meeting-brief

Daily meeting preparation system that checks your calendar each morning, deeply researches external attendees (LinkedIn, company info, GitHub, past notes), and sends you personalized briefs via email (1 per person). Use when you want automated preparation for upcoming meetings with context about each person you're meeting.

Quality

73%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/sales/composites/meeting-brief/SKILL.md

Quality

Content

62%

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-structured skill body with real bundled scripts and concrete commands, weakened mainly by verbosity (duplicate research section, full example brief/JSON) and a monolithic structure that underuses progressive disclosure and lacks a validate-before-send loop for its email-sending workflow.

Suggestions

Move the full example brief and example research JSON into a references/ file (e.g. EXAMPLES.md) and link to it from the body to cut tokens and improve progressive disclosure.

Remove the duplicate research-process description or merge "Research Process" into step 3 of "How It Works".

Add an explicit validate/dry-run checkpoint before the email-send step (e.g. "Send only after confirming DRY_RUN brief output looks correct") to strengthen the feedback loop.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and well-organized, but padded with a full 30-line example brief, a complete example research JSON, and the research process described twice (in "How It Works" and again in "Research Process") — content that could be trimmed or moved.	2 / 3
Actionability	Provides concrete executable commands ("node scripts/research_person.js ...", "./scripts/run_daily.sh", "gcalcli agenda today tomorrow") plus a complete config example and a real file-tree; all referenced scripts (run_daily.sh, check_calendar.sh, research_person.js, generate_brief.js, send_slack.sh) exist in ./scripts/.	3 / 3
Workflow Clarity	The 7-step run_daily workflow is clearly sequenced, but for an outward-facing/destructive operation (sending emails to your inbox) validation checkpoints are weak — only DRY_RUN and post-hoc dedup logs are mentioned, with no explicit validate-before-send feedback loop.	2 / 3
Progressive Disclosure	SKILL.md is a ~300-line monolith: the example brief, example research JSON, and detailed brief-format sections are inline content that would be better split into reference files; no one-level-deep references are provided.	2 / 3
	Total	9 / 12 Passed

Description

85%

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 specific, complete description with explicit what-and-when structure and a clear niche. Trigger phrasing is the weakest dimension — it could capture more natural ways users would request daily meeting prep.

Suggestions

Add more natural trigger variations, e.g. "Use when preparing for meetings, briefing yourself on attendees, or getting context before calls".

Consider tightening the long parenthetical research list to keep the description scannable.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "checks your calendar each morning", "deeply researches external attendees (LinkedIn, company info, GitHub, past notes)", "sends you personalized briefs via email (1 per person)" — matching the highest anchor.	3 / 3
Completeness	Clearly answers what (checks calendar, researches attendees, sends briefs) and when with an explicit "Use when you want automated preparation for upcoming meetings with context about each person you're meeting" trigger clause.	3 / 3
Trigger Term Quality	Uses some natural terms ("calendar", "meetings", "external attendees", "briefs", "meeting preparation"), but the trigger phrasing ("automated preparation for upcoming meetings with context about each person") is generic and misses common variations users would say (e.g. "prep for my meetings", "who am I meeting today").	2 / 3
Distinctiveness Conflict Risk	The combined daily-cron + attendee-research + per-person-email-brief niche is distinct with specific triggers ("each morning", "external attendees", "1 per person"), making conflict with other skills unlikely.	3 / 3
	Total	11 / 12 Passed

Validation

100%

Warnings & errors only

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: gooseworks-ai/goose-skills
Path: skills/sales/composites/meeting-brief/SKILL.md
Commit: 8866b2a

Reviewed: 1 day ago

Table of Contents

Discovery Implementation Validation

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.