Skills for Real Engineers. Straight from my .agents directory.
minutes-lint
Agent skill fromsilverstein/minutes
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.
How to install minutes-lint
npx skills add silverstein/minutes# or add only this skill to Claude Code: copy the folder
tooling/skills/sources/minutes-lint/
# into
~/.claude/skills/minutes-lint/ (all projects)
.claude/skills/minutes-lint/ (one project)
1# /minutes-lint23Run a consistency check across policy-authorized normal meetings to find4decision conflicts and stale commitments. Restricted meetings are excluded from5this agent workflow by default and must never be described as absent evidence.67## How to run the lint891. **Run the consistency check**:10 ```bash11 minutes consistency --stale-after-days 1412 ```1314 Optional filters:15 - `--owner <name>` — limit to commitments assigned to a specific person16 - `--stale-after-days <N>` — change the staleness threshold (default: 7)17182. **Parse the JSON output** and present it as readable markdown.1920## Formatting the report2122### Decision Conflicts2324For each conflict, show:2526```27**Topic: {topic}**28- Latest: "{latest decision text}" — *{meeting title}* ({date})29- Prior: "{prior decision text}" — *{meeting title}* ({date})30- **Status**: These decisions may contradict each other.31```3233**Frontmatter v2: resolved supersessions.** When the `resolution` field is34present on a conflict, the newer decision has a `supersedes:` entry in its35frontmatter. Treat this as informational, not a red flag. Format as:3637```38**Topic: {topic}** ✓ Resolved39- Current: "{latest decision text}" — *{meeting title}* ({date})40- Superseded: "{prior decision text}" — *{meeting title}* ({date})41- **Status**: {resolution text}42```4344If the latest decision also carries an `authority` field (`high`/`medium`/`low`),45surface it next to the title. Authority is optional — when absent, omit the tag.46…
Excerpt shown under the repository's MIT license.
More skills in minutes
Similar skill repositories
An agentic skills framework & software development methodology that works.
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
Public repository for Agent Skills
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
