Name: minutes-ingest
Rating: 75.2 (1 reviews)
Author: silverstein

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.

Quality

93%

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

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

Quality

Content

86%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 tight, highly actionable body: executable commands, a complete config example, sample output with interpretation, and useful gotchas, with a dry-run validation checkpoint for the batch operation. The only real flaw is redundancy — the dry-run-first guidance is repeated three times — and an operator sequence that is implied rather than explicitly ordered.

Suggestions

Consolidate the dry-run guidance into one place: keep the 'Preview without writing' command and the gotcha, and drop the duplicate 'Dry-run' bullet from Safety guarantees (conciseness).

State the recommended operator sequence explicitly — configure → minutes ingest --all --dry-run → review output → real run — instead of relying on section order to imply it (workflow_clarity).

Add a brief post-run verification step (e.g., check the written/skipped counts in the output or inspect one updated profile) so the batch write has a feedback loop beyond the pre-run dry-run (workflow_clarity).

Dimension	Reasoning	Score
Conciseness	Lean and specific throughout with no explanation of concepts Claude already knows, but the dry-run-first advice is stated three times (the 'recommended first time' note, the 'Dry-run' safety bullet, and the 'First run should be dry-run' gotcha) — trimmable redundancy that keeps it at anchor 4 rather than 'every token earns its place' (5).	4 / 5
Actionability	Copy-paste-ready commands ('minutes ingest ~/meetings/2026-04-03-strategy-call.md', 'minutes ingest --all --dry-run'), a complete config TOML block, and a realistic output sample with per-line interpretation fully cover the common cases, matching anchor 5 rather than the 'minor gaps' of 4.	5 / 5
Workflow Clarity	The numbered 'What it does' steps, output/error interpretation, and the explicit dry-run checkpoint for the batch '--all' operation provide a clear sequence with most checkpoints (the batch cap at 3 does not apply since dry-run validation is present), but the operator sequence (configure → dry-run → run → interpret) is implied by section order rather than stated and there is no post-write verification — anchor 4.	4 / 5
Progressive Disclosure	The skill is self-contained (~75 lines) with no bundle files and none needed; all content (prerequisites, commands, gotchas) is appropriately inline in well-organized, easy-to-navigate sections, fitting anchor 5's 'content appropriately split' reading for a skill with no external references better than anchor 4's 'minor organization gaps'.	5 / 5
	Total	18 / 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.

An exemplary description: concrete actions and artifacts, an explicit 'Use when' clause with six natural trigger phrases covering synonyms and ecosystem names, and a clear niche that is unlikely to fire for the wrong skill. Third-person imperative voice is used correctly.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions ('Extract facts from meetings', 'update your knowledge base') and concrete artifacts ('person profiles, chronological log, and index'), matching the score-5 anchor for multiple specific actions with comprehensive coverage rather than the 'minor gaps' of a 4.	5 / 5
Completeness	Explicitly answers both what (extract facts, update profiles/log/index) and when ('Use when the user asks...') with concrete trigger phrases, exactly matching the score-5 anchor; the 4 anchor requires a less explicit 'when', which this does not.	5 / 5
Trigger Term Quality	Six verbatim natural user phrases ('ingest my meetings', 'update my knowledge base', 'extract facts from meetings', 'sync meetings to wiki', 'backfill knowledge') plus ecosystem synonyms (PARA/Obsidian/wiki) give comprehensive natural-term coverage as the score-5 anchor requires.	5 / 5
Distinctiveness Conflict Risk	Clear niche (meeting ingestion into a knowledge base) with quoted task-specific triggers; 'update my knowledge base' is mildly broad but the trigger set as a whole is distinct with minimal conflict risk, fitting anchor 5 better than anchor 4's 'minor overlap risk'.	5 / 5
	Total	20 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: silverstein/minutes
Path: .opencode/skills/minutes-ingest/SKILL.md
Commit: 5fbe77b

Reviewed: 6 days 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.