CtrlK
BlogDocsLog inGet started
Tessl Logo

minutes-setup

Guided first-time setup for Minutes — download whisper model, create directories, configure audio input. Use when the user says "set up minutes", "install minutes", "first time setup", "configure minutes", "get started with minutes", "how do I start using minutes", or when verify shows missing components.

68

Quality

85%

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

SKILL.md
Quality
Evals
Security

Quality

Content

75%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 solid, well-structured setup guide: concrete commands throughout, a sensible check-verify-test workflow, and appropriate deferral of deep audio detail to a reference. It uniformly lands at anchor 4 due to minor gaps — no PATH/symlink command, no failure-recovery guidance after verify, a hardcoded repo path, and an unverifiable cross-skill reference path.

Suggestions

Replace 'The user should add it to their PATH or create a symlink' with a concrete command (e.g., 'sudo ln -s ~/Sites/minutes/target/release/minutes /usr/local/bin/minutes') to make step 2 fully copy-paste ready.

Add error-recovery guidance after the step-6 verify (e.g., 'If any check still fails, revisit the matching step above and re-run verify') to close the workflow feedback loop.

Soften the hardcoded 'cd ~/Sites/minutes' by instructing Claude to locate the user's minutes repo checkout, and root the cross-skill reference in ${CLAUDE_PLUGIN_ROOT} (as done for the verify script) so the audio-devices.md path resolves reliably.

DimensionReasoningScore

Conciseness

The body is lean — command blocks, a compact model table, and a Gotchas section with no explanations of concepts Claude already knows — but "Walk the user through first-time Minutes setup, step by step" duplicates the H1 and the inline "macOS 26 (Tahoe)" version-specific workaround is the kind of time-sensitive detail the rubric penalizes outside a dedicated section; anchor 4 (minor instances that could be trimmed), not 3 (padding is minimal) or 5 (small redundancies remain).

4 / 5

Actionability

Nearly everything is copy-paste executable ("cargo build --release", "minutes setup --model <chosen-model>", "brew install blackhole-2ch", "minutes record --title \"Test recording\"") with a model-selection table, but "add it to their PATH or create a symlink" gives no concrete command and "cd ~/Sites/minutes" hardcodes an assumed repo location — minor gaps that keep it below fully copy-paste-ready coverage.

4 / 5

Workflow Clarity

A clear 7-step sequence with explicit checkpoints (step 1 checks current state and says "Skip any steps that already pass", step 6 re-runs verify, step 7 tests end-to-end and checks the output file), but there is no error-recovery loop telling Claude what to do when verify still fails after a step — a minor validation gap rather than missing checkpoints.

4 / 5

Progressive Disclosure

Well-organized sections with one clearly signaled one-level reference ("See minutes-record/references/audio-devices.md for the full guide") that appropriately defers deep audio-routing detail, but no bundle files exist in this skill and the referenced path is a relative cross-skill path that cannot be verified against an actual file — minor organization gaps.

4 / 5

Total

16

/

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 with concrete capabilities, exhaustive natural trigger phrasings, and explicit what/when structure in third-person voice. The only weaknesses are unmentioned setup sub-tasks and a verify-failure trigger that slightly overlaps a sibling skill.

DimensionReasoningScore

Specificity

Names three concrete actions ("download whisper model, create directories, configure audio input") that map directly to the body's steps, matching anchor 4 for several specific actions with minor gaps; not 5 because binary building, PATH configuration, and test recording are unmentioned.

4 / 5

Completeness

Explicitly answers both what ("download whisper model, create directories, configure audio input") and when (quoted trigger phrases plus the verify-failure condition), matching the anchor-5 example structure exactly.

5 / 5

Trigger Term Quality

Six natural trigger phrasings ("set up minutes", "install minutes", "first time setup", "configure minutes", "get started with minutes", "how do I start using minutes") including a question form, giving comprehensive coverage of how a user would actually phrase the request.

5 / 5

Distinctiveness Conflict Risk

Triggers are anchored to the product name "minutes" giving a clear niche, but "when verify shows missing components" overlaps the minutes-verify skill's domain — minor overlap risk with a closely related skill rather than minimal conflict.

4 / 5

Total

18

/

20

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.

Validation — 15 / 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.