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.

72

Quality

88%

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

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-structured, highly actionable setup guide with clear sequencing and built-in verification. Main weaknesses are minor conciseness trim opportunities and the absence of an explicit verify-failure feedback loop.

Suggestions

Add an explicit feedback loop after step 6: "If verify reports failures, return to the failing step and re-run it before testing recording."

Trim hand-holding prose such as "This is a known Apple SDK issue" and "The binary lands at target/release/minutes" to tighten token efficiency.

Clarify the model-selection command by showing a concrete example (e.g. `minutes setup --model small`) alongside the placeholder.

DimensionReasoningScore

Conciseness

Largely lean with purposeful code blocks and a useful Gotchas section, but a few prose lines ("The binary lands at target/release/minutes", "This is a known Apple SDK issue") hand-hold slightly beyond what Claude needs, keeping it just below the every-token-earns-its-place anchor 5.

4 / 5

Actionability

Copy-paste-ready commands throughout (cargo build, minutes setup --model, mkdir, brew install, minutes record/stop) plus a concrete model-selection table; the only non-code step (Audio MIDI Setup) is inherently GUI and given as explicit manual actions.

5 / 5

Workflow Clarity

Seven clearly numbered steps with validation checkpoints (verify at start in step 1, verify again in step 6, test recording in step 7) and skip-if-pass logic, but lacks an explicit error-recovery feedback loop ("if verify fails, return to step X"), which the anchor-5 example requires.

4 / 5

Progressive Disclosure

Well-organized into numbered sections with one clearly signaled one-level-deep reference ("See minutes-record/references/audio-devices.md for the full guide"); no bundle files exist within this skill, and the ~90-line single-file body is appropriately scoped, so it sits at good-structure anchor 4 rather than the multi-reference anchor 5.

4 / 5

Total

17

/

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: concise, concrete, and explicit about both capability and trigger conditions with abundant natural synonyms. The only minor gap is that the action list is good rather than comprehensive.

DimensionReasoningScore

Specificity

Lists three concrete actions — "download whisper model, create directories, configure audio input" — matching the anchor-4 example of several specific actions, but not the comprehensive four-action coverage of anchor 5.

4 / 5

Completeness

Explicitly answers both what ("Guided first-time setup for Minutes — download whisper model, create directories, configure audio input") and when ("Use when the user says...") with concrete trigger phrases, matching the anchor-5 example.

5 / 5

Trigger Term Quality

Comprehensive natural-language triggers with many synonyms ("set up minutes", "install minutes", "configure minutes", "get started with minutes", "how do I start using minutes") plus a state-based trigger ("when verify shows missing components"); no file-extension equivalent applies to a setup task.

5 / 5

Distinctiveness Conflict Risk

Targets a clear niche (first-time setup of the specific Minutes app) with distinct triggers, so minimal risk of firing for an unrelated skill.

5 / 5

Total

19

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

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.