CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

teamharness-task-execution

Use when you act as Worker: receive TASK_ASSIGNED, acknowledge the task, work inside shared/tasks/{task-id}/, submit with taskflow submit_task, publish deliverables through submit_task, and report TASK_COMPLETED or blockers in the Task room.

Quality

88%

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

77%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 highly actionable, well-sequenced protocol guidance with concrete JSON examples and strong validation/recovery checkpoints. Its weaknesses are density and monolithic structure: deep edge-case semantics that belong in one-level-deep reference files are inlined, making the skill longer than the core workflow needs.

Suggestions

Move the submission-identity, digest, retry-conflict, and legacy-task adoption semantics out of the Submit section into a reference file (e.g., references/submission-protocol.md), keeping only the core submit/retry rules in SKILL.md.

Extract the 'Coding CLI runs (when used)' sub-workflow into its own reference file, since it is a niche case that interrupts the main Worker flow.

Tighten the conclusions paragraph to the essential rule (3-5 one-line strings) and move the strict-mode, first-5 truncation, and digest-exclusion details into the same reference file.

DimensionReasoningScore

Conciseness

The body avoids generic concept explanations (all rules are bespoke protocol detail), but the Submit section carries heavy edge-case density (digest composition, AGENTTEAMS_TASK_CONCLUSIONS_STRICT, legacy-task adoption, byte-identical event format) that could be tightened or trimmed. Fits the 3 anchor (mostly efficient, some tightening possible) rather than 4, since several paragraphs exceed what the core workflow requires.

3 / 5

Actionability

Fully executable guidance throughout: copy-paste-ready JSON payloads for ack_task and submit_task, exact path templates, the complete status enum, exact first-line completion formats, and concrete field specs for request_attention (kind, question, options, suggested, expiresAt). Matches the 5 anchor's copy-paste-ready coverage of common cases.

5 / 5

Workflow Clarity

The multi-step process is clearly sequenced (acknowledge → read spec → execute with progress reports → submit → completion event) with explicit validation checkpoints and error-recovery loops: "confirm the acknowledgment reached shared storage (synced: true)", ack failure → report blocker instead of inventing files, sync interruption → exact-retry rules, and "Check publishedArtifacts in the tool result". Matches the 5 anchor's explicit validation steps and feedback loops.

5 / 5

Progressive Disclosure

Sections are well organized with clear headers, but the skill is a single ~260-line file with no bundle references, and substantial edge-case material (submission identity/digest/legacy semantics, conclusions corner rules, the coding-CLI sub-workflow) is inlined where reference files would be appropriate. Fits the 3 anchor (content that should be separate is inline); not 2 because the structure is far from minimal, and not 4 because there are no references at all to offload detail.

3 / 5

Total

16

/

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.

The description is a strong, protocol-specific trigger: it states an explicit when (act as Worker on TASK_ASSIGNED) and enumerates the full lifecycle of concrete actions with exact paths, commands, and event tokens. Its only weakness is slightly thin synonym/variation coverage of trigger terms.

Suggestions

Add a few natural trigger variations such as the BLOCKED status, report_progress, or phrasings like "assigned task" to broaden keyword coverage.

Remove the redundancy of mentioning submit_task twice ("submit with taskflow submit_task, publish deliverables through submit_task") to tighten the description.

DimensionReasoningScore

Specificity

"receive TASK_ASSIGNED, acknowledge the task, work inside shared/tasks/{task-id}/, submit with taskflow submit_task, publish deliverables through submit_task, and report TASK_COMPLETED or blockers" lists multiple concrete actions covering the complete worker lifecycle (receive, acknowledge, work, submit, publish, report). This matches the 5 anchor's comprehensive concrete coverage rather than 4, which expects minor gaps.

5 / 5

Completeness

"Use when you act as Worker: receive TASK_ASSIGNED" explicitly answers when with a concrete trigger event, and the enumerated actions explicitly answer what. This matches the 5 anchor (both what and when clearly and explicitly stated with concrete trigger phrases); 4 would require the when to be less specific.

5 / 5

Trigger Term Quality

Key trigger tokens are present ("TASK_ASSIGNED", "Worker", "taskflow submit_task", "TASK_COMPLETED", "Task room") and would naturally occur when this skill is needed, but a few natural terms are missing (e.g., BLOCKED status, report_progress, generic phrasings like "assigned task"). Good coverage with minor omissions fits the 4 anchor, below 5's comprehensive synonym coverage.

4 / 5

Distinctiveness Conflict Risk

Highly specific protocol tokens (TASK_ASSIGNED, taskflow, shared/tasks/{task-id}/, Task room) establish a clear niche with essentially no overlap risk against generic skills. Matches the 5 anchor's distinct triggers and minimal conflict risk.

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-execution/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.