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

88%

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

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 tight, operationally precise skill body that gives concrete commands, exact clarification prompts, and a validated hand-off sequence. Weakest on actionability and workflow_clarity where behavioral policy and one placeholder command prevent a top score.

Suggestions

Replace the '--since <cursor>' placeholder with a concrete example value or a one-line note on what a cursor token looks like, so the bounded-read command is fully copy-paste ready.

Add a short numbered summary of the core live-session loop (acknowledge user -> bounded read -> answer in posture -> defer proactive nudges) so the mid-skill workflow is as explicitly sequenced as the hand-off section.

If any posture-specific guidance grows, move the per-posture detail into a referenced file to keep SKILL.md an overview and push progressive_disclosure toward 5.

DimensionReasoningScore

Conciseness

Lean, directive prose that assumes competence and avoids explaining concepts Claude already knows; every section states operational rules (finals vs current_draft, foreground priority, evidence provenance) that earn their place for a genuinely complex live-meeting context.

5 / 5

Actionability

Provides concrete, copy-paste-ready commands ('minutes transcript --status', 'minutes transcript --since 2m --include-current', 'minutes stop') and an exact posture menu, but a meaningful portion is behavioral policy and one argument ('--since <cursor>') is a placeholder rather than a literal value.

4 / 5

Workflow Clarity

Sections form a clear sequence (select surface -> establish contract -> attach -> respect foreground -> end/hand off), and the hand-off section is an explicit numbered list with validation checkpoints (check status, report processing state, wait for finalized artifact before debrief); the mid-skill flow is section-based rather than strictly numbered, leaving minor gaps.

4 / 5

Progressive Disclosure

Well-organized into clearly headed sections with no nested or buried references; all content is appropriately inline because it is needed at runtime during a live meeting, though at ~100 lines it exceeds the under-50-line simple-skill exception that would allow a 5 with sections alone.

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, specific description with explicit what/when trigger guidance and excellent distinctiveness from the sibling minutes-copilot skill. The only weakness is second-person phrasing ('asks you, the terminal agent'), which the rubric penalizes on specificity.

DimensionReasoningScore

Specificity

Enumerates multiple concrete actions ('watch a meeting, follow the live transcript, answer during the call, offer strategist thoughts, silently watch for risks, or track decisions'), which is comprehensive coverage; reduced from 5 to 4 because the description uses second person ('asks you, the terminal agent'), which the rubric penalizes by one specificity point.

4 / 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... to watch a meeting, follow the live transcript...') with concrete trigger phrases and negative boundary guidance.

5 / 5

Trigger Term Quality

Covers natural phrases users would actually say ('watch a meeting', 'follow the live transcript', 'answer during the call', 'silently watch for risks', 'track decisions', 'coach me live') with multiple synonyms and variations across postures.

5 / 5

Distinctiveness Conflict Risk

Clear niche (live sidekick in the current terminal session) explicitly distinguished from the separate Minutes Coach HUD, with routing for the ambiguous 'coach me live' case to minutes-copilot, giving minimal conflict risk.

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.