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
79
70%
Does it follow best practices?
Impact
91%
1.59xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./cursor-agent-supervisor/SKILL.mdQuality
Discovery
40%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 conveys the general idea of delegating scoped tasks to sub-agents but lacks specificity in both capabilities and trigger conditions. The 'when' clause is present but too abstract to reliably guide skill selection. It would benefit from concrete examples of task types and more natural trigger terms.
Suggestions
Add specific concrete actions the sub-agent performs, e.g., 'Delegates implementation of well-scoped coding tasks, test writing, or file transformations to sub-agents that execute independently.'
Improve trigger terms by including natural phrases users would say, such as 'delegate', 'subtask', 'run in parallel', 'spawn agent', 'break this into smaller tasks'.
Make the 'Use when' clause more explicit with concrete scenarios, e.g., 'Use when the user asks to delegate a self-contained task, implement a spec, or when a task can be completed without needing full project context.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description uses vague language like 'offloading tasks' and 'implement a set of specs' without listing concrete actions. It doesn't specify what kinds of tasks, what tools are used, or what the sub-agent mechanism actually does. | 1 / 3 |
Completeness | It provides a weak 'what' (offloading tasks to sub-agents) and a vague 'when' ('whenever a task should not need a broad knowledge of the whole project'). The 'when' clause exists but is imprecise and doesn't provide explicit trigger scenarios. | 2 / 3 |
Trigger Term Quality | It includes some relevant terms like 'sub-agent' and 'specs' that a user might mention, but misses common variations like 'delegate', 'parallel tasks', 'subtask', 'spawn agent', or 'break down work'. The term 'well-defined scope' is more of a qualifier than a trigger term. | 2 / 3 |
Distinctiveness Conflict Risk | The concept of sub-agents is somewhat distinctive, but the description is broad enough ('offloading tasks') that it could overlap with any task delegation, orchestration, or workflow management skill. The scope criterion ('should not need broad knowledge') is subjective and hard to distinguish on. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
100%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is an excellent skill file that is concise, actionable, and well-structured. It provides concrete commands, a useful task template, clear workflow sequencing with validation checkpoints, and error recovery guidance—all without unnecessary verbosity or explaining concepts Claude already understands.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient. It doesn't explain what sub-agents are conceptually or waste tokens on things Claude already knows. Every section provides specific, actionable information—commands, templates, checklists—without padding. | 3 / 3 |
Actionability | Provides fully executable commands (cursor-agent with flags), a concrete task description template with fill-in-the-blank structure, specific timeout values, and clear do/don't lists. The guidance is copy-paste ready and immediately usable. | 3 / 3 |
Workflow Clarity | The workflow is clearly sequenced: setup (prepare the revision) → invoke sub-agent (with timeout) → give instructions (with template) → verify results (check diff, review code, run tests, update status). The 'After Sub-agent Completes' section provides explicit validation steps, and 'When Things Go Wrong' provides error recovery/feedback loops. | 3 / 3 |
Progressive Disclosure | For a standalone skill with no bundle files, the content is well-organized into logical sections (Model Selection, Invocation, Setup, Instructions, After Completion, Error Handling) that progressively build on each other. The structure is clear and navigable without being monolithic. | 3 / 3 |
Total | 12 / 12 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 — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- YPares/agent-skills
- Commit
84b1da5
- 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.