task-management

Use before any Leader taskflow call or task-level workflow involving delegating a ready DAG or Loop node, writing task meta/spec, checking a Worker task result, handling result statuses, task directory ownership, or Worker result contracts. Always use this skill when the request mentions delegate_task, check_task, task result.md, task spec.md, BLOCKED, REVISION_NEEDED, INTERRUPTED, SUCCESS, or assigning/delegating a Worker task.

Quality

96%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

92%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 clearly sequenced, validation-gated workflows and concrete tool payloads. The main weakness is progressive disclosure: the one reference file duplicates inline content instead of extending it, and a lot of detail lives inline in SKILL.md.

Suggestions

Make references/dag-tasks.md extend rather than duplicate the body — move the detailed delegation/completion step-by-step into the reference and keep SKILL.md as a tight overview pointing to it.

Trim the repeated delegate_task/check_task JSON payloads in the body to one canonical example each, referencing the detail file for the full flow.

Consider splitting the Worker Name Canonicality lookup (bash + table) into its own reference so the core delegation/check loop stays scannable.

Dimension	Reasoning	Score
Conciseness	The body is dense operational protocol — exact paths, tool actions, and field names — with no padding explaining concepts Claude already knows; every section earns its place. It is long but not verbose.	3 / 3
Actionability	Provides fully executable concrete guidance: JSON taskflow payloads with exact fields, a copy-paste bash `agt get workers` lookup, exact deliverable paths, and tables mapping statuses and plan markers — copy-paste ready.	3 / 3
Workflow Clarity	Delegation and checking flows are explicit numbered sequences with validation checkpoints — 'If the Project is paused, stop', blocking directory pulls that 'stop and report the sync failure', and 'do not mark [x] just because the Worker wrote SUCCESS' — with clear feedback loops.	3 / 3
Progressive Disclosure	There is a single, real, one-level-deep reference ('references/dag-tasks.md') signaled with 'Read only when needed', but the body is a long monolithic block and the reference largely duplicates inline content rather than splitting detail out — content that could be separate is inline.	2 / 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 explicitly answers both what and when, with a clear distinct niche. It uses the imperative 'Use when...' form consistent with the good examples rather than first/second-person voice that would be penalized.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions — 'delegating a ready DAG or Loop node', 'writing task meta/spec', 'checking a Worker task result', 'handling result statuses', 'task directory ownership', 'Worker result contracts' — matching the score-3 anchor.	3 / 3
Completeness	Explicitly answers both what (Leader taskflow calls and task-level workflows) and when ('Use before any Leader taskflow call...' and 'Always use this skill when the request mentions...'), with an explicit 'Use when' clause.	3 / 3
Trigger Term Quality	Covers natural trigger terms a user would actually say — 'delegate_task', 'check_task', 'task result.md', 'task spec.md', 'BLOCKED', 'REVISION_NEEDED', 'INTERRUPTED', 'SUCCESS', 'assigning/delegating a Worker task' — with good coverage of variations.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (individual Worker task delegation/result checks) with distinct protocol tokens unlikely to trigger for adjacent skills like team-coordination or project-management.	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: manager/agent/team-leader-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.