Health-check your meeting knowledge for contradictions, stale commitments, and decision conflicts. Use when the user asks "any conflicts in my meetings", "check for stale action items", "lint my meetings", "consistency check", "are there contradictions", or wants to audit their decision history.
npx skills add https://github.com/silverstein/minutes --skill 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.
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)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:
**Topic: {topic}** ✓ Resolved
- Current: "{latest decision text}" — *{meeting title}* ({date})
- Superseded: "{prior decision text}" — *{meeting title}* ({date})
- **Status**: {resolution text}
If the latest decision also carries an authority field (high/medium/low),
surface it next to the title. Authority is optional — when absent, omit the tag.
For each stale item, show:
- [ ] **@{who}**: {task} (due {due_date}, {age_days} days overdue)
- Last discussed: *{meeting title}* ({date})
If no conflicts and no stale commitments, say: "No decision conflicts or stale commitments found across your meetings. Everything looks consistent."
/minutes-debrief on the most recent conflicting meeting, or /minutes-search "{topic}" to review the full decision historyminutes commitments --json; treat a nonzero exit as unavailable, never emptygraph.db (it does not exist)Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation
Use when completing tasks, implementing major features, or before merging to verify work meets requirements
Execute git commit with conventional commit message analysis, intelligent staging, and message generation. Use when user asks to commit changes, create a git commit, or mentions "/commit". Supports: (1) Auto-detecting type and scope from changes, (2) Generating conventional commit messages from diff, (3) Interactive commit with optional type/scope/description overrides, (4) Intelligent file staging for logical grouping
Comprehensive GitHub code review with AI-powered swarm coordination
Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.
Use this skill to review code. It supports both local changes (staged or working tree) and remote Pull Requests (by ID or URL). It focuses on correctness, maintainability, and adherence to project standards.
Refactor bloated AGENTS.md, CLAUDE.md, or similar agent instruction files to follow progressive disclosure principles. Splits monolithic files into organized, linked documentation.
Create high-quality git commits: review/stage intended changes, split into logical commits, and write clear commit messages (including Conventional Commits). Use when the user asks to commit, craft a commit message, stage changes, or split work into multiple commits.
Take silverstein/minutes-lint from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.