This runs a consistency check across your meeting notes to surface decision conflicts and overdue action items. It flags when two meetings reached different conclusions on the same topic, shows commitments that have gone stale past a threshold you set, and can filter by person or staleness window. The conflict detection is topic based, so it will flag intentional reversals alongside genuine contradictions. You'll need to use judgment to tell which is which. Useful when your meeting corpus gets large enough that you're not sure if last week's pricing decision contradicts the one from last month, or when you want to audit who's sitting on overdue tasks. Outputs JSON that you format into a readable report.

GitHub stars
1.3K
last updated
Jun 11, 2026

Install

$ npx -y skills add silverstein/minutes --skill minutes-lint --agent claude-code

Installs into .claude/skills of the current project.

Files

/minutes-lint

Run a consistency check across policy-authorized normal meetings to find decision conflicts and stale commitments. Restricted meetings are excluded from this agent workflow by default and must never be described as absent evidence.

How to run the lint

  1. Run the consistency check:

    minutes consistency --stale-after-days 14
    

    Optional filters:

    • --owner <name> — limit to commitments assigned to a specific person
    • --stale-after-days <N> — change the staleness threshold (default: 7)
  2. Parse the JSON output and present it as readable markdown.

Formatting the report

Decision Conflicts

For each conflict, show:

**Topic: {topic}**
- Latest: "{latest decision text}" — *{meeting title}* ({date})
- Prior: "{prior decision text}" — *{meeting title}* ({date})
- **Status**: These decisions may contradict each other.

Frontmatter v2: resolved supersessions. When the resolution field is present on a conflict, the newer decision has a supersedes: entry in its frontmatter. Treat this as informational, not a red flag. Format as:

Sponsors

Details

Repository
github.com/silverstein/minutes
Categories
Code Review & Quality, Productivity & Planning
License
MIT
First seen
Jun 11, 2026

More from silverstein/minutes

All 19
1spencermarx avatarPair Programmingspencermarx/open-code-reviewAI-assisted pair programming with multiple modes (driver/navigator/switch), real-time verification, quality monitoring, and comprehensive testing. Supports TDD,0skills.sh installs
2tugtool avatartug-refactortugtool/tugtool|0skills.sh installs
3tzachbon avatarralph-specum-refactortzachbon/smart-ralphThis is a specialized coordinator for updating Ralph Specum spec artifacts after you've learned something during implementation.0skills.sh installs
4VilnaCRM-Org avatarquality-standardsVilnaCRM-Org/user-serviceOverview of protected quality thresholds and quick reference for all quality tools. Use when you need to understand quality metrics, run comprehensive quality c0skills.sh installs
5emilkowalski avatarreview-animationsemilkowalski/skillsReviews animation and motion code against a high craft bar derived from Emil Kowalski's design engineering philosophy. Default to flagging; approval is earned.295.2Kskills.sh installs
6obra avatarrequesting-code-reviewobra/superpowersUse when completing tasks, implementing major features, or before merging to verify work meets requirements276.5Kskills.sh installs