task-management

Use when admin gives a task to delegate to a Worker, when a Worker reports task completion, when managing recurring scheduled tasks, or when you need to check worker availability.

Quality

80%

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-management/SKILL.md

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, highly actionable, and models progressive disclosure well with a verified reference table. Its only real gap is workflow clarity: the body states guardrails but defers validation steps for its riskier operations to the bundled scripts and reference docs.

Suggestions

Add a short numbered delegation workflow in the body with an explicit validation checkpoint (e.g. '1. select Worker → 2. register in state.json via manage-state.sh → 3. verify entry exists → 4. push to MinIO → 5. notify') so the risky auto-stop flow has an inline verify step.

State the verification the body currently assumes from manage-state.sh (e.g. 'confirm the task appears in state.json before notifying') so readers don't have to infer it.

Dimension	Reasoning	Score
Conciseness	Punchy imperative Gotchas with brief consequence notes and a tight situation→file routing table that assumes Claude's competence; every token earns its place with no padding or explanation of known concepts.	3 / 3
Actionability	Concrete directives reference specific tools and artifacts ('manage-state.sh', 'find-skills', 'state.json', MinIO, 'SOUL.md') with exact ordering ('push task files to MinIO before notifying', 'pull task directory from MinIO before reading results'), which is actionable instruction-only guidance.	3 / 3
Workflow Clarity	The routing table sequences behavior and warns against loading everything, but the body delegates verification to scripts/references and lacks an explicit in-body validation checkpoint for the risky auto-stop-on-missing-registration flow, so checkpoints are implicit rather than stated.	2 / 3
Progressive Disclosure	A concise overview body points to one-level-deep references via a well-signaled table ('Read the relevant doc before executing. Do not load all of them.'), and all four referenced reference files exist, giving clear easy navigation.	3 / 3
	Total	11 / 12 Passed

Description

72%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 has strong, natural trigger coverage and a clear niche, but it over-relies on 'when' clauses and never states what the skill actually does, leaving the 'what' implicit. Adding a leading action clause would lift completeness and specificity.

Suggestions

Lead with the action: e.g. 'Delegates tasks to Workers, registers them in state.json, and manages recurring scheduled tasks. Use when...' so the 'what' is explicit, not implied.

Add a concrete action verb per situation (e.g. 'register', 'schedule', 'check availability') so specificity moves beyond pure triggers.

Dimension	Reasoning	Score
Specificity	Names four concrete triggering situations ('delegate to a Worker', 'reports task completion', 'recurring scheduled tasks', 'check worker availability') but describes the skill entirely through triggers rather than stating the concrete actions it performs, so it is not comprehensive enough for a 3.	2 / 3
Completeness	An explicit 'Use when...' clause covers the 'when' well, but the 'what' (what the skill actually does — delegate/register/track) is only implied through the triggers rather than clearly stated, so it does not fully answer both.	2 / 3
Trigger Term Quality	Phrases like 'admin gives a task to delegate', 'Worker reports task completion', 'recurring scheduled tasks', and 'check worker availability' are the natural terms a user of this system would say, giving good coverage across all four scenarios.	3 / 3
Distinctiveness Conflict Risk	The Worker-delegation, recurring-task, and availability-check niche is distinctive with triggers tied to a specific domain, making it unlikely to fire for the wrong skill.	3 / 3
	Total	10 / 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: manager/agent/skills/task-management/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.