tool-discovery
Recommend the right agents and skills for any task. Covers both heavyweight agents (Task tool) and lightweight skills (Skill tool). Triggers on: which agent, which skill, what tool should I use, help me choose, recommend agent, find the right tool.
88
83%
Does it follow best practices?
Impact
100%
5.26xAverage score across 3 eval scenarios
Passed
No known issues
Quality
Discovery
89%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 solid description with strong trigger terms and clear completeness. Its main weakness is that the 'what' portion could be more specific about the concrete actions performed (e.g., comparing agents, explaining tradeoffs, listing available tools). The explicit trigger clause and distinct meta-skill niche are notable strengths.
Suggestions
Add more specific concrete actions beyond 'recommend', such as 'compare agent capabilities, explain tradeoffs between Task and Skill tools, list available tools for a given domain'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain (recommending agents and skills) and distinguishes between heavyweight agents (Task tool) and lightweight skills (Skill tool), but doesn't list multiple concrete actions beyond 'recommend'. It lacks specifics like 'compare capabilities', 'explain tradeoffs', or 'suggest configurations'. | 2 / 3 |
Completeness | Clearly answers both 'what' (recommend the right agents and skills, covering Task tool and Skill tool) and 'when' (explicit 'Triggers on:' clause with multiple trigger phrases). The trigger guidance is explicit and well-structured. | 3 / 3 |
Trigger Term Quality | Includes a good set of natural trigger phrases: 'which agent', 'which skill', 'what tool should I use', 'help me choose', 'recommend agent', 'find the right tool'. These closely match what users would naturally say when seeking guidance on tool/agent selection. | 3 / 3 |
Distinctiveness Conflict Risk | This is a meta-skill about recommending other tools/agents, which is a clear and distinct niche. The trigger terms are specific to tool/agent selection and unlikely to conflict with the actual domain-specific skills it recommends. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
77%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, concise tool discovery skill that efficiently maps tasks to the right tools using compact tables and a clear decision flowchart. Its main weakness is that the invocation examples are schematic rather than fully executable, and the referenced catalog files are not provided in the bundle. Overall it serves its purpose as a quick-reference recommendation guide effectively.
Suggestions
Make the 'How to Launch' examples more concrete and executable—show actual tool call syntax with realistic parameters rather than arrow notation.
Include the referenced bundle files (agents-catalog.md, skills-catalog.md) or remove the references if they don't exist.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every token earns its place. The decision flowchart is minimal, tables are compact, and there's no explanation of what agents or skills are conceptually—it assumes Claude already knows. No padding or unnecessary context. | 3 / 3 |
Actionability | The tables provide concrete mappings from triggers to tools, and the 'How to Launch' section shows invocation syntax. However, the launch examples are somewhat schematic rather than fully executable (e.g., 'Skill tool → skill: "file-search"' is not a real command), and there's no complete worked example of a recommendation flow. | 2 / 3 |
Workflow Clarity | The decision flowchart provides a clear sequence for choosing between skills and agents. The 'Match by Task Type' table acts as a validation checkpoint showing when to escalate from skill to agent. For this type of recommendation/lookup skill (single decision task), the workflow is unambiguous and complete. | 3 / 3 |
Progressive Disclosure | The skill references './references/agents-catalog.md' and './references/skills-catalog.md' for deeper content, which is good one-level-deep disclosure. However, no bundle files were provided, so these references are unverifiable. The inline tables are appropriately concise for an overview, but the references section feels tacked on rather than well-integrated into the flow. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- NeverSight/skills_feed
- Commit
25d5403
- 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.