dev-docs-guide
Search the public Glean developer documentation for API, SDK, MCP, authentication, indexing, and integration details. Use when the user is building with Glean rather than searching internal company knowledge.
67
81%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
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 well-crafted description that clearly defines its scope (Glean developer documentation), includes relevant trigger terms, and explicitly distinguishes itself from a related but different use case (internal knowledge search). The main weakness is that the action verb is limited to 'search' — listing more specific capabilities (e.g., 'find code examples, troubleshoot authentication errors, look up API endpoints') would strengthen specificity.
Suggestions
Expand the action verbs beyond just 'Search' to list more specific capabilities, e.g., 'Search Glean developer documentation to find API endpoints, code examples, SDK setup guides, and authentication troubleshooting steps.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Glean developer documentation) and lists several topic areas (API, SDK, MCP, authentication, indexing, integration), but the core action is just 'search' — it doesn't describe multiple distinct concrete actions like extracting, generating, or configuring. | 2 / 3 |
Completeness | Clearly answers both 'what' (search Glean developer documentation for specific topics) and 'when' (use when the user is building with Glean rather than searching internal company knowledge), with an explicit differentiating trigger clause. | 3 / 3 |
Trigger Term Quality | Includes strong natural keywords a developer would use: 'Glean', 'API', 'SDK', 'MCP', 'authentication', 'indexing', 'integration', and 'building with Glean'. These cover a good range of terms a user would naturally mention. | 3 / 3 |
Distinctiveness Conflict Risk | The explicit contrast 'building with Glean rather than searching internal company knowledge' creates a very clear boundary, distinguishing this from a general Glean search skill. The niche of Glean developer docs is well-defined and unlikely to conflict with other skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
72%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, concise skill that clearly communicates when and how to use the Glean developer docs tools. Its main strengths are token efficiency and clean organization. The primary weakness is the workflow section, which could benefit from error handling guidance (e.g., no results found, ambiguous queries) and a brief example of expected tool output to make the skill more actionable.
Suggestions
Add a brief example showing a complete search-then-fetch interaction with representative tool output, so Claude knows what to expect and how to present results.
Include a fallback step in the workflow for when `docs_search` returns no or irrelevant results (e.g., broaden query terms, suggest the user check the Glean developer portal directly).
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every section is lean and purposeful. No unnecessary explanations of what Glean is, what APIs are, or how MCP works. The table format for tool selection is efficient, and query tips are given as terse examples rather than lengthy explanations. | 3 / 3 |
Actionability | The skill provides concrete tool names and example invocations (e.g., `docs_search "API authentication"`), but these are tool calls rather than executable code. The guidance is specific enough to act on but lacks complete worked examples showing a full interaction pattern with expected output shapes. | 2 / 3 |
Workflow Clarity | The 4-step workflow is clearly sequenced and logical, but it lacks validation checkpoints or error handling—e.g., what to do if `docs_search` returns no results, or if `docs_fetch` fails. For a non-destructive search workflow this is less critical, but the absence of any feedback loop or fallback guidance keeps it at 2. | 2 / 3 |
Progressive Disclosure | For a simple skill with no bundle files, the content is well-organized into clearly labeled sections (Tools, When to use, Tool selection, Workflow, Query tips, Differentiating). The cross-reference to the `using-glean` skill in `glean-core` is a clean one-level-deep pointer. No monolithic walls of text or nested references. | 3 / 3 |
Total | 10 / 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.