teamharness-task-delegation

Use when a Leader turns ready Quick Task or Project Work state into Worker task instructions, sends assignment messages, checks submitted results, and defines completion/blocker report contracts. Do not use to create projects, create rooms, or execute Worker tasks.

Quality

81%

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

77%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.

A highly actionable, well-sequenced skill body with executable JSON payloads and an explicit validation feedback loop for checking submitted results. Its weaknesses are conciseness (verbatim duplication of the completion-report block) and progressive disclosure (everything inline with no reference files to offload detail).

Suggestions

Remove the verbatim duplicate of the Completion Report block — keep it once in the 'Task Spec Completion Report' section and reference it from the delegate_task spec example instead of embedding the full text twice.

Split the stable detail (full result-contract format, completion-report templates, post-action notification protocol) into reference files under references/ and link to them from the body to improve progressive disclosure and reduce inline length.

Consolidate the recurring notification guidance so the assignment-message and notification rules are stated once rather than revisited across 'Assignment Message' and 'Post-Action Notification'.

Dimension	Reasoning	Score
Conciseness	The body is dense and free of concept-explanation padding, but the Completion Report block is duplicated verbatim (embedded in the delegate_task spec and restated in its own section) and notification guidance recurs across sections, so it 'could be tightened'; not 3 due to the duplication, not 1 because it is not padded with concepts Claude already knows.	2 / 3
Actionability	Provides complete, copy-paste-ready taskflow JSON payloads, exact file paths (shared/tasks/{task-id}/meta.json, spec.md), a ready assignment-message template, and a concrete STATUS/SUMMARY/DELIVERABLES result contract; fully executable; not 2 because it is concrete and complete rather than pseudocode.	3 / 3
Workflow Clarity	Sequences delegate→assign→check→accept with an explicit validation checkpoint ('If effective is false, do not accept... wait for a corrected result') forming a validate→fix→retry loop, plus a numbered pre-delegation checklist; not 2 because checkpoints are explicit rather than implicit.	3 / 3
Progressive Disclosure	Clear section headers give structure, but with no bundle/reference files present, the full result-contract spec, completion-report templates, and notification protocol all live inline in a single ~185-line file; content that should be separate is inline; not 3 because there are no well-signaled one-level-deep references, not 1 because it is organized rather than a monolithic wall or nested refs.	2 / 3
	Total	10 / 12 Passed

Description

85%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.

A strong, specific description with an explicit trigger and clear negative-scope boundaries that distinguish it from adjacent team-harness skills. Its main weakness is trigger-term quality: the phrasing relies on internal system vocabulary rather than the plain-language variations a user would naturally say.

Suggestions

Add plain-language trigger terms a leader would naturally say (e.g., 'delegate a task', 'assign work to a Worker', 'review a Worker's submitted result') alongside the existing 'Project Work state' / 'Quick Task' framing.

Consider listing a couple of common variation phrases (assigning tasks, sending task assignments, checking task results) to broaden natural keyword coverage.

Dimension	Reasoning	Score
Specificity	Enumerates four concrete actions — 'turns ready... state into Worker task instructions', 'sends assignment messages', 'checks submitted results', 'defines completion/blocker report contracts' — matching the multiple-specific-actions anchor; not 2 because it is comprehensive rather than naming only a domain and a couple actions.	3 / 3
Completeness	An explicit 'Use when a Leader turns ready...' clause gives the trigger while the action list gives the 'what', plus a 'Do not use to...' negative scope; clearly answers both what and when; not 2 because the 'when' is explicit rather than merely implied.	3 / 3
Trigger Term Quality	Relevant delegation verbs (assign, check, report) are present but framed in internal jargon ('Project Work state', 'completion/blocker report contracts') rather than plain variations a user would naturally say, so it sits at 'some relevant keywords but missing common variations'; not 3 because the term set leans on system vocabulary over natural phrasing.	2 / 3
Distinctiveness Conflict Risk	The 'Do not use to create projects, create rooms, or execute Worker tasks' clause carves out a clear Leader-side delegation niche against named sibling skills, making wrong-skill triggering unlikely; not 2 because it actively disambiguates rather than only being 'somewhat specific'.	3 / 3
	Total	11 / 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/task-delegation/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.