CtrlK
BlogDocsLog inGet started
Tessl Logo

minutes-brief

Fast non-interactive briefing before any meeting — auto-detects your next calendar event, pulls relationship history, surfaces open commitments, and produces a one-page brief in under 30 seconds. Use this whenever the user says "brief me", "give me a quick brief", "what's coming up", "background on my next call", "who am I meeting next", "brief me on Sarah", "I have a call in 10 min", "quick rundown", or right before walking into a meeting. Different from /minutes-prep — brief is the fast hook-fireable version that doesn't ask questions and doesn't set goals. Use brief when speed matters; use prep when the user wants to think hard about goals first.

75

Quality

92%

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

85%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 highly actionable, well-sequenced workflow with strong validation discipline and honest failure handling — nearly everything is copy-paste executable. The weaknesses are a somewhat long single-file layout with no progressive disclosure (the Gotchas and example sections could be split into a reference) and minor padding in the extended example section.

Suggestions

Move the Gotchas section and the extended "Open with" good/bad example into a single one-level-deep reference file (e.g., references/gotchas.md), keeping SKILL.md to the five phases plus a pointer — this would address both progressive_disclosure and conciseness.

Trim the explanatory prose after the good "Open with" example ("The good version is specific (cites Q2 freeze...)" — the contrast with the two bad examples is already self-evident) to cut tokens without losing guidance.

Consolidate the near-duplicate alias-persistence commands in Phase 0 and the Gotchas section into one place, keeping only a pointer at the second mention.

DimensionReasoningScore

Conciseness

The body is dense and operational — commands, contracts, and output templates with almost no generic explanation Claude already knows. But the multi-paragraph "Open with" good/bad tutorial (including the explanation of why the good version is good) and the 15-item Gotchas list contain minor padding that could be trimmed, matching anchor 4 rather than the lean anchor 5.

4 / 5

Actionability

Every phase has copy-paste-ready commands (minutes person/search/get with exact flags, calendar fallbacks including a concrete osascript snippet), an exact output template for the brief, precise slug/permission rules (chmod 700/600, YYYY-MM-DD-first-name.brief.md), and an exact closing line. Fully executable guidance covering the common cases — anchor 5.

5 / 5

Workflow Clarity

Phases 0–5 are clearly sequenced with explicit validation checkpoints and failure feedback loops: "Require exit status 0", "Never suppress a nonzero exit", verify via live-source search before declaring "first meeting on record", "If none return anything, ask once", and silent-exit behavior for hook mode. Matches anchor 5's sequence + checkpoints + error-recovery pattern.

5 / 5

Progressive Disclosure

The 205-line body is well-sectioned into phases, but everything is inline in a single file with no reference split at all — the extended Open-with tutorial, the detailed slug rules, and the long Gotchas list are candidates for a one-level-deep reference file. This matches anchor 3 (some structure, content that should be separate is inline) rather than 4, since no appropriately-split reference material exists.

3 / 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.

An exemplary description: concrete third-person capability statements, a rich set of natural trigger phrases, explicit when-to-use and when-not-to-use guidance, and explicit differentiation from the sibling /minutes-prep skill. Nothing material is missing or vague.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions — "auto-detects your next calendar event, pulls relationship history, surfaces open commitments, and produces a one-page brief in under 30 seconds" — with comprehensive coverage of what the skill does, matching the anchor-5 example. It is not a 4 because there are no gaps in the capability enumeration; every core function is named with a concrete verb.

5 / 5

Completeness

Explicitly answers "what" (first sentence of concrete capabilities) and "when" ("Use this whenever the user says...") with concrete trigger phrases, plus a when-not-to clause ("use prep when the user wants to think hard about goals first"). Matches anchor 5 exactly; the 'Use when' cap of 3 clearly does not apply.

5 / 5

Trigger Term Quality

Nine quoted natural trigger phrases ("brief me", "give me a quick brief", "what's coming up", "background on my next call", "who am I meeting next", "brief me on Sarah", "I have a call in 10 min", "quick rundown", "right before walking into a meeting") cover synonyms, name-argument variants, and urgency variants a user would actually say. Matches anchor 5's comprehensive natural-term coverage.

5 / 5

Distinctiveness Conflict Risk

"Different from /minutes-prep — brief is the fast hook-fireable version that doesn't ask questions and doesn't set goals" plus "Use brief when speed matters; use prep when..." explicitly disambiguates from the only sibling skill. Clear niche with distinct triggers and minimal conflict risk; not a 4 because the one close neighbor is already explicitly fenced off.

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.