find-expert

Find subject matter experts on a topic, technology, or internal system by combining real expertise signals (code contributions, document authorship, and meeting or discussion activity) rather than relying on job titles. Use this whenever the user wants to know who to ask about something — phrasings such as who knows about, who is the expert on, the go-to person for, who has worked on, who can I ask about, or subject matter expert for. Use it even when the user does not say the word expert but clearly needs a person with deep, demonstrated knowledge of an area. Do not use it for plain directory lookups (an email address, manager, or org placement with no expertise angle), which is a simple employee lookup.

Quality

87%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

75%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 well-structured, actionable, and concise, with a clear three-phase workflow and explicit vetting criteria. The main improvement area is conciseness — the verbose report templates could be factored into a reference file to further reduce token load.

Suggestions

Move the large expert-report and no-experts markdown templates into a references/ file (e.g. REPORT_TEMPLATE.md) and link to it, shrinking the inlined templates to a short skeleton — this would improve both conciseness and progressive_disclosure.

Tighten the Phase 3 template by collapsing the 'Also Consider' / 'Rejected Candidates' / 'How to Engage' sub-blocks into a single annotated example rather than three separate filled-out sections.

Add a one-line cross-reference validation note in Phase 1 confirming that the named tools (chat, employee_search, code_search, search) are available, so failures surface as a setup step rather than mid-workflow.

Dimension	Reasoning	Score
Conciseness	Lean and assumes Claude's competence (tight 'Core Principles' bullets, no padding about what expertise means); the full report templates earn their length but add some verbosity that could be trimmed.	4 / 5
Actionability	Concrete tool calls (chat, employee_search, code_search, search) and a vetting table with explicit numeric thresholds (6 months, 3+ signals) give mostly executable guidance; placeholders like [topic] are parameterized rather than fully literal.	4 / 5
Workflow Clarity	A clear 3-phase sequence (gather → vet → report) with an explicit vetting table and a no-results fallback; because the operation is read-only research rather than destructive/batch mutation, no validate-then-retry loop is required.	4 / 5
Progressive Disclosure	No bundle files exist, so structure rests entirely on the SKILL.md, which is well-organized into clearly headed sections with no nested references; minor gap is that the full report templates are inlined where a reference file could carry the bulk.	4 / 5
	Total	16 / 20 Passed

Description

92%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.

The description is strong: it clearly states what the skill does, when to use it, and when not to, with rich natural trigger phrasings and an explicit negative boundary. Specificity is slightly held back by a single composite action rather than an enumerated action list.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete signal types ('code contributions, document authorship, and meeting or discussion activity') but the core action 'find experts' is a single composite action rather than a comprehensive list of discrete actions.	4 / 5
Completeness	Explicitly answers both what ('Find subject matter experts... by combining real expertise signals') and when ('Use this whenever the user wants to know who to ask about something'), and adds a negative boundary ('Do not use it for plain directory lookups').	5 / 5
Trigger Term Quality	Comprehensive natural phrasings users would actually say ('who knows about', 'who is the expert on', 'the go-to person for', 'who can I ask about', 'subject matter expert for'), plus the no-'expert'-word variant.	5 / 5
Distinctiveness Conflict Risk	Clear niche (evidence-based expertise vs org-chart lookup) with distinct triggers and an explicit exclusion for plain directory lookups, minimizing conflict with employee-search skills.	5 / 5
	Total	19 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: gleanwork/claude-plugins
Path: plugins/glean/skills/find-expert/SKILL.md
Commit: a549de6

Reviewed: 5 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.