agent-creator
Create and configure AiderDesk agent profiles by defining tool groups, approval rules, subagent settings, and provider/model selection. Use when setting up a new agent, creating a profile, or configuring agent tools and permissions.
95
92%
Does it follow best practices?
Impact
100%
1.28xAverage score across 3 eval scenarios
Passed
No known issues
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong skill description that clearly articulates specific capabilities (creating/configuring AiderDesk agent profiles with detailed sub-features), includes an explicit 'Use when' clause with natural trigger terms, and is highly distinctive due to product-specific terminology. It follows the third-person voice convention and is concise without being vague.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Create and configure AiderDesk agent profiles', 'defining tool groups, approval rules, subagent settings, and provider/model selection'. These are concrete, specific capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (create and configure AiderDesk agent profiles with tool groups, approval rules, subagent settings, provider/model selection) and 'when' (explicit 'Use when setting up a new agent, creating a profile, or configuring agent tools and permissions'). | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'agent profiles', 'tool groups', 'approval rules', 'subagent settings', 'provider/model selection', 'setting up a new agent', 'creating a profile', 'configuring agent tools and permissions'. Good coverage of terms a user would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly specific to AiderDesk agent profiles with distinct triggers like 'agent profiles', 'tool groups', 'approval rules', 'subagent settings'. The product-specific naming ('AiderDesk') and domain-specific terminology make it very unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured skill that provides clear, actionable guidance for creating agent profiles through a defined conversational workflow. Its strengths are the explicit multi-step process, concrete JSON examples, and well-organized references to supporting files. Minor verbosity in the Q&A steps and some repeated instructions prevent a perfect conciseness score.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient but has some redundancy — the Q&A process steps include conversational prompts that pad the content, and some instructions repeat (e.g., 'correct obvious typos only' appears twice, provider/model validation is stated twice). The subagent section could be tighter. | 2 / 3 |
Actionability | Provides concrete JSON structure, specific key formats (three-dash separator), exact file paths, clear approval value options, and a complete minimal config example. The step-by-step Q&A process gives Claude precise instructions on what to ask and when. | 3 / 3 |
Workflow Clarity | Clear 6-step sequential workflow with explicit checkpoints: gather info → propose → review → confirm → create. Includes validation step (Step 6: verify against reference), explicit instruction to avoid per-item confirmations, and conditional logic for Step 3. The validation section provides a clear checklist. | 3 / 3 |
Progressive Disclosure | Excellent structure with a concise overview in the SKILL.md and clear one-level-deep references to schema, subagent guide, examples, tool approval guide, template, and sample profile. References are well-signaled and organized in a dedicated Resources section. | 3 / 3 |
Total | 11 / 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
- hotovo/aider-desk
- Commit
9bcd9bb
- 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.