CtrlK
BlogDocsLog inGet started
Tessl Logo

minutes-tag

Lightweight outcome tagging for meetings — won, lost, stalled, great, or noise. Use whenever the user says "tag this meeting", "mark that as a win", "that one was a loss", "tag yesterday's call as stalled", "mark this great", "that meeting was noise", "label that meeting", or any time they describe a meeting outcome in passing. Tagging takes 5 seconds and unlocks /minutes-mirror correlation analysis — the more meetings get tagged, the smarter mirror gets at telling the user what behavior patterns lead to wins. Surface this skill any time the user mentions a meeting result, win, loss, or wasted time.

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%

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 checkpoints and an appropriately referenced helper script. The only weakness is moderate redundancy of the speed messaging and light promotional padding.

Suggestions

Consolidate the repeated "speed is the feature" rationale into the opening and Gotchas once, removing the restatements in Phases 1, 2, 3, and 5.

Trim the promotional phrasing ("Tagging takes 5 seconds", "the smarter mirror gets at telling the user what behavior patterns lead to wins") to factual capability descriptions.

DimensionReasoningScore

Conciseness

Mostly efficient and free of concepts Claude already knows, but the "speed is the entire feature" message is repeated across Phase 1, 2, 3, 5, and Gotchas, and promotional phrasing ("Tagging takes 5 seconds", "the smarter mirror gets") could be tightened.

2 / 3

Actionability

Fully executable guidance throughout: exact bash commands (minutes list/search, python3 tag_apply.py with precise flags), concrete AskUserQuestion options, and copy-paste-ready note-parsing examples — matching the top anchor.

3 / 3

Workflow Clarity

Five clearly sequenced phases with an explicit validation checkpoint in Phase 5 (minutes get ... | head -3), error-recovery guidance for malformed frontmatter, and idempotent nudge state via a marker file — matching the top anchor with feedback loops.

3 / 3

Progressive Disclosure

Well-organized into clear phases and a Gotchas section, with the single helper script (scripts/tag_apply.py, verified present) referenced one level deep via an exact path; appropriate for a single-purpose skill per the simple-skills scoring note.

3 / 3

Total

11

/

12

Passed

Description

100%

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 trigger guidance, concrete tag vocabulary, and a clear niche distinct from sibling minutes skills. Voice is correctly third person throughout.

DimensionReasoningScore

Specificity

Lists concrete actions and the full set of outcome tags — "Lightweight outcome tagging for meetings — won, lost, stalled, great, or noise" — naming multiple specific capabilities rather than vague language.

3 / 3

Completeness

Explicitly answers both what (outcome tagging with the five standard tags) and when ("Use whenever the user says..." plus "Surface this skill any time the user mentions a meeting result, win, loss, or wasted time"), satisfying the top anchor with explicit triggers.

3 / 3

Trigger Term Quality

Dense coverage of natural phrases users would say ("tag this meeting", "mark that as a win", "that one was a loss", "tag yesterday's call as stalled", "mark this great", "that meeting was noise", "label that meeting"), matching the top anchor for natural-term coverage.

3 / 3

Distinctiveness Conflict Risk

Occupies a clear niche (meeting outcome tagging) with distinct triggers and explicit references to sibling skills (/minutes-mirror, /minutes-debrief), making conflict with other skills unlikely.

3 / 3

Total

12

/

12

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.