meeting-ingestion

Ingest meeting transcripts from ANY meeting recorder into brain pages with attendee enrichment, entity propagation, and timeline merge. One unified pipeline: normalize the source into a standard transcript record, split multi-meeting recordings, resolve speakers by evidence, create the page, pass every surprising claim through the consistency check (transcript + brain + plausibility), enrich every entity, then run the verification checklist — substance AND sequence. A meeting is NOT fully ingested until the enrich skill has processed every entity AND the verification checklist passes, including the sequence verify (PASS or explicit user waive).

Quality

72%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

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

Quality

Content

81%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 a dense, highly actionable pipeline with excellent workflow sequencing and validation feedback loops. Its main weakness is length — the Anti-Patterns section duplicates the phase rules and could be condensed for better token efficiency.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and domain-specific rather than explaining concepts Claude already knows, but the long Anti-Patterns list largely restates the phase rules and some sections (invariants, downgrade protocol) could be tightened.	3 / 5
Actionability	Provides fully executable guidance throughout — concrete gbrain commands with arguments (search, query, get, put, timeline-add, sync, day), a complete transcript-record schema, a copy-paste meeting-page template, and mechanical deterministic checks (PHASE_INVERSION, TELEPORT).	5 / 5
Workflow Clarity	Nine phases are clearly sequenced with explicit validation gates — Phase 6 consistency check and the HARD GATE checklist V1–V6 — plus a fix → re-check → fix feedback loop and PASS/BLOCK verdicts for a mutating, batch-style skill.	5 / 5
Progressive Disclosure	Well-organized with clear section headers and one-level-deep, clearly signaled references to external skills/conventions (enrich, signal-detector, brain-filing-rules); no bundle files exist, though the single-file body is long and the Anti-Patterns section could be trimmed.	4 / 5
	Total	17 / 20 Passed

Description

63%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 highly specific and comprehensive about what the pipeline does, but omits explicit 'when to use' guidance and leans on internal jargon over natural user phrases. Adding a 'Use when...' clause and everyday synonyms would lift completeness and trigger quality.

Suggestions

Add an explicit 'Use when...' clause naming natural triggers (e.g. 'Use when processing meeting transcripts, meeting notes, or recordings from any meeting recorder').

Replace or supplement internal jargon ('entity propagation', 'timeline merge') with user-facing synonyms users actually say.

Mention common variations like 'meeting notes' and file/source types to broaden natural keyword coverage.

Dimension	Reasoning	Score
Specificity	Lists many concrete actions — 'normalize the source into a standard transcript record, split multi-meeting recordings, resolve speakers by evidence, create the page, ... enrich every entity, then run the verification checklist — substance AND sequence' — covering the pipeline comprehensively.	5 / 5
Completeness	It clearly and thoroughly answers 'what' the skill does, but there is no 'Use when...' clause or equivalent explicit 'when' guidance inside the description (triggers live in a separate frontmatter field), so completeness is capped at 3 per the rubric guideline.	3 / 5
Trigger Term Quality	Contains natural terms a user would say ('meeting transcripts', 'meeting recorder', 'brain pages') but the rest is internal jargon (entity propagation, timeline merge, consistency check) and common synonyms like 'meeting notes' or 'capture meetings' are absent from the description.	3 / 5
Distinctiveness Conflict Risk	The meeting-ingestion niche is clear and distinct with specific triggers, but it references and chains into the enrich skill and overlaps slightly with adjacent ingestion/archival skills, leaving minor conflict risk.	4 / 5
	Total	15 / 20 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: 055ac6c

Reviewed: about 2 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.