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.

74

Quality

92%

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

85%

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

The body is concise, actionable, and well-organized with concrete commands and config examples. Its main gap is workflow clarity around the batch backfill: validation is presented as an optional recommendation rather than a required checkpoint before mutating the knowledge base.

Suggestions

Make dry-run an explicit mandatory checkpoint in the workflow (e.g., 'Run minutes ingest --all --dry-run first; review the summary for SKIP/errors before running without --dry-run') rather than only a suggestion.

Add a verify/reconcile step after writing (e.g., confirm 'written' vs 'error(s)' counts and inspect any errors before declaring success) to create a feedback loop for the batch operation.

Note the confidence-threshold/dedup behavior as the safety checkpoint that gates writes, so the sequence 'extract -> threshold/dedup check -> write' reads as an explicit validation gate.

DimensionReasoningScore

Conciseness

Lean and efficient throughout: every section (Prerequisites, How to run, What it does, Safety guarantees, output, Gotchas) earns its place without explaining concepts Claude already knows or padding.

3 / 3

Actionability

Fully executable commands (e.g., 'minutes ingest ~/meetings/...md', 'minutes ingest --all --dry-run'), a concrete config.toml block, and a copy-pasteable annotated output sample.

3 / 3

Workflow Clarity

The 'What it does' list sequences the pipeline steps but there is no explicit validation checkpoint before writing facts to the knowledge base, and the batch/destructive backfill operation only relies on the optional --dry-run suggestion rather than a mandatory verify step.

2 / 3

Progressive Disclosure

A single self-contained, well-organized SKILL.md with no bundle directories and clear sectioned navigation; for a sub-50-line single-purpose skill this is appropriate.

3 / 3

Total

11

/

12

Passed

Description

100%

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 with concrete capabilities and a rich set of natural trigger phrases covering both what and when. It is appropriately concise and clearly differentiated.

DimensionReasoningScore

Specificity

Lists multiple concrete actions: 'Extract facts from meetings and update your knowledge base', 'person profiles, chronological log, and index', and explicit targets like 'PARA/Obsidian/wiki profiles'.

3 / 3

Completeness

Explicitly answers both what (extract facts and update person profiles/log/index) and when (a 'Use when...' clause with concrete trigger phrases).

3 / 3

Trigger Term Quality

Provides a broad set of natural phrasings a user would say: 'ingest my meetings', 'update my knowledge base', 'extract facts from meetings', 'sync meetings to wiki', 'backfill knowledge'.

3 / 3

Distinctiveness Conflict Risk

The meeting/knowledge-base niche with PARA/Obsidian/wiki triggers is clearly distinct and unlikely to fire for unrelated skills.

3 / 3

Total

12

/

12

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

Total

15

/

16

Passed

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.