CtrlK
BlogDocsLog inGet started
Tessl Logo

minutes-x1-send-meeting

Send one of the user's own Minutes meetings to their X1 household for review. Use when the user wants a meeting's summary, decisions, action items, and open questions to reach X1 so they can confirm what belongs in their household record. X1 asks the user to approve the send, and nothing reaches the household record until they confirm each item. Never use it for a restricted meeting, a transcript, or someone else's meeting.

76

Quality

94%

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

96%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.

An excellent operational skill: concrete, executable, and validation-heavy, with explicit stop conditions, feedback loops for every anticipated X1 response, and untrusted-data warnings. Its only structural weakness is that everything lives inline in one longish SKILL.md rather than splitting operational detail into reference files.

DimensionReasoningScore

Conciseness

The body is lean and assumes competence: every line is a domain-specific rule (field mappings, byte limits, idempotency key format, error-message handling) that Claude could not already know. There is no padding or explanation of known concepts, fitting the "every token earns its place" anchor.

5 / 5

Actionability

Fully executable guidance: exact tool names ("Minutes search_meetings", "X1 request_human_confirmation"), a copy-paste JSON argument envelope, a precise idempotencyKey recipe ("mx1:<externalMeetingId>:<clientId>" cut to 110 chars), and per-field mapping rules. The error-response section enumerates the actual X1 messages and the exact bounded retry suffixes (":2 through :5, then :YYYYMMDD").

5 / 5

Workflow Clarity

The six-step sequence is explicit with validation checkpoints throughout: verify mounted capabilities before starting ("Call X1 get_user_capabilities first"), stop on restricted stubs and empty meetings, household-selection rules, idempotent replay handling, and a full fix-once-and-retry feedback loop for invalid-detail errors. Error recovery is enumerated message-by-message.

5 / 5

Progressive Disclosure

Well-sectioned single file (Required connections, Workflow, Handling X1's answers, Boundaries) with no nested or buried references and no bundle files to misplace. It sits just below the 5 anchor because the skill is ~147 lines in one file — the under-50-line well-organized-sections exception doesn't apply — and some operational detail (e.g. the error-response handling) could live in a reference file.

4 / 5

Total

19

/

20

Passed

Description

92%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 description: third person, concrete, with an explicit "Use when" clause and explicit negative triggers that sharply bound when it applies. The only minor gap is a couple of missing natural synonyms a user might say when asking to send or share a meeting.

DimensionReasoningScore

Specificity

The description names several concrete actions — "Send one of the user's own Minutes meetings to their X1 household for review" plus "summary, decisions, action items, and open questions" — giving comprehensive, specific coverage of what the skill moves and where. It is not the level below (4) because it enumerates the full payload rather than listing actions with minor gaps.

5 / 5

Completeness

It explicitly answers both questions: what ("Send one of the user's own Minutes meetings to their X1 household for review" with the item types) and when ("Use when the user wants a meeting's summary, decisions, action items, and open questions to reach X1"), reinforced by negative triggers ("Never use it for a restricted meeting, a transcript, or someone else's meeting").

5 / 5

Trigger Term Quality

Good natural-term coverage: "Minutes meetings", "X1", "meeting", "summary", "decisions", "action items", "household record", "review", "send" — phrases a user would naturally say. It falls short of the 5 anchor only because a few synonymous phrasings users might use (e.g. "share a meeting with X1", "sync") are absent.

4 / 5

Distinctiveness Conflict Risk

It occupies a clear niche — routing the user's own Minutes meetings into their X1 household review queue — anchored by two distinct product names and explicit exclusions, so conflict risk with other skills is minimal.

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.

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.