meeting-synthesis

Turn one or more meeting transcripts, notes, or Slack threads into concise takeaways and clear action items with DRIs. Works with a single meeting or a batch from the whole week.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

72%

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

A highly actionable, well-structured synthesis prompt that is held back by a touch of marketing padding and the absence of explicit validation checkpoints for the multi-meeting batch path.

Suggestions

Trim the marketing intro and de-duplicate the 'action items table is most important' guidance to improve token efficiency.

Add an explicit verification step for the batch path, e.g. after consolidating combined action items, check that every row has a DRI or is flagged 'NEEDS DRI' and that duplicates were removed.

Dimension	Reasoning	Score
Conciseness	Mostly efficient, but the marketing-style intro ("This skill extracts what matters ... so you can share it immediately and move on") and repeated emphasis on the action-items table being most important could be tightened; not quite the lean 'every token earns its place' bar.	2 / 3
Actionability	Provides a copy-paste-ready prompt template with exact output sections, table column schemas, and concrete good/bad examples ("Follow up on pricing" vs "Share revised pricing tiers with the team by Friday"), giving fully executable guidance.	3 / 3
Workflow Clarity	The detect-single-vs-multiple branch and output sections are clearly sequenced, but there are no explicit validation/checkpoint steps for the batch (multiple-meeting) path, which the rubric flags as a gap.	2 / 3
Progressive Disclosure	Self-contained with no bundle files; content is organized into clearly signaled sections (Prompt Template, Tips) with no nested references, appropriate for a single-purpose skill.	3 / 3
	Total	10 / 12 Passed

Description

82%

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, specific description that clearly conveys capabilities and natural vocabulary, weakened only by the absence of an explicit use-when trigger clause inside the description field itself.

Suggestions

Add an explicit 'Use when...' clause to the description (e.g., 'Use when the user asks to summarize a meeting, recap action items, or process a batch of meeting notes') so completeness is not capped at 2.

Consider folding one or two of the most natural trigger phrases from suggest_when directly into the description.

Dimension	Reasoning	Score
Specificity	Names concrete inputs ("meeting transcripts, notes, or Slack threads") and concrete outputs ("concise takeaways and clear action items with DRIs"), listing multiple specific actions rather than vague language.	3 / 3
Completeness	Clearly answers "what" it does, but the description field lacks an explicit "Use when..." trigger clause; the when-guidance lives in the separate suggest_when field, so completeness is capped at 2 per the rubric.	2 / 3
Trigger Term Quality	Uses natural terms users would say — "meeting transcripts", "notes", "Slack threads", "takeaways", "action items" — giving good coverage of phrasings a user reaches for when they need this skill.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (meeting synthesis with DRIs/action items) with distinct input types, making it unlikely to trigger for the wrong skill.	3 / 3
	Total	11 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: amplitude/builder-skills
Commit: 22b0634

Reviewed: 2 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.