meeting-ingestion

Ingest meeting transcripts into brain pages with attendee enrichment, entity propagation, and timeline merge. A meeting is NOT fully ingested until the enrich skill has processed every entity.

Quality

70%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/meeting-ingestion/SKILL.md

Quality

Content

72%

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 and actionable with real CLI commands and a meeting-page template, but it duplicates guidance across Contract/Phases/Anti-Patterns and lacks an explicit validation checkpoint for its mutating batch workflow.

Suggestions

Add an explicit validation phase before reporting completion (e.g. verify every attendee has a people page and every mentioned entity has a back-link to the meeting page) since this is a mutating batch operation.

Collapse the redundancy between the Contract, Phases, and Anti-Patterns sections — state each guarantee once in the Phases and reference it, rather than restating enrichment/propagation rules three times.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with concrete phases and commands, but the Contract section and Anti-Patterns section largely restate what the Phases already specify (e.g. mandatory attendee enrichment, entity propagation), so it could be tightened to earn a 3.	2 / 3
Actionability	It provides executable commands (`gbrain search`, `gbrain put`, `gbrain timeline-add`, `gbrain sync`) and a copy-paste-ready meeting page markdown template, matching the 'fully executable code/commands; copy-paste ready' anchor.	3 / 3
Workflow Clarity	The six phases are clearly sequenced, but this is a mutating batch operation (every attendee + every entity) with no explicit validation/verification checkpoint before reporting done, so per the guideline workflow clarity is capped at 2.	2 / 3
Progressive Disclosure	The single self-contained file is well organized into Contract, Phases, Output, and Anti-Patterns, and its two external references (`skills/_brain-filing-rules.md`, `skills/conventions/quality.md`) are clearly signaled via blockquotes one level deep — appropriate for a skill with no bundle files.	3 / 3
	Total	10 / 12 Passed

Description

67%

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 specific and distinctive with concrete named actions, but it omits an explicit 'Use when...' trigger clause and only covers one natural keyword, capping completeness and trigger-term quality at 2.

Suggestions

Add an explicit trigger clause such as 'Use when processing meeting transcripts, meeting notes, or meeting minutes received from a user.'

Include more natural trigger variations (e.g. 'meeting notes', 'meeting minutes', 'transcript') alongside 'meeting transcripts' to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete actions — 'attendee enrichment, entity propagation, and timeline merge' on top of 'Ingest meeting transcripts into brain pages' — matching the anchor for several specific concrete actions rather than a single domain mention.	3 / 3
Completeness	It clearly answers 'what' but provides no explicit 'Use when...' trigger clause, so per the guideline a missing explicit trigger guidance caps completeness at 2 even though the what-side is strong.	2 / 3
Trigger Term Quality	'meeting transcripts' is a natural term a user would say, but the description lacks common variations (e.g. 'meeting notes', 'meeting minutes'), placing it at 'some relevant keywords but missing common variations' rather than full coverage.	2 / 3
Distinctiveness Conflict Risk	The niche is sharply defined — meeting transcript ingestion into 'brain pages' with a dependency on the 'enrich skill' — making it unlikely to trigger for unrelated skills, matching the 'clear niche with distinct triggers' anchor.	3 / 3
	Total	10 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 1 missing	Warning

	Total	14 / 16 Passed

Repository: garrytan/gbrain
Path: skills/meeting-ingestion/SKILL.md
Commit: 3fafb69

Reviewed: about 19 hours 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.