search-first

Research-before-coding workflow. Search for existing tools, libraries, and patterns before writing custom code. Invokes the researcher agent.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

50%

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

The skill is well-structured and broadly actionable with concrete shortcuts and examples, but it relies on a placeholder agent-invocation template and lacks explicit validation checkpoints and progressive disclosure for its longer inline sections.

Suggestions

Replace the placeholder Full Mode prompt with a concrete, executable Task invocation example, or justify the template form explicitly.

Add an explicit validation/verification checkpoint in the workflow (e.g., confirm a candidate is maintained and licensed before adopting it).

Move the Search Shortcuts by Category and/or Integration Points sections into one-level-deep reference files (e.g. SHORTCUTS.md) and signal them from the body.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean (ASCII diagram, decision matrix, shortcut tables) and avoids explaining known concepts, but the Integration Points section and the restated decision logic add tokens without proportional value and could be tightened.	2 / 3
Actionability	Concrete shortcuts ("rg through relevant modules/tests", named packages per category) and worked examples are strong, but the central Full Mode block is a placeholder template ("[DESCRIPTION]", "[LANG]") rather than executable code.	2 / 3
Workflow Clarity	The 5-step workflow is clearly sequenced and includes an EVALUATE step, but there are no explicit validation/verification checkpoints or feedback loops for error recovery.	2 / 3
Progressive Disclosure	The single SKILL.md is well-organized into clear sections with no nested references, but at ~155 lines content such as the per-category search shortcuts and Integration Points could be split into one-level-deep reference files.	2 / 3
	Total	8 / 12 Passed

Description

57%

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 clearly conveys what the skill does and carves a distinct niche, but it lacks an explicit "Use when..." trigger clause and richer natural trigger terms that users would actually say.

Suggestions

Add an explicit "Use when..." clause, e.g. "Use when adding a dependency, integrating a service, or about to write a utility/helper that may already exist."

Include natural trigger terms users actually say, such as "add a package", "is there a library for", or "before reinventing the wheel".

Consider enumerating a couple of concrete action verbs (search package registries, check MCP servers, compare candidates) to lift specificity toward 3.

Dimension	Reasoning	Score
Specificity	Names the domain and concrete actions ("Search for existing tools, libraries, and patterns before writing custom code", "Invokes the researcher agent"), but does not enumerate multiple distinct specific actions like the 3-anchor.	2 / 3
Completeness	The "what" is stated clearly, but there is no "Use when..." clause or equivalent explicit trigger guidance, which per the guidelines caps completeness at 2.	2 / 3
Trigger Term Quality	Relevant keywords are present ("Research-before-coding", "existing tools, libraries, and patterns", "before writing custom code") but it leans on process phrasing and misses common natural user variations like "add a package" or "is there a library for".	2 / 3
Distinctiveness Conflict Risk	"Research-before-coding" with an explicit researcher-agent invocation carves a clear niche unlikely to trigger for unrelated skills.	3 / 3
	Total	9 / 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: devrev/meerkat
Commit: 8155fdc

Reviewed: 1 day 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.