CtrlK
BlogDocsLog inGet started
Tessl Logo

minutes-ingest

Extract facts from meetings and update your knowledge base — person profiles, chronological log, and index. Use when the user asks "ingest my meetings", "update my knowledge base", "extract facts from meetings", "sync meetings to wiki", "backfill knowledge", or wants their PARA/Obsidian/wiki profiles updated from conversation data.

72

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

The canonical home for this skill is minutes-ingest in silverstein/minutes

SKILL.md
Quality
Evals
Security

Quality

Content

76%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.

A well-structured, actionable skill body: executable commands, a concrete config block, and a real output example make it highly actionable. The main gap is workflow clarity for a batch operation — dry-run validation is offered but not sequenced as an explicit validate-then-proceed checkpoint — plus minor dry-run redundancy.

Suggestions

Sequence the run flow as an explicit batch workflow with a validation checkpoint: e.g. "1. Run `minutes ingest --all --dry-run` 2. Review skipped/errors 3. Only then run `minutes ingest --all` 4. Confirm the final written/skipped/error counts" — this lifts workflow clarity above the batch cap of 3.

Consolidate the dry-run guidance: the Safety "Dry-run" bullet and the Gotchas "First run should be dry-run" bullet say nearly the same thing; keep one and cross-reference it.

Remove the redundancy between the "Preview without writing (recommended first time)" command block and the standalone dry-run tips so each mention earns its place.

DimensionReasoningScore

Conciseness

The body is lean and assumes competence (no concept over-explanation), but dry-run guidance is repeated three times — "Preview without writing", the Safety "Dry-run" bullet, and the Gotchas "First run should be dry-run" bullet — with the latter two near-duplicates that could be consolidated.

4 / 5

Actionability

Commands are fully executable and copy-paste ready ("minutes ingest --all --dry-run"), the config.toml block is concrete, and a real annotated output example covers the common single and backfill cases.

5 / 5

Workflow Clarity

Prereqs, run, and output-interpretation steps are present and a --dry-run preview plus error/skip reporting exist, but for a batch operation (backfilling 73 meetings into a knowledge base) the validation is recommended rather than sequenced as an explicit checkpoint with a fix-and-retry feedback loop, so the batch cap of 3 applies.

3 / 5

Progressive Disclosure

No bundle files exist and none are needed; the body is a single-purpose CLI wrapper organized into clearly headed sections (Prerequisites, How to run, What it does, Safety, Output, Gotchas) with easy navigation. It sits just over the ~50-line simple-skill threshold, so it does not fully qualify for the top anchor.

4 / 5

Total

16

/

20

Passed

Description

100%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, model description: it states concrete capabilities up front, follows with an explicit 'Use when' clause packed with natural trigger phrases and synonyms, and occupies a clearly distinct niche. It hits the top anchor on all four dimensions.

DimensionReasoningScore

Specificity

"Extract facts from meetings and update your knowledge base — person profiles, chronological log, and index" lists multiple concrete actions (extract, update profiles, append log, maintain index) with comprehensive coverage of the domain.

5 / 5

Completeness

It explicitly answers both what (extract facts, update profiles/log/index) and when, with a concrete "Use when the user asks..." trigger clause including verbatim trigger phrases.

5 / 5

Trigger Term Quality

The "Use when" clause enumerates natural phrases users would actually say — "ingest my meetings", "update my knowledge base", "sync meetings to wiki", "backfill knowledge" — plus synonyms PARA/Obsidian/wiki.

5 / 5

Distinctiveness Conflict Risk

The meeting-ingestion-into-knowledge-base niche is specific with distinct triggers, and the PARA/Obsidian/wiki framing minimizes overlap with generic note or KB skills.

5 / 5

Total

20

/

20

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
silverstein/minutes
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.