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.
91
87%
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 excellent trigger terms and clear completeness, explicitly covering both what the skill does and when to use it. Its main weakness is that the capability description could be more specific about the concrete actions performed (e.g., comparing agents, explaining tradeoffs, matching tasks to tools). The meta-level nature of the skill gives it strong distinctiveness.
Suggestions
Add more specific concrete actions beyond 'recommend', such as 'compare agent capabilities, explain tradeoffs between Task and Skill tools, match user tasks to appropriate tools'.
| 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 | The description 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-defined. | 3 / 3 |
Trigger Term Quality | The description 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 skill occupies a clear meta-level niche — it's about choosing other tools/agents rather than performing a domain task. The trigger terms ('which agent', 'recommend agent', 'help me choose') are distinct and unlikely to conflict with skills that actually perform tasks. | 3 / 3 |
Total | 11 / 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-crafted discovery/recommendation skill that efficiently uses tables and a decision flowchart to guide tool selection. It's concise, well-organized with progressive disclosure to detailed catalogs, and appropriate for its purpose as a lookup/routing skill. The only minor weakness is that the launch examples could be slightly more concrete with complete parameter examples.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every section is lean and purposeful. No unnecessary explanations of what agents or skills are conceptually—jumps straight to decision criteria and lookup tables. The ASCII flowchart is minimal yet effective. | 3 / 3 |
Actionability | The tables and flowchart provide concrete guidance for choosing tools, and the 'How to Launch' section shows invocation syntax. However, the launch examples are somewhat pseudocode-like (not fully executable with all required parameters), and the matching table is helpful but limited in scope. | 2 / 3 |
Workflow Clarity | For a recommendation/lookup skill, the workflow is clear and unambiguous: follow the decision flowchart, match against tables, then launch using the provided syntax. This is a single-purpose skill where the decision tree serves as the workflow, and it's well-sequenced. | 3 / 3 |
Progressive Disclosure | The skill provides a concise overview with quick-reference tables inline, then clearly points to one-level-deep references (agents-catalog.md and skills-catalog.md) for complete details. Navigation is well-signaled and appropriately structured. | 3 / 3 |
Total | 11 / 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
9f4534c
- 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.