CtrlK
BlogDocsLog inGet started
Tessl Logo

minutes-live-sidekick

Act as the user's live meeting sidekick inside the current terminal agent session. Use when the user explicitly asks you, the terminal agent, to watch a meeting, follow the live transcript, answer during the call, offer strategist thoughts, silently watch for risks, or track decisions. Do not use this skill to start or control the separate Minutes Coach HUD; explicit Coach or HUD lifecycle requests belong to minutes-copilot, and an ambiguous request such as "coach me live" requires one short surface clarification.

71

Quality

87%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

The canonical home for this skill is minutes-live-sidekick in silverstein/minutes

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 well-organized instruction skill with concrete commands, explicit postures, and a sequenced, checkpointed hand-off workflow. It is concise and assumes competence, with only minor redundancy and conditional-host caveats keeping it from the top anchor.

Suggestions

Reduce repetition of 'directly typed user request' phrasing across the foreground-priority, evidence, and hand-off sections by stating the rule once and back-referencing it.

Add a short note clarifying behavior when the host does not expose the documented minutes commands, so actionability does not depend on an assumed tool surface.

Tighten the 'End and hand off' step into an explicit validate-wait-recheck loop to match the strongest workflow-clarity anchor.

DimensionReasoningScore

Conciseness

Lean body that assumes Claude's competence and avoids concept over-explanation, with minor redundancy (the 'directly typed user request' phrasing recurs across sections) that could be tightened; not 5 due to that repetition, not 3 since most tokens earn their place.

4 / 5

Actionability

Provides concrete executable commands ('minutes transcript --status', '--since 2m', 'minutes stop', 'minutes status') and enumerated postures, with minor gaps around host-adapter availability; not 5 because some guidance is conditional on host capabilities, not 3 since the core commands are concrete and executable.

4 / 5

Workflow Clarity

The 'End and hand off' section is a clear numbered sequence with validation checkpoints (check status, report state, wait for finalized artifact before debrief); not 5 because the feedback/retry loop is lighter than the validate-fix-revalidate anchor, not 3 since checkpoints are explicit.

4 / 5

Progressive Disclosure

Self-contained, well-sectioned single file with clearly signaled sibling-skill references and no nested bundle references (none exist); not 5 only because organization is solid but not a textbook overview-with-one-level-deep split, not 3 since structure is clear and nothing is buried.

4 / 5

Total

16

/

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.

A strong, concrete description that states a clear niche, enumerates specific actions, supplies natural trigger phrases, and explicitly disambiguates from a sibling skill. Both 'what' and 'when' are explicit, with conflict risk actively minimized.

DimensionReasoningScore

Specificity

Lists multiple concrete actions ('watch a meeting, follow the live transcript, answer during the call, offer strategist thoughts, silently watch for risks, or track decisions'), matching the comprehensive-coverage anchor; it is not the level below since it goes well beyond 1-2 actions.

5 / 5

Completeness

Explicitly answers both what ('Act as the user's live meeting sidekick inside the current terminal agent session') and when ('Use when the user explicitly asks...'), with concrete trigger phrases; not below since both are explicit, not weakly implied.

5 / 5

Trigger Term Quality

Covers natural user phrases including synonyms ('watch a meeting,' 'follow the live transcript,' 'coach me live'), matching the comprehensive natural-term anchor rather than the few-terms-missing level below.

5 / 5

Distinctiveness Conflict Risk

Clear niche with explicit disambiguation from minutes-copilot and handling of ambiguous 'coach me live', matching the minimal-conflict-risk anchor; not below because triggers are distinct, not merely mostly distinct.

5 / 5

Total

20

/

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.

Validation15 / 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.