CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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.

72

Quality

91%

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

81%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 operational skill: exact commands, explicit fail-closed validation rules, and a concrete output template. Its main weakness is conciseness — the Gotchas section re-states several rules already given in the phases, and version-pinned CLI contract details are inlined rather than isolated.

Suggestions

De-duplicate rules repeated between the phases and Gotchas ("Hooks should never spam the user", alias set-alias commands, chmod 600/privacy, "never invent history") — state each rule once and keep Gotchas for genuinely new edge cases only.

Move the version-pinned CLI stream-handling contract ("Today (0.8.0)") into a dedicated CLI-contract reference file or an 'old patterns' section so version churn does not age the skill body.

Drop the contributor-facing maintenance instruction ("update this skill in the same PR that ships the CLI change") from the runtime skill body — it guides skill maintainers, not skill execution.

DimensionReasoningScore

Conciseness

The body is mostly operational, but several points are stated twice — "Hooks should never spam the user" appears in Phase 0 and again in Gotchas, the alias `set-alias` commands appear in Phase 0 and Gotchas, "chmod 600"/privacy appears in Phase 4 and Gotchas, and "never invent history" appears in both the Phase 3 rules and Gotchas. It also embeds time-sensitive version information ("Today (0.8.0)") and a contributor-facing maintenance instruction ("update this skill in the same PR that ships the CLI change") inline, which fits the 3 anchor (mostly efficient but could be tightened) rather than 4. It is not a 2 because nothing explains concepts Claude already knows — every section is skill-specific operational detail.

3 / 5

Actionability

Fully executable, copy-paste-ready guidance throughout: exact commands ("minutes search \"<name>\" --limit 10 --since <60-days-ago> --format json"), an MCP call signature, exact save paths and slug rules with worked examples ("María José Pérez → maria"), and a complete brief template with a good-vs-bad "Open with" example. Matches the 5 anchor; common cases are covered concretely.

5 / 5

Workflow Clarity

Phases 0–5 are clearly sequenced with explicit validation checkpoints ("require exit status 0 before interpreting their output", "Any nonzero exit from a live-source command means the source is unavailable") and error-recovery paths (ordered calendar fallbacks, "If none return anything, ask once", silent exit in --auto mode, verify before claiming "first meeting on record"). Matches the 5 anchor with feedback loops and a gotcha checklist; no destructive or batch operations exist to trigger the cap.

5 / 5

Progressive Disclosure

No bundle files exist (references/, scripts/, assets/ are all absent), and the ~190-line body is a single self-contained file with clean phase headers and well-placed code blocks — good structure with minor organization gaps, matching the 4 anchor. It is not a 5 because there is no reference structure at all and some content (CLI stream contracts, detailed slug rules, the 15-bullet Gotchas list) could be split into a reference file; it is not a 3 because headers are clear and placement is appropriate for a speed-critical single-shot skill.

4 / 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 action list, explicit 'Use this whenever' trigger guidance with many natural user phrases, and explicit disambiguation against the sibling /minutes-prep skill. Slight redundancy in stating the prep/brief distinction twice does not reduce any dimension's anchor fit.

DimensionReasoningScore

Specificity

The description lists four concrete actions — "auto-detects your next calendar event, pulls relationship history, surfaces open commitments, and produces a one-page brief in under 30 seconds" — which comprehensively covers the detect→gather→synthesize flow. This matches the 5 anchor (multiple specific concrete actions, comprehensive coverage); it is not a 4 because there are no coverage gaps for a briefing skill.

5 / 5

Completeness

It explicitly answers both what ("pulls relationship history, surfaces open commitments, and produces a one-page brief") and when ("Use this whenever the user says 'brief me' … or right before walking into a meeting") with concrete trigger phrases. This is an exact match for the 5 anchor; a 4 would require the when-clause to be less explicit, which it is not.

5 / 5

Trigger Term Quality

It quotes a comprehensive set of natural user phrases — "brief me", "give me a quick brief", "what's coming up", "background on my next call", "who am I meeting next", "I have a call in 10 min", "quick rundown" — including synonyms and situational variants. This matches the 5 anchor; a 4 would require missing common variations, and none are obviously absent.

5 / 5

Distinctiveness Conflict Risk

It explicitly disambiguates from the nearest sibling skill — "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" — giving a clear niche with distinct triggers and minimal conflict risk, matching the 5 anchor. It is not a 4 because the one real overlap risk (prep vs. brief) is directly resolved with a usage rule.

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.

Validation — 15 / 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

Path

tooling/skills/goldens/claude/minutes-brief/SKILL.md

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.