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

95%

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

92%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.

An effective, lean single-purpose skill: executable commands for every step and failure mode, a clean one-script workflow with a complete remedy map, and well-organized sections with a verified bundle reference. The only trimmable content is the thrice-repeated macOS audio-input caveat.

Suggestions

Consolidate the macOS audio-input / desktop Readiness Center caveat into one place (e.g. the Gotchas section) and keep the table row and remedy bullet to a short cross-reference, saving the duplicated wording.

The 'Spotlight privacy' explanation appears in both the table and Gotchas; the Gotchas entry could drop the re-statement of the marker path and keep only the non-obvious distinction (folder-level markers, not volume-wide Spotlight disabling).

Dimension	Reasoning	Score
Conciseness	The checks table and failure-remedy list are tight and every line is non-obvious, but the macOS audio-input / desktop Readiness Center caveat is repeated in three places (the table row "CLI-context audio input visibility", the "Audio input warning" bullet, and the Gotchas section) with slightly different wording. Not 5: that repetition could be consolidated; not 3: the rest is efficient with no over-explanation of known concepts.	4 / 5
Actionability	Fully executable guidance throughout: the exact invocation `bash "$MINUTES_SKILL_ROOT/scripts/verify-setup.sh"` (the script exists in the bundle), and copy-paste remedies like `cargo build --release`, `minutes setup --model small`, `mkdir -p ~/meetings/memos`, and `rm ~/.minutes/recording.pid` for each failure mode. Not 4: no gaps — even the optional config case has explicit severity guidance (informational, not error).	5 / 5
Workflow Clarity	A simple single-purpose skill where the single action is unambiguous: set the two env vars, run the script, read the per-check pass/fail output, report, and apply the mapped fix. The complete failure→remedy mapping functions as an error-recovery loop, and the read-only health check triggers no destructive/batch validation cap. Not 4: sequencing and checkpoints are fully explicit for this scope.	5 / 5
Progressive Disclosure	Well-organized sections (Skill Path, How to verify, What gets checked, After verification, Gotchas) at ~55 lines with a single clearly-signaled bundle file, scripts/verify-setup.sh, which exists — no references/ or assets/ directories and no nested references. Not 4: nothing is inlined that belongs in a separate file, and navigation is trivial.	5 / 5
	Total	19 / 20 Passed

Description

96%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 check enumeration, explicit 'Use when' triggers quoted as natural user phrases, and a clear product niche. The only weakness is a couple of unqualified generic trigger phrases ("check my setup") that slightly raise conflict risk.

Dimension	Reasoning	Score
Specificity	"model downloaded, mic accessible, directories exist, no stale state" enumerates the concrete checks comprehensively for the setup-verification domain, matching the 5-anchor's multiple specific concrete actions. Not 4: there are no meaningful gaps in what gets verified.	5 / 5
Completeness	Explicitly answers both what ("Verify that Minutes is properly set up and working") and when, with a concrete quoted trigger list — a direct match for the 5-anchor example. Not 4: the 'when' is fully explicit, not improvable.	5 / 5
Trigger Term Quality	Six natural user phrases are quoted verbatim ("is minutes working", "check my setup", "verify minutes", "test recording setup", "why isn't minutes working", "minutes health check") plus the context "after running setup for the first time", giving comprehensive coverage of how a user would actually ask. Not 4: common variations and synonyms are already present.	5 / 5
Distinctiveness Conflict Risk	The Minutes product niche is distinct and most triggers are minutes-qualified, but "check my setup" and "test recording setup" are semi-generic without the qualifier, creating minor overlap risk with other setup/verification skills. Not 5: those unqualified generic phrases could plausibly fire for the wrong skill.	4 / 5
	Total	19 / 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: 39bb670

Reviewed: 7 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.