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

90%

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

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 skill: runnable commands, complete config, output interpretation, and useful gotchas (pre-summarization meetings, agent-engine CLI requirements). The two soft spots are the thrice-repeated dry-run advice and the absence of any guidance for handling the 'error(s)' the tool can report.

Suggestions

Consolidate the dry-run advice into one place — e.g. keep it in 'How to run' as the recommended first command and drop the duplicate bullet in Safety guarantees and the repeated Gotcha — to reclaim a leaner token budget.

Add a short feedback loop for the error path: the sample output shows "1 error(s)" but the skill never says what to do next (e.g. re-run the single failing file, check its frontmatter validity, or read the CLI's error output before retrying).

The Gotchas on agent-engine CLIs and PARA items.json schema are engine/adapter-specific detail; if more such variants accumulate, move them into a reference file so SKILL.md stays the overview.

Dimension	Reasoning	Score
Conciseness	Sections are lean and imperative with no explanations of concepts Claude already knows, but dry-run advice is repeated three times — "(recommended first time)" in How to run, "Dry-run: Always suggest --dry-run first" in Safety guarantees, and "First run should be dry-run" in Gotchas. This matches anchor 4 (minor instances that could be trimmed) rather than anchor 5's every-token-earns-its-place.	4 / 5
Actionability	Fully executable, copy-paste-ready commands with real paths and flags ("minutes ingest ~/meetings/2026-04-03-strategy-call.md", "minutes ingest --all --dry-run"), a complete config TOML block, and a sample output with per-field interpretation. Not 4 — the common cases (single, backfill, preview) are each covered with runnable commands.	5 / 5
Workflow Clarity	The sequence — verify the [knowledge] config, dry-run, real run, interpret written/skipped/SKIP output — is clear with dry-run as an explicit validation checkpoint, so the batch-operation cap of 3 does not apply. Not 5: the sample output shows "1 error(s)" but the skill gives no feedback loop for investigating or retrying errored meetings, a minor validation gap matching anchor 4.	4 / 5
Progressive Disclosure	There are no bundle files (references/, scripts/, assets/ are absent) and none are needed: at ~80 lines of well-organized single-purpose sections, all content appropriately lives inline. Per the simple-skill exception, well-organized sections with no external-reference needs match anchor 5. Not 4 — there is no content that should have been split out and no navigation gap.	5 / 5
	Total	18 / 20 Passed

Description

95%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: concrete actions, an explicit 'Use when' clause with realistic quoted trigger phrases, and format-synonym coverage. The only gap is that the description stops just short of the fuller capability picture (confidence filtering, dedup, provenance) that the body documents.

Dimension	Reasoning	Score
Specificity	"Extract facts from meetings and update your knowledge base — person profiles, chronological log, and index" names the domain and several concrete actions, matching anchor 4. It is not 5 because pipeline details like confidence thresholds and deduplication are absent from the description itself, leaving minor coverage gaps.	4 / 5
Completeness	The first sentence explicitly states what the skill does, and "Use when the user asks ... or wants their PARA/Obsidian/wiki profiles updated" gives explicit when-guidance with concrete trigger phrases, matching anchor 5 exactly. Not 4 — the when-clause is already fully explicit and specific.	5 / 5
Trigger Term Quality	The quoted phrases "ingest my meetings", "update my knowledge base", "extract facts from meetings", "sync meetings to wiki", "backfill knowledge", plus "PARA/Obsidian/wiki", give comprehensive natural-term coverage including format synonyms. Not 4 — no common user phrasing for this domain is plausibly missing.	5 / 5
Distinctiveness Conflict Risk	"Extract facts from meetings" + "update your knowledge base" with meeting-ingestion-specific triggers carves out a clear niche with minimal overlap against generic note-taking or wiki skills. Not 4 — the trigger phrasing is domain-unique rather than merely mostly distinct.	5 / 5
	Total	19 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: silverstein/minutes
Path: .claude/plugins/minutes/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.