mainly to redundant restatement of the script commands and a missing recovery path when a marker is active.

Suggestions

Collapse the 'Scripts' section into a short reference table (script, args, exit codes) and remove the command blocks already shown in the protocol to cut redundancy.

Add a brief recovery step for the active-marker case (e.g., wait for expiration, then re-check) so the workflow has an explicit feedback loop.

Trim the 'Best Practices' list to items not already implied by the numbered protocol.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with no generic concept padding, but the 'Scripts' section restates the same commands already shown in the 'Coordination Protocol', and 'Best Practices' partly reiterates the protocol steps.	3 / 5
Actionability	Fully executable guidance: copy-paste bash commands with absolute paths, a concrete marker JSON format, exit-code semantics, and three real scripts in the bundle that match the referenced paths.	5 / 5
Workflow Clarity	A clear 6-step sequence with a validation checkpoint (check marker, exit 1 = do not modify); the gap is that it states 'do NOT modify' but gives no retry/backoff guidance for the active-marker case.	4 / 5
Progressive Disclosure	Well-organized sections with the protocol and marker format inline and script implementations correctly offloaded to one-level-deep files in scripts/; minor gap is the duplicated script-usage block.	4 / 5
	Total	16 / 20 Passed

Description

71%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 clearly answers both what and when with a concrete trigger clause and a distinct mechanism, but its action list and natural-language trigger terms are narrower than top-tier examples.

Suggestions

Broaden the action list beyond 'Coordinate access' to the concrete operations (check, create, remove the .processing marker) for higher specificity.

Add user-natural trigger phrasing (e.g., 'Use when multiple agents might edit the same task workspace at the same time') alongside the Manager/Worker jargon.

Dimension	Reasoning	Score
Specificity	Names the domain ('shared task directories') and a concrete mechanism ('.processing marker files') plus the action 'Coordinate access', but coverage is limited to one coordination action rather than a comprehensive list.	3 / 5
Completeness	It explicitly states what ('Coordinate access to shared task directories using .processing marker files') and gives a concrete 'Use before accessing a Worker's workspace...' trigger phrase with the conflict scenario.	5 / 5
Trigger Term Quality	Relevant terms like 'task directories', '.processing marker', and 'conflicts' appear, but the phrasing leans on internal jargon ('Worker's workspace', 'Manager') and lacks common synonyms a user would naturally say.	3 / 5
Distinctiveness Conflict Risk	The .processing marker mechanism and Manager/Worker coordination form a distinct niche, with only minor overlap risk against general task-management skills.	4 / 5
	Total	15 / 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/skills/task-coordination/SKILL.md
Commit: 223ddc2

Reviewed: 13 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.