CtrlK
BlogDocsLog inGet started
Tessl Logo

task-management

Use before any Worker taskflow call or assigned-task workflow, including reading task state, acknowledging a task, executing a task, tracking progress, handling blockers/questions, submitting structured results, or reporting completion. Always use this skill when the message mentions assigned task, task ID, shared/tasks, spec.md, meta.json, result.md, deliverables, BLOCKED, REVISION_NEEDED, SUCCESS, submit_task, or ack_task.

75

Quality

92%

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

85%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 content is a tight, executable protocol with concrete JSON payloads, exact paths, and explicit error/assignment checks. It is well-organized for a short single-purpose skill and avoids padding, with only minor conciseness trimming and an optional final verification step suggested.

Suggestions

Tighten the ack_task description to avoid restating the call's internal mechanics (e.g. 'pulls the task directory from storage, reads spec.md and meta.json...') since the JSON example already conveys the action.

Add an explicit post-submit verification step in the main success flow (parallel to the BLOCKED path's 'verifies result.md exists'), so the happy path has the same feedback-loop rigor as the error paths.

Consider collapsing the repeated @coordinator mention templates into a single format reference to reduce token usage across the success and blocked sections.

DimensionReasoningScore

Conciseness

The body is mostly lean and avoids explaining concepts Claude already knows, but a few sentences (e.g. 'This single call pulls the task directory from storage, reads spec.md and meta.json, acknowledges the task, and pushes the acknowledged status back to storage') restate mechanics that could be trimmed slightly.

4 / 5

Actionability

It provides fully copy-paste-ready JSON payloads for ack_task and submit_task, exact path templates, and the literal completion message format, covering the common cases concretely and executably.

5 / 5

Workflow Clarity

The execution flow is a clear numbered sequence with explicit validation/error checkpoints (assignment mismatch, missing room_id, verification that result.md exists), but progress tracking and the success path lack a final explicit verification feedback loop, leaving minor gaps.

4 / 5

Progressive Disclosure

The body is under 50 lines with no external references needed, organized into clearly headed sections (Task Directory, Execution Flow, Blocked, Progress), so the simple-skill exception applies and structure scores full.

5 / 5

Total

18

/

20

Passed

Description

100%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 exemplary: it concisely covers the full task lifecycle, provides explicit use-when triggers with both natural phrases and technical tokens, and is clearly scoped to the Worker/taskflow domain. It is somewhat long but the density is justified by comprehensive trigger coverage.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions (reading task state, acknowledging, executing, tracking progress, handling blockers, submitting structured results) referencing named APIs, giving comprehensive coverage of the skill's capabilities.

5 / 5

Completeness

It explicitly states what the skill does (the full task lifecycle) and when to use it via 'Use before any Worker taskflow call...' and 'Always use this skill when the message mentions...', answering both what and when with concrete triggers.

5 / 5

Trigger Term Quality

It enumerates natural trigger phrases a user would say including 'assigned task', 'task ID', 'shared/tasks', 'spec.md', 'meta.json', 'BLOCKED', 'REVISION_NEEDED', 'SUCCESS', 'submit_task', and 'ack_task', covering synonyms, file names, and API call names.

5 / 5

Distinctiveness Conflict Risk

The triggers are highly specific to the Worker/taskflow domain (task IDs, shared/tasks paths, ack_task/submit_task actions), creating a clear niche with minimal overlap risk against other skills.

5 / 5

Total

20

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
agentscope-ai/AgentTeams
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.