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.

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

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

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 well-structured, operational behavioral skill with concrete commands, explicit postures, validation-gated handoff, and strong evidence-handling discipline. It is tight and actionable, with only minor conciseness trims and a reactive (rather than linearly sequenced) core operating mode preventing a perfect content score.

DimensionReasoningScore

Conciseness

The body is dense but almost entirely operational (postures, commands, Never-list, handoff) with little concept-padding Claude already knows; a few explanatory clauses such as "Recording additionally creates durable media...it is not a transcript-later-only mode" could be trimmed, so it sits at efficient-with-minor-trim rather than every-token-earns-its-place.

4 / 5

Actionability

Copy-paste-ready commands cover the common cases ("minutes transcript --status", "minutes transcript --since 2m --include-current", the --include-current fallback, "minutes stop", "minutes status"), four named postures are concrete, and the 5-step handoff is fully specified; not 4 because the commands are executable and cover the common cases without real gaps.

5 / 5

Workflow Clarity

The handoff is a clear sequenced workflow with an explicit validation gate ("Wait for the finalized meeting artifact" then "Once finalization is confirmed, use /minutes-debrief") and the evidence section has replace-draft feedback loops, and `minutes stop` is guarded by a direct-user-request check; not 5 because the primary operating mode is reactive/event-driven rather than one coherent sequenced workflow with checkpoints throughout.

4 / 5

Progressive Disclosure

No bundle files exist; the single SKILL.md is organized into eight clearly labeled H2 sections (Select the surface, Establish the contract, Attach, Respect foreground priority, Treat context as evidence, Handle speakers, Stay useful, End and hand off) with easy navigation, and the behavioral content is appropriately self-contained — splitting would reduce usability rather than aid discovery; not 4 because there are no real organization gaps.

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 excellent description that concretely states the skill's role, enumerates specific operating postures as natural trigger phrases, and explicitly answers both what and when while cleanly disambiguating the sibling minutes-copilot skill. It is dense but every clause serves trigger guidance or boundary clarity.

DimensionReasoningScore

Specificity

Lists multiple specific concrete actions — "watch a meeting, follow the live transcript, answer during the call, offer strategist thoughts, silently watch for risks, or track decisions" — with comprehensive coverage of the sidekick's operating modes, matching the score-5 anchor; not 4 because coverage is comprehensive rather than having minor gaps.

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 you...") with concrete trigger phrases, plus a "Do not use..." boundary; not 4 because both what and when are concrete and explicit.

5 / 5

Trigger Term Quality

Natural user-facing phrases ("watch a meeting", "follow the live transcript", "answer during the call", "track decisions", "coach me live") with synonyms (watch/follow/answer) give comprehensive coverage; not 4 because common variations are present rather than a few missing.

5 / 5

Distinctiveness Conflict Risk

Clear niche (live sidekick in the terminal session) with an explicit disambiguation from minutes-copilot/Coach HUD and an ambiguous-request clarification, giving minimal conflict risk; not 4 because the boundary is explicit rather than having minor overlap.

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.

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.