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.

5.26x

Quality

—

Does it follow best practices?

Impact

100%

5.26x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Quality

Content

92%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A lean, highly actionable reference skill with a clear decision flowchart and concrete invocation guidance. Its one real defect is progressive disclosure: it directs Claude to load catalog files (./references/*.md) that are not present in the bundle.

Suggestions

Create the referenced ./references/agents-catalog.md and ./references/skills-catalog.md files (or remove the 'Additional Resources' section) so the signaled one-level-deep references resolve instead of pointing to non-existent files.

If the catalogs are intentionally not bundled, replace the file-load instruction with a note that the in-body quick-reference tables are the complete set, so Claude does not attempt to load missing files.

Verify each named skill (e.g. file-search, sql-patterns) and agent (e.g. python-expert, sql-expert) actually exists in the environment, since the recommendations cannot be validated against the missing catalogs.

Dimension	Reasoning	Score
Conciseness	The body is a dense, tabular reference with a compact decision flowchart and no padding explaining concepts Claude already knows; every section (flowchart, quick-reference tables, launch syntax, match-by-task, tips) earns its place, matching the lean score-3 anchor.	3 / 3
Actionability	It gives concrete, specific guidance: exact tool + parameter invocation syntax ('Skill tool → skill: "file-search"', 'Task tool → subagent_type: "python-expert"') and a match-by-task table naming exact skill/agent identifiers per task, which is fully actionable for an instruction skill per the code_vs_instruction scoring note.	3 / 3
Workflow Clarity	The decision flowchart provides a clear, sequenced branching process (reference? → SKILL; needs reasoning? → AGENT; maybe → catalogs) and the match-by-task table reinforces it; as a single-purpose recommendation skill with no destructive/batch operations, no validation checkpoints are required.	3 / 3
Progressive Disclosure	The body is well-organized into clear sections and signals one-level-deep references ('For complete catalogs, load: ./references/agents-catalog.md', './references/skills-catalog.md'), but those referenced files and the references/ directory do not exist, so the signaled navigation is broken rather than genuinely progressive.	2 / 3
	Total	11 / 12 Passed

Description

90%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, third-person description that explicitly states both what it does and when to use it via a rich set of natural trigger phrases. Its only weakness is that it expresses essentially one action (recommend) rather than multiple distinct concrete actions.

Dimension	Reasoning	Score
Specificity	It names the domain ('agents and skills') and a concrete action ('Recommend the right agents and skills') plus two sub-categories with tool names ('heavyweight agents (Task tool)' and 'lightweight skills (Skill tool)'), but the verb set is essentially singular ('Recommend'); it does not list multiple distinct concrete actions like the score-3 anchor (extract, fill, merge).	2 / 3
Completeness	It clearly answers both 'what' ('Recommend the right agents and skills for any task. Covers both heavyweight agents (Task tool) and lightweight skills (Skill tool).') and 'when' with an explicit trigger clause ('Triggers on: ...'), so it is not capped at 2 by the missing-'Use when' guideline.	3 / 3
Trigger Term Quality	The phrase 'Triggers on: which agent, which skill, what tool should I use, help me choose, recommend agent, find the right tool' gives good coverage of natural terms a user would actually say, matching the score-3 anchor.	3 / 3
Distinctiveness Conflict Risk	It occupies a clear meta-niche (tool/agent-skill recommendation) with distinct triggers ('which agent', 'which skill', 'recommend agent') that are unlikely to fire for task-specific skills, matching the score-3 anchor; the broader phrases ('find the right tool') are secondary.	3 / 3
	Total	11 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: NeverSight/skills_feed
Commit: 26d37ce

Reviewed: 4 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.