CtrlK
BlogDocsLog inGet started
Tessl Logo

mgrep-code-search

Semantic code search using mgrep for efficient codebase exploration. This skill should be used when searching or exploring codebases with more than 30 non-gitignored files and/or nested directory structures. It provides natural language semantic search that complements traditional grep/ripgrep for finding features, understanding intent, and exploring unfamiliar code.

87

11.62x
Quality

83%

Does it follow best practices?

Impact

93%

11.62x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

The canonical home for this skill is mgrep-code-search in intellectronica/agent-skills

SKILL.md
Quality
Evals
Security

Quality

Content

82%Weight 40%Scale 1-5

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

The body is highly actionable with copy-paste commands and clean sectioning, requiring no external bundle files. Slight redundancy across the Quick Start, Search Commands, and Workflow sections is the main tightening opportunity.

Suggestions

Consolidate the repeated watch/search command examples so Quick Start, Search Commands, and Workflow do not restate the same invocations verbatim.

Trim the Overview sentence restating capabilities already covered by the frontmatter description and the When-to-Use section.

DimensionReasoningScore

Conciseness

Largely lean and command/table-driven, but the Workflow and Search Commands sections repeat the same 'bunx @mixedbread/mgrep watch' and search invocations already shown in Quick Start, leaving minor tightening opportunities.

4 / 5

Actionability

Provides fully executable, copy-paste-ready commands throughout, with an options table and concrete examples covering the common search cases.

5 / 5

Workflow Clarity

A clear three-step sequence (index -> search -> refine) is given; validation checkpoints are not required for read-only search, and the 'refine as needed' step acts as a light feedback loop, but no explicit error-recovery guidance is provided.

4 / 5

Progressive Disclosure

Self-contained SKILL.md with well-organized section headers and no nested external references; slightly above the simple-skill threshold, so it lands at good-but-not-exemplary structure.

4 / 5

Total

17

/

20

Passed

Description

83%Weight 40%Scale 1-5

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, well-targeted description that clearly states both capability and explicit usage triggers with a concrete file-count heuristic. Minor room to expand the list of distinct capabilities and synonyms.

Suggestions

Add a few more concrete capability verbs (e.g., 'index', 're-rank', 'AI-synthesised answers') to lift specificity toward comprehensive coverage.

Include additional natural synonyms such as 'code navigation', 'locate code', or 'fuzzy code search' to broaden trigger-term coverage.

DimensionReasoningScore

Specificity

Names the domain (semantic code search via mgrep) and several concrete actions/use-cases such as 'finding features, understanding intent, and exploring unfamiliar code', but stops short of comprehensive coverage of the tool's capabilities.

4 / 5

Completeness

Explicitly answers both 'what' (natural language semantic search via mgrep) and 'when' with concrete trigger phrases ('when searching or exploring codebases with more than 30 non-gitignored files and/or nested directory structures').

5 / 5

Trigger Term Quality

Includes natural phrases a user would say ('searching or exploring codebases', 'semantic search', 'grep/ripgrep', 'finding features') with good coverage, though a few common synonyms are absent.

4 / 5

Distinctiveness Conflict Risk

Names a specific tool (mgrep) and carves a clear niche as a complement to grep/ripgrep, with minor overlap risk against generic code-search skills.

4 / 5

Total

17

/

20

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
intellectronica/agent-skills
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.