using-glean-code
Search and analyze internal source code across the user's organization's repositories. Use when the user asks how something is implemented, where the code for a system lives, who has been working on a codebase, or wants to find similar patterns across teams — i.e., questions that need visibility beyond the local working directory.
86
82%
Does it follow best practices?
Impact
92%
1.41xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Quality
Discovery
100%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 an excellent skill description that clearly communicates its purpose, scope, and trigger conditions. It uses third person voice, provides concrete use cases in the 'Use when' clause, and explicitly differentiates itself from local code tools by emphasizing cross-repository, organization-wide visibility. The description is concise yet comprehensive.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple concrete actions: 'search and analyze internal source code', finding implementations, locating code for systems, identifying contributors, and finding similar patterns across teams. These are specific, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (search and analyze internal source code across repositories) and 'when' (explicit 'Use when' clause with multiple trigger scenarios like asking about implementations, code locations, contributors, and cross-team patterns). | 3 / 3 |
Trigger Term Quality | Includes natural trigger terms users would say: 'how something is implemented', 'where the code lives', 'who has been working on', 'find similar patterns', 'repositories', 'across teams', 'beyond the local working directory'. These cover a good range of natural phrasings. | 3 / 3 |
Distinctiveness Conflict Risk | Clearly distinguished from local code search or general file operations by specifying 'across the user's organization's repositories' and 'beyond the local working directory'. The scope is well-defined as organization-wide source code search, creating a distinct niche. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
64%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 routing/overview skill that efficiently tells Claude when and why to use Glean code search, with good vetting and output formatting guidance. Its main weakness is that nearly all concrete, actionable detail (tool parameters, search strategies, workflow steps) is deferred to reference files that aren't available in the bundle, making it hard to use as a standalone resource. Adding at least one concrete example query with expected output would significantly improve actionability.
Suggestions
Add a concrete example showing an actual code_search invocation with parameters and a sample result summary, so the skill is actionable even without the referenced files.
Include a brief inline workflow sequence (e.g., search → vet results → group and cite → flag drift) with numbered steps rather than deferring the entire workflow to reference files.
Provide at least one example of the related commands in action (e.g., `/glean-code:similar-code` with input and expected output shape) to make the commands section more actionable.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient. It doesn't explain what code search is or how repositories work. Every section earns its place — when to use it, tool reference, vetting criteria, output expectations, and related commands. No padding or unnecessary explanation. | 3 / 3 |
Actionability | The skill provides useful guidance (vetting criteria, output formatting rules, related commands) but lacks concrete executable examples — no actual code_search invocations with parameters, no example queries, no sample output. The actionable details are deferred to referenced files that aren't provided in the bundle. | 2 / 3 |
Workflow Clarity | The skill outlines when to use it and what to do with results (vetting, output formatting), but the actual multi-step workflows are delegated to reference files (exploration.md, plan-prep.md) that aren't available. The main file itself doesn't present a clear sequenced workflow with validation checkpoints — it's more of a routing document. | 2 / 3 |
Progressive Disclosure | The skill has good structure with clear section headers and references to deeper content (exploration.md, plan-prep.md, code-search.md, vetting.md). However, no bundle files were provided, so we can't verify these references resolve correctly. The references also span two levels — some point to a separate plugin's files (glean-core) which adds navigational complexity. The overview itself is well-organized but relies heavily on absent supporting files. | 2 / 3 |
Total | 9 / 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
- gleanwork/claude-plugins
- Commit
39a5c99
- 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.