meeting-prep

Prepare for an upcoming meeting — surface context from past meetings, related docs, and attendee information. Trigger phrases include "prep for my meeting", "context for the meeting", "what should I know before", "1:1 prep with", "prepare for [name]", "background on this meeting", "agenda context", "talking points for".

Quality

81%

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

67%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 content is a clear, well-sequenced workflow with concrete tool calls and a usable output template. Its main weakness is conciseness — the duplicated prep-document templates and verbose vetting criteria inflate the body — followed by minor actionability gaps where tool signatures use placeholders.

Suggestions

Consolidate the Phase 5 and 'If First Meeting / No History' markdown templates into one template with a conditional 'First Instance' branch to remove the duplicated structure.

Tighten the Phase 4 vetting sub-tests into a compact checklist (e.g., a short table of Test / INCLUDE / MAYBE / OMIT) to cut tokens without losing the decision criteria.

Replace placeholder tool arguments with one fully-specified example invocation per tool so the guidance is copy-paste ready and tool signatures are unambiguous.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and avoids explaining concepts Claude already knows, but the two near-duplicate output templates (Phase 5 and 'If First Meeting / No History') and the verbose vetting sub-tests could be tightened into a single parameterized template, so it sits at the 'could be tightened' level rather than the 'minor trim' level 4.	3 / 5
Actionability	Concrete, executable tool calls are provided ('meeting_lookup "[topic or person name] upcoming"', 'chat "..."', 'search query=...', 'employee_search "..."') plus a full output template, but placeholder arguments and unspecified exact tool signatures leave minor gaps short of copy-paste-ready level 5.	4 / 5
Workflow Clarity	Five phases are clearly sequenced with stated goals, actions, and clarification checkpoints ('If multiple matches, ask the user to clarify'), plus a troubleshooting section; because the operation is read-only (no destructive/batch cap applies), it earns 4, falling short of 5 only because there is no explicit confirm-with-user checkpoint before producing the final prep doc.	4 / 5
Progressive Disclosure	Content is well organized into labeled phases and troubleshooting with clear headers, and no bundle files exist to reference; it is not level 5 because the skill exceeds the 'under 50 lines, no external references needed' exception and keeps two long inline templates that could be consolidated or split.	4 / 5
	Total	15 / 20 Passed

Description

86%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 the skill's purpose and provides an explicit, comprehensive set of natural trigger phrases in third person. The only soft spot is specificity, where the action verbs are condensed into the single high-level phrase 'surface context'.

Dimension	Reasoning	Score
Specificity	Names the meeting-prep domain and surfaces concrete sources ('past meetings, related docs, and attendee information'), but the governing action ('surface context') is high-level rather than a comprehensive list of distinct capabilities; not the level-4 'several specific actions' since the verbs are essentially one.	3 / 5
Completeness	Explicitly answers both 'what' ('Prepare for an upcoming meeting — surface context from past meetings, related docs, and attendee information') and 'when' with concrete trigger phrases, matching the level-5 anchor for both.	5 / 5
Trigger Term Quality	Eight natural user phrases including synonyms and variations ('prep for my meeting', 'context for the meeting', '1:1 prep with', 'prepare for [name]', 'talking points for') give comprehensive coverage of terms a user would actually say.	5 / 5
Distinctiveness Conflict Risk	The meeting-prep niche is distinct and triggers like '1:1 prep with [name]' and 'prepare for [name]' are specific, but broader phrases ('agenda context', 'talking points for') carry minor overlap risk with agenda- or doc-search skills, keeping it just below level 5.	4 / 5
	Total	17 / 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/meeting-prep/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.