By eins78
Agent skills collection: session management, TypeScript patterns, Chrome CDP, tmux, Apple integrations
Convene a council of ~4 frontier models via the OpenRouter API for independent parallel reviews of a PR, plan doc, or files, then synthesize agreements and dissents in-session. Use for high-stakes or contested changes, before irreversible decisions, or when one extra model's opinion is not enough — costs real money per run. Triggers on /ai-council-review, "council review", "panel review", "multi-model review", "review with multiple models", "ask several models", "get a third opinion", "high-stakes review", "openrouter review". For a quick single-model second opinion, use ai-review instead.
Get AI code review from a second model (Gemini/OpenAI) mid-session via CLI. Use when asked to review code, get a second opinion, check quality, or verify implementation — especially in unfamiliar stacks. Triggers on /ai-review, "review this", "get a second opinion", "check with another model".
Read email via Apple Mail.app and AppleScript. Use when asked to check, search, or read emails. READ ONLY — no sending or modifying emails.
Read Apple Notes via AppleScript. Use when asked to check, search, or read notes. READ ONLY — no creating or modifying notes.
Use when decisions happen async — reviewer(s) look at it over chat, on a PR, on a train, or any time outside the agent session. Triggers: async decision, PR review, pull request, remote reviewer, handoff, away-from-keyboard, decision ballot, architecture call, architecture decision record, ADR, hiring panel, vendor selection, household decision, reconcile, per-reviewer, tick box, ballot.
Modifies files
Hook triggers on file write and edit operations
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Collection of Agent Skills for Claude Code and compatible AI coding agents.
Looking for Plot? The git-native planning workflow has moved to its own repo: plot-pm/plot
Moved skills:
tracer-bulletsnow ships with plot-pm/plot (it's Plot's companion skill);typescript-strict-patternsmoved to quatico-solutions/agent-skills
| Skill | Description |
|---|---|
| ai-council-review | Council review — ~4 frontier models via OpenRouter review a PR/plan/files in parallel, dissent-preserving synthesis in-session |
| ai-review | Get AI code review from a second model (Gemini/OpenAI) mid-session via CLI |
| apple-mail | Read email via Apple Mail.app and AppleScript (read-only) |
| apple-notes | Read Apple Notes via AppleScript (read-only) |
| ballot | Durable decision artefact for async decisions — reviewed over chat, on a PR, on a train, after the session ends. Must/Should/Could tiers, empty checkboxes, reconciliation in sessionlog. Single async decider or multi-reviewer panel; pairs with dossier or stands alone (ADRs, PR review, hiring, vendor, household) |
| bye | Session wrap-up — reconstructs history, creates sessionlog, commits, summarizes next steps |
| chrome-browser | Dedicated Chrome with CDP for Playwright MCP — persistent sessions, launchd-managed, Cloudflare tips |
| dossier | Structured research — ranked recommendations, cited sources, parallel subagents, optional decision ballots |
| lab-notes | Experiment management — hypothesis, append-only running log, verdict. Rigorous + Lite modes. |
| pandoc | Document format conversion — 60+ formats via pandoc instead of ad-hoc scripts |
| pdf-zine | Convert a PDF into a fold-and-print booklet (zine) — A4 sheets, 2-up, fold to A5, via the pdf2zine Docker CLI |
| private-podcast-feed | Private MP3+RSS feed for self-subscription — itunes:block, token URLs, ID3 chapters, Overcast ping |
| text-to-speech | Convert a text document to an audio MP3 file via a local TTS pipeline (backend-configurable) |
| tmux-control | Reliable tmux patterns — targeting, send-keys, capture-pane, wait-for sync, monitoring |
Register the marketplace and install:
/plugin marketplace add eins78/agent-skills
/plugin install eins78-skills@eins78-marketplace
Skills auto-update when you run /plugin update.
pnpx skills add https://github.com/eins78/agent-skills.git --global --agent claude-code --all --yes
Individual skills are listed in the marketplace and can be installed by name:
/plugin install bye@eins78-marketplace
# Symlink a single skill
ln -s ~/CODE/agent-skills/skills/tmux-control ~/.claude/skills/tmux-control
# Or copy it
cp -r ~/CODE/agent-skills/skills/tmux-control ~/.claude/skills/
Skills are picked up automatically by Claude Code based on their globs frontmatter.
Each skill follows the Agent Skills spec — a SKILL.md file with YAML frontmatter (name, description, globs) and markdown instructions.
my-skill/
├── SKILL.md # Required: frontmatter + instructions
├── README.md # Required: development notes, design decisions, testing history
└── REFERENCE.md # Optional: detailed reference material (>100 lines)
---
name: my-skill-name # lowercase, hyphens, max 64 chars, must match directory
description: What it does and when to use it. Include trigger keywords. (max 1024 chars)
# Optional fields per agentskills.io spec:
compatibility: claude-code, cursor
license: MIT
metadata:
source: https://github.com/your-org/your-repo
version: "1.0.0"
---
# My Skill Name
[Instructions here — keep under 500 lines]
See [REFERENCE.md](REFERENCE.md) for details.
Note: Reference files over 100 lines should include a table of contents.
Swiss weather data for AI assistants — forecasts, current conditions, stations, and pollen from MeteoSwiss Open Data. Free, no API key required.
Semantic search for Claude Code conversations. Remember past discussions, decisions, and patterns.
npx claudepluginhub eins78/agent-skills --plugin tmux-controlCurated plugin marketplace for AI agents, compatible with Claude Code, Codex, and OpenSkills frameworks.
Personal Claude Code / Codex skills — spec-driven development, agent teams, browser automation, productivity, and setup helpers. Install with `npx skills add devstefancho/claude-plugins`.
Agent Skills for improving SKILL.md files: mine repeated workflows from history, personalize and audit existing skills, or generalize personal skills for publication.
Plugin-safe Claude Code distribution of Agentic Awesome Skills with 1,913 supported skills.
Unified capability management center for Skills, Agents, and Commands.
Production-grade engineering skills for AI coding agents — covering the full software development lifecycle from spec to ship.