CtrlK
BlogDocsLog inGet started
Tessl Logo

minutes-copilot

Start and control Minutes Coach, the separate real-time copilot HUD, with an explicit meeting goal. Use only for explicit Coach or HUD lifecycle requests such as "start Minutes Coach", "open the Coach HUD", "pause Minutes Coach", "resume Minutes Coach", "Minutes Coach status", or "stop Minutes Coach". Do not use for requests that explicitly ask the current terminal agent to watch or strategize; those belong to minutes-live-sidekick. An ambiguous request such as "coach me live" requires one short surface clarification and must not automatically start Coach.

75

Quality

93%

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

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, action-oriented skill body: exact CLI commands, verbatim clarification scripts, and strong guardrails with no fluff. The only weaknesses are the minor mismatch between the mode-selection step and the hardcoded mode in the start command, and the absence of an explicit post-start verification step.

Suggestions

Make the start command template reflect step 2 by using "--mode <mode>" (with generic as the stated default) instead of hardcoding "--mode generic".

Add an explicit verification checkpoint after start, e.g. run "minutes copilot status" and only report the one-line success message once an active session is confirmed.

Clarify how to detect that first-party MCP controls are "actually available" (e.g., check the tool list) so the MCP-vs-CLI branch is deterministic.

DimensionReasoningScore

Conciseness

The ~40-line body is entirely directive — exact commands, exact clarification wording, and guardrails — with no explanation of concepts Claude already knows and no padded sections. Every token earns its place.

5 / 5

Actionability

Guidance is mostly executable: the start command and the four control commands are copy-paste ready, and clarification questions are given verbatim. However, the start example hardcodes "--mode generic" while step 2 instructs choosing a supported mode, and the MCP path deliberately names no tool, leaving minor gaps versus the fully-executable anchor.

4 / 5

Workflow Clarity

The start flow is a clear numbered sequence with a double-start guard ("Do not start a second session when minutes copilot status reports one active") and a failure path for provider unavailability. It falls short of the 5 anchor because there is no explicit post-start verification checkpoint confirming the session actually came up.

4 / 5

Progressive Disclosure

A simple, under-50-line, single-purpose skill with no need for external references; sections (Start Coach, Control an active session, Output, Guardrails) are well-organized, which merits a 5 under the simple-skill guideline. No bundle files exist or are needed.

5 / 5

Total

18

/

20

Passed

Description

100%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.

An exemplary description: it states the skill's concrete lifecycle actions, gives literal user-facing trigger phrases, and cleanly separates itself from the sibling live-sidekick skill with an explicit ambiguity rule. Third-person voice is used and there is no padding.

DimensionReasoningScore

Specificity

The description lists multiple concrete lifecycle actions — "Start and control Minutes Coach" plus enumerated commands "start", "pause", "resume", "status", "stop" — giving comprehensive coverage of the skill's scope with no gaps, matching the comprehensive-coverage anchor rather than the minor-gaps anchor.

5 / 5

Completeness

It explicitly answers both what ("Start and control Minutes Coach, the separate real-time copilot HUD, with an explicit meeting goal") and when ("Use only for explicit Coach or HUD lifecycle requests such as...") with concrete trigger phrases, and adds an explicit when-not clause.

5 / 5

Trigger Term Quality

It quotes the literal phrases a user would naturally say ("start Minutes Coach", "open the Coach HUD", "pause Minutes Coach", "Minutes Coach status", "stop Minutes Coach") and even covers the ambiguous variant "coach me live", providing comprehensive natural-term coverage including synonyms (Coach/HUD).

5 / 5

Distinctiveness Conflict Risk

It carves out a clear niche with distinct triggers, explicitly routes the overlapping case to "minutes-live-sidekick", and defines disambiguation behavior for ambiguous requests, so conflict risk is minimal.

5 / 5

Total

20

/

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.

Validation — 16 / 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.