minutes-verify

Verify that Minutes is properly set up and working — model downloaded, mic accessible, directories exist, no stale state. Use when the user says "is minutes working", "check my setup", "verify minutes", "test recording setup", "why isn't minutes working", "minutes health check", or after running setup for the first time.

Quality

86%

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

82%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-organized, actionable health-check skill: it delegates verification to a bundled script and gives concrete remediation for every failure mode. It is lean and executable, with only minor room to tighten macOS caveats and make the script reference more clearly navigable.

Suggestions

Signal the script reference more explicitly (e.g. "See [scripts/verify-setup.sh](scripts/verify-setup.sh) for the full check logic") to strengthen progressive disclosure.

Add one line distinguishing WARN vs FAIL handling in the report step so Claude knows which failures block recording versus which are informational.

Trim the repeated macOS desktop-app caveats across the table, After-verification, and Gotchas sections into a single concise note.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence — a tight table of checks, a run command, and targeted remediation — with only minor padding in the macOS audio/Spotlight caveats that could be trimmed slightly.	4 / 5
Actionability	Provides copy-paste-ready commands throughout: the env-var exports, the verification script invocation, and specific remediation commands for each failure (e.g. "cargo build --release", "minutes setup --model small", "rm ~/.minutes/recording.pid").	5 / 5
Workflow Clarity	The sequence is clear — set paths, run the script, read pass/fail output, report, then remediate per failure — with the script acting as the validation checkpoint and an explicit error-recovery section; falls just short of 5 because the report/distinguish-warn-vs-fail step is left somewhat implicit.	4 / 5
Progressive Disclosure	The overview lives in SKILL.md while the actual check logic is delegated one level deep to scripts/verify-setup.sh, and the "What gets checked" table summarizes without dumping the script; structure is good, though the reference to the script is a plain path rather than a clearly signaled link.	4 / 5
	Total	17 / 20 Passed

Description

91%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 clearly states what the skill verifies, lists the concrete components checked, and provides explicit, natural trigger phrases. Minor overlap risk on a couple of generic phrases keeps distinctiveness just below maximum.

Suggestions

Tie the more generic triggers ("check my setup", "test recording setup") explicitly to Minutes, e.g. "check my Minutes setup", to reduce overlap with other health-check skills.

Dimension	Reasoning	Score
Specificity	Names the domain (Minutes setup verification) and lists several concrete components checked — "model downloaded, mic accessible, directories exist, no stale state" — giving broad coverage, though it frames one verify action with sub-checks rather than enumerating multiple distinct actions.	4 / 5
Completeness	Explicitly answers both what ("Verify that Minutes is properly set up and working — model downloaded, mic accessible, directories exist, no stale state") and when (a clear "Use when..." clause with concrete trigger phrases).	5 / 5
Trigger Term Quality	Includes a comprehensive set of natural phrases users would actually say — "is minutes working", "check my setup", "verify minutes", "test recording setup", "why isn't minutes working", "minutes health check" — covering synonyms and the post-setup trigger.	5 / 5
Distinctiveness Conflict Risk	Minutes-specific triggers ("is minutes working", "minutes health check") carve a clear niche with low conflict risk, but a few phrases like "check my setup" and "test recording setup" could overlap with other setup/health skills.	4 / 5
	Total	18 / 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-verify/SKILL.md
Commit: a9a4a8b

Reviewed: 2 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.