cursor-agent-supervisor

Offloading tasks with a well-defined scope to sub-agents, for instance to use a sub-agent to implement a set of specs. Use this skill whenever a task should not need a broad knowledge of the whole project

1.59x

Quality

71%

Does it follow best practices?

Impact

91%

1.59x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./cursor-agent-supervisor/SKILL.md

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 is a well-structured, actionable guide with concrete commands, a reusable task template, an explicit verification checklist, and error-recovery feedback loops. It is slightly verbose in a few emphatic passages and could show the create-chat to --resume uuid handoff as a single executable flow.

Dimension	Reasoning	Score
Conciseness	The body is largely lean and actionable with concrete commands, a template, and tight Do/Don't lists, but a few emphatic lines ('YOU are in charge of bookkeeping, not them. YOU have the big picture, they don't.') and the loose 'hack on code, run build/tests, hack on code, etc.' could be trimmed, matching the 'efficient; minor over-explanation' anchor.	4 / 5
Actionability	It provides copy-paste-ready commands (cursor-agent create-chat / --resume, timeout: 600000) and a concrete task template with a default model (sonnet-4.5), but the Do/Don't and 'Setting things up' sections remain partly advisory and the real uuid handoff between create-chat and --resume is not shown as one executable flow, leaving minor gaps.	4 / 5
Workflow Clarity	The process is clearly sequenced (create chat -> give task with long timeout -> prepare -> instruct -> verify -> handle failures) with an explicit verification checklist ('Check what changed', 'Review the actual code', 'Run verification commands') and feedback loops ('Fails... Read the output, fix any blocking issues, retry'), matching the anchor for explicit validation steps plus error-recovery loops.	5 / 5
Progressive Disclosure	The body is well-organized into clearly headed sections with easy navigation and no nested-reference anti-pattern, and being instruction-only with no bulk API material it needs no external files; at ~95 lines with a sizable inline template block it is good structure with minor organization gaps rather than the ideal split-overview level.	4 / 5
	Total	17 / 20 Passed

Description

62%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 clearly states both what the skill does and when to use it with an explicit 'Use this skill whenever...' trigger, and stays in third person. It is somewhat abstract and would benefit from more concrete action enumeration and additional natural trigger synonyms.

Suggestions

List 2-3 more concrete actions (e.g., 'delegate a well-scoped coding task', 'spawn a sub-agent to implement a spec', 'run an isolated change in parallel') to lift specificity.

Add natural trigger synonyms users would actually say, such as 'delegate', 'spawn a subagent', or 'parallelize', alongside 'offloading'.

Expand the 'when' clause with a second concrete trigger phrase (e.g., 'or when you want to isolate a self-contained change from the rest of the project') to reach explicit multi-trigger completeness.

Dimension	Reasoning	Score
Specificity	It names the domain ('offloading tasks with a well-defined scope to sub-agents') and one concrete action ('implement a set of specs'), but does not enumerate several specific actions, matching the 'domain and 1-2 concrete actions' anchor rather than the 'lists several specific actions' anchor above.	3 / 5
Completeness	It explicitly answers both what ('Offloading tasks... to sub-agents') and when ('Use this skill whenever a task should not need a broad knowledge of the whole project'), but the 'when' offers a single trigger condition rather than multiple concrete trigger phrases, so it is not the level-5 anchor.	4 / 5
Trigger Term Quality	It includes relevant keywords like 'sub-agents', 'offloading tasks', and 'specs', but misses common natural synonyms users would actually say such as 'delegate', 'spawn', or 'parallelize', fitting the 'some relevant keywords but missing common variations' anchor.	3 / 5
Distinctiveness Conflict Risk	The sub-agent supervision niche is mostly distinct and the 'should not need a broad knowledge of the whole project' trigger is fairly specific, though there is minor overlap risk with other agent-orchestration or delegation skills.	4 / 5
	Total	14 / 20 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: YPares/agent-skills
Path: cursor-agent-supervisor/SKILL.md
Commit: e9d2149

Reviewed: 3 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.