CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

teamharness-task-delegation

Use when you act as Leader to turn ready Quick Task or Project Work state into Worker task instructions, send assignment messages, check submitted results, and define completion/blocker report contracts. Do not use to create projects, create rooms, or execute Worker tasks.

Quality

89%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

81%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 delivers fully executable, well-sequenced Leader instructions with explicit validation and error-recovery paths. Its main weakness is redundancy: the auto-notify rule and the completion-report template each appear multiple times, and two sections overlap substantially.

Suggestions

State the "delegate_task auto-notifies — do not send a second mention" rule once (in Assignment Message) and reference it from the other two places instead of repeating it in Before delegation step 6 and Post-Action Notification.

Keep the completion-report template in one place (the Task Spec Completion Report section) and shorten the JSON delegate_task example's embedded spec to a summary pointing at that template.

Merge the overlapping Assignment Message and Post-Action Notification sections into one notification section covering both the auto-notify and the manual create_quick_project follow-up cases.

DimensionReasoningScore

Conciseness

The body is mostly efficient domain-specific instruction, but the "delegate_task auto-notifies — do not send a second mention" rule is stated three times (Before delegation step 6, Assignment Message, Post-Action Notification) and the completion-report template is duplicated inside the JSON spec example and again as a standalone block. This fits 'mostly efficient but could be tightened' rather than anchor 2, since the padding is repetition of genuinely important rules rather than generic explanation.

3 / 5

Actionability

Guidance is fully executable: copy-paste-ready JSON payloads for delegate_task and check_task, exact message templates with placeholders ("@worker-a:matrix.local TASK_ASSIGNED: ..."), exact paths (shared/tasks/{task-id}/result.md), enumerated accepted statuses, and explicit decision rules for effective/submissionId. Matches the copy-paste-ready anchor; not 4 because common cases are concretely covered with no material gaps.

5 / 5

Workflow Clarity

The multi-step process is clearly sequenced (roster resolution, readyNodes confirmation, bounded spec, assignment, check, acceptance) with explicit validation checkpoints and a feedback loop ("If effective is false, do not accept the task. Tell the Worker what is missing and wait for a corrected result"), plus notificationNeeded and submissionId checkpoints. This matches the explicit-validation-with-error-recovery anchor rather than the minor-gaps anchor 4.

5 / 5

Progressive Disclosure

The single-file skill is well organized with clear section headers and clearly signaled cross-skill pointers (teamharness-project-management, teamharness-roomflow, teamharness-task-execution) each stated with its purpose, and no bundle files exist to verify or traverse. It is not 5 because at ~210 lines the under-50-line exception does not apply and the overlapping Assignment Message / Post-Action Notification sections are a minor organization gap; it is above anchor 3 since nothing that belongs in a separate file is inlined and navigation is easy.

4 / 5

Total

17

/

20

Passed

Description

92%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.

A strong description: concrete actions, an explicit 'Use when' trigger tied to the Leader role, and clear negative boundaries against sibling skills. The only weakness is keyword coverage that misses a few natural synonyms such as 'delegate'.

DimensionReasoningScore

Specificity

The description lists four concrete actions covering the full delegation lifecycle — "turn ready Quick Task or Project Work state into Worker task instructions", "send assignment messages", "check submitted results", "define completion/blocker report contracts" — which matches the comprehensive multi-action anchor; it is not 4 because coverage relative to the skill's scope has no gaps.

5 / 5

Completeness

It explicitly answers both questions: a multi-action "what" and a concrete trigger clause "Use when you act as Leader to turn ready Quick Task or Project Work state into..." plus a negative boundary ("Do not use to create projects, create rooms, or execute Worker tasks"). This clearly matches the anchor where both what and when are explicit with concrete triggers, not the weaker-'when' anchor 4.

5 / 5

Trigger Term Quality

Natural domain terms a Leader user would say are present ("Leader", "Worker task", "Quick Task", "Project Work", "assignment messages", "completion/blocker report"), but a few common variations such as "delegate/delegation" are missing, fitting good-but-not-comprehensive keyword coverage rather than anchor 5's synonym-level coverage.

4 / 5

Distinctiveness Conflict Risk

The explicit negative scope ("Do not use to create projects, create rooms, or execute Worker tasks") carves a clear niche against sibling skills, and the Leader-role trigger is distinct, so conflict risk is minimal — the anchor-5 case rather than the minor-overlap anchor 4.

5 / 5

Total

19

/

20

Passed

Validation

100%

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

Reviewed

Table of Contents

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.