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.

72

Quality

89%

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

78%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.

The body is a tightly written, self-contained set of behavioral rules with real commands, a validation-gated hand-off checklist, and explicit safety boundaries. It is slightly verbose in places and relies on instructive prose for postures, keeping conciseness, actionability, and workflow clarity at 4 while progressive disclosure is maximal.

DimensionReasoningScore

Conciseness

The body is efficient and assumes Claude's competence throughout, but a few clauses restate safety rationale at length (e.g., the full 'Never' list and the proactive-update precondition) that could be trimmed slightly without losing clarity.

4 / 5

Actionability

Concrete executable commands are present (`minutes transcript --status`, `--since 2m --include-current`, `minutes stop`) with real fallback handling, but the posture and speaker-correction guidance is instructive rather than scripted, leaving minor execution gaps.

4 / 5

Workflow Clarity

The end-and-hand-off section is a well-sequenced 5-step checklist with explicit validation (wait for finalized artifact before debriefing) and the transcript-evidence section has clear checkpoints; it is not quite a 5 because the upfront surface-selection/contract flow has implicit ordering rather than an explicit validation gate.

4 / 5

Progressive Disclosure

The single SKILL.md is a lean overview with clear section headers and no nested file references; for a self-contained skill under 50 lines with no external references needed, this well-organized structure meets the 5-anchor simple-skill exception.

5 / 5

Total

17

/

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.

The description is exemplary: it states concrete capabilities, gives natural trigger phrases, answers both 'what' and 'when', and proactively disambiguates against the related minutes-copilot skill. It earns top marks across all four dimensions.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'follow the live transcript, answer during the call, offer strategist thoughts, silently watch for risks, or track decisions' — covering the skill's capabilities comprehensively rather than abstract language.

5 / 5

Completeness

Explicitly answers 'what' (act as the live meeting sidekick) and 'when' (a 'Use when' clause enumerating trigger conditions) plus a clear 'Do not use' boundary, matching the 5-anchor pattern.

5 / 5

Trigger Term Quality

Captures the natural phrasings a user would say — 'watch a meeting', 'follow the live transcript', 'answer during the call', 'coach me live' — with good synonym coverage and an explicit ambiguous-case example.

5 / 5

Distinctiveness Conflict Risk

The description carves a clear niche and explicitly routes Coach/HUD lifecycle requests to minutes-copilot, with an ambiguity clause, minimizing conflict with the sibling skill.

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.