Skills for Real Engineers. Straight from my .agents directory.
minutes-tag
Agent skill fromsilverstein/minutes
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.
How to install minutes-tag
npx skills add silverstein/minutes# or add only this skill to Claude Code: copy the folder
tooling/skills/sources/minutes-tag/
# into
~/.claude/skills/minutes-tag/ (all projects)
.claude/skills/minutes-tag/ (one project)
1# /minutes-tag23Lightweight outcome tagging — adds an `outcome:` field to a meeting's frontmatter so `/minutes-mirror` can correlate the user's behavior with their results over time.45The whole point of this skill is **speed**. Tagging should take 5 seconds, not 5 questions. Don't be precious about it — most users will never adopt tagging if it feels like data entry.67## How it works89### Phase 1: Identify the meeting1011Three patterns the user might use. **Always filter to meetings, not voice memos** — voice memos can't be "won" or "lost".1213**1. Most recent** ("tag this meeting", "mark that as a win", "tag the call I just finished"):14```bash15minutes list --content-type meeting --limit 116```17Use the most recent. **Don't ask which one** — that defeats the speed promise. The default behavior should always be "the call you just had".1819**2. By date** ("tag yesterday's call", "tag the Tuesday call"):20```bash21minutes list --content-type meeting --limit 1022```23Pick the meeting matching the date. If multiple meetings match the same day, ask once: "You had <N> meetings <date>. Which one?" with options listing titles.2425**3. By name** ("tag my call with Sarah as a win"):26```bash27minutes search "<name>" --content-type meeting --limit 528```29Pick the most recent. If ambiguous, ask once.3031### Phase 2: Identify the tag3233If the user already named the outcome in their message ("tag that as a win"), use it directly. Don't ask again — they already told you.34…
Excerpt shown under the repository's MIT license.
More skills in minutes
Similar skill repositories
Public repository for Agent Skills
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
Production-grade engineering skills for AI coding agents.
The 1st Collaborative AI Design Agent Workspace. Local-first and open source. Create motion, prototypes, websites, apps, dashboards, presentations, images, and videos with your team and AI agents. Share work, exchange feedback, and iterate together in one workspace.
Turn any idea, plan, or codebase into a beautiful interactive diagram. An agent skill for Claude Code, Codex, and more.
