CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

77%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 an exemplar of actionable, well-sequenced instruction: concrete commands, a hard verification gate with a fix-recheck loop, and specific error recovery. Its weaknesses are token efficiency — the same invariants restated in four places and long digressions into host-system behavior — and a complete absence of progressive disclosure, with everything inlined in one 550-line file.

Suggestions

Move the auto-link/MCP receipt semantics (Phase 7 note) and the facts_backstop/chronicle extraction lifecycle (Phase 5) into a one-level-deep reference file (e.g. references/extraction-behavior.md) and link to it from the relevant phases, cutting the top-level file to the core pipeline.

State each invariant once: the "not ingested until the checklist passes" rule and the facts_backstop rationale each appear in four places (Contract, phases, Verify gate, Output Format, Anti-Patterns) — keep the HARD GATE statement and cross-reference it elsewhere instead of restating it.

Convert Phase 7's ~25-line auto-link prose into a short bullet list of rules (who gets attended edges, when to run `gbrain extract --stale`, what to do over MCP vs stdio) to preserve the content at a fraction of the tokens.

DimensionReasoningScore

Conciseness

There is no generic padding — no explaining what meetings or diarization are — but key invariants repeat across sections: "A meeting is NOT fully ingested until" appears in the Contract, the Verify gate, Output Format, and Anti-Patterns; the facts_backstop lifecycle is explained in the sidecar section, Phase 5, "The loop", and Output Format; and Phase 7's auto-link/MCP note runs ~25 lines on host-system behavior. This fits anchor 3 (mostly efficient but could be tightened) rather than 4, because the repetition and digressions exceed "minor instances of over-explanation".

3 / 5

Actionability

Copy-paste-ready commands throughout — `gbrain whois <email> --json`, `gbrain timeline-add {person-slug} {date} "Attended {meeting-title}"`, `gbrain day {date}`, `gbrain sync --source <id> --no-pull`, `gbrain extract --stale` — plus a complete normalized-record YAML schema, a fill-in meeting page template, exact dedup criteria ("date ± 1 day + attendee overlap ≥ 50%"), and named receipt fields to check. This matches the 5 anchor: fully executable guidance with specific examples covering the common cases.

5 / 5

Workflow Clarity

Nine numbered phases in strict sequence, a "HARD GATE" verification checklist (V1–V6) with deterministic checks, an explicit feedback loop ("The loop: fix → re-check → fix, until every item passes"), and an error-recovery section ("`put_page` returns `revision_conflict`... re-read and merge; never overwrite a person page from an old read"). This is exactly the 5 anchor: explicit validation steps, feedback loops for error recovery, and a checklist for a complex process.

5 / 5

Progressive Disclosure

No bundle files exist (no references/, scripts/, or assets/), so all ~550 lines live in SKILL.md. Cross-references to other skills are clearly signaled ("skills/enrich/SKILL.md", "docs/guides/life-chronicle.md", "../conventions/brain-first.md#identity-exact-match"), but reference-grade material — the auto-link/MCP receipt semantics and the facts_backstop/chronicle extraction lifecycle — is inlined rather than split into one-level-deep files. This is anchor 3 (content that should be separate is inline), not 2 because structure and signaling are good, and not 4 because essentially nothing is offloaded to progressively disclosed files.

3 / 5

Total

16

/

20

Passed

Description

80%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.

A strong description: it enumerates the full pipeline in concrete, third-person verbs, defines an explicit completion contract, and is backed by a rich natural-language triggers list. The main gaps are the absence of an integrated use-when clause inside the description text itself and a few missing natural trigger variations (minutes, call summary).

DimensionReasoningScore

Specificity

The description enumerates a complete concrete 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" — on top of "attendee enrichment, entity propagation, and timeline merge". This matches the 5 anchor (multiple specific concrete actions, comprehensive coverage) rather than 4, which permits minor coverage gaps; no pipeline stage is left unnamed.

5 / 5

Completeness

The "what" is explicit and comprehensive (the entire pipeline is enumerated), and the "when" is supplied as equivalent explicit trigger guidance via the frontmatter triggers list, so the missing-Use-when cap at 3 does not apply. It stays below the 5 anchor because the description field itself contains no integrated "Use when..." clause — the timing guidance lives in a separate field rather than in the description text with concrete trigger phrases.

4 / 5

Trigger Term Quality

The description carries natural terms — "meeting transcripts", "ANY meeting recorder", "ingest" — and the frontmatter's explicit triggers block adds "process this meeting", "meeting notes", "ingest this recording", "capture meetings", "did I get the order right", giving good keyword coverage with synonyms. It is not the 5 anchor because common variations users would say — "meeting minutes", "summarize this call", recorder product names — are missing.

4 / 5

Distinctiveness Conflict Risk

"Ingest meeting transcripts from ANY meeting recorder into brain pages with attendee enrichment, entity propagation, and timeline merge" carves a clear niche with brain-specific vocabulary. It is not the 5 anchor (minimal conflict risk) because sequence-oriented triggers — "check the sequence", "did I get the order right" — and the delegated enrichment step overlap with closely related skills (chronology-guard and enrich are listed as upstream), matching anchor 4: mostly distinct, minor overlap risk.

4 / 5

Total

17

/

20

Passed

Validation

81%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (592 lines); consider splitting into references/ and linking

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

relative_links

Relative link issues: 2 suspicious

Warning

Total

13

/

16

Passed

Repository

garrytan/gbrain

Path

skills/meeting-ingestion/SKILL.md

Reviewed

Table of Contents

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.