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.

Quality

91%

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

Quality

Content

88%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 skill body with executable commands and a real validation checkpoint. Slight verbosity in rationale passages and a single-script bundle keep it just short of perfect.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and assumes Claude's competence, with executable commands throughout; a few explanatory passages (the lifetime nudge rationale, gotcha prose) could be trimmed without losing clarity.	4 / 5
Actionability	Fully executable: concrete minutes commands, exact tag_apply.py invocation with flags, and worked note-parsing examples — copy-paste ready and covering the common cases.	5 / 5
Workflow Clarity	Five clearly sequenced phases with explicit validation checkpoint (minutes get parse check in Phase 5), idempotent re-tagging handling, and an error-recovery fallback path.	5 / 5
Progressive Disclosure	Well-structured with clear sections and one real bundle file (scripts/tag_apply.py) referenced and used appropriately; minor gaps as everything lives in SKILL.md plus one script rather than split-out references.	4 / 5
	Total	18 / 20 Passed

Description

95%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: concrete, well-triggered with natural phrases, and explicitly answering both what and when. Only minor room for tightening the action enumeration.

Dimension	Reasoning	Score
Specificity	Names the domain (outcome tagging for meetings) and concrete actions — adding an outcome field, tagging meetings with standard outcomes — though it leans more on describing the task than enumerating distinct operations.	4 / 5
Completeness	Clearly states both what it does (lightweight outcome tagging adding an outcome field) and when to use it with concrete trigger phrases ("Use whenever the user says..."), plus explicit surface-any-time guidance.	5 / 5
Trigger Term Quality	Comprehensive 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") including synonyms across all five tags.	5 / 5
Distinctiveness Conflict Risk	Narrow niche (meeting outcome tagging) with distinct triggers tied to specific outcomes, minimal overlap risk; clearly distinguished from /minutes-mirror and /minutes-debrief.	5 / 5
	Total	19 / 20 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: silverstein/minutes
Path: .agents/skills/minutes/minutes-tag/SKILL.md
Commit: a9a4a8b

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.