This repo packages three agent skills from Wade Foster into general-purpose Markdown files. Each skill tells the agent how to run a repeatable workflow: convene a decision panel, turn a meeting into follow-ups, or build a ranked weekly agenda from your real inputs. The files are tool-agnostic, with placeholders you replace once for your own tools.
Builders who want their agent to handle meeting debriefs, decision review, and weekly agenda planning the same way every time.
You can turn meetings and weekly inputs into structured decisions, follow-ups, and priorities without re-explaining the workflow.
Runs a panel of expert personas, including a ruthless CFO and contrarian board member, to stress-test a decision and produce a ranked recommendation.
Turns a finished meeting into a debrief, decisions, action items, follow-up drafts, and proposed writebacks to your systems.
Sweeps meetings, chat, email, and calendar to produce a forced-ranked list of 5-10 leadership topics tied to real sources.
Uses bracketed placeholders for your meeting notes, email, CRM, and other tools so the same skill can run in different stacks.
Can be installed as a plugin for Claude Code, Codex, and Copilot, or copied into Cursor and Claude Code skill folders.
Three of the agent "skills" Wade Foster (Co-Founder & CEO, Zapier) demoed during his Running Remote 2026 fireside chat, cleaned up into general-purpose versions you can drop into your own AI setup.
A "skill" here is just a Markdown file that tells an AI agent (Cursor, Claude Code, Claude Projects, a custom GPT, etc.) how to run a specific workflow. Each one is written to be tool-agnostic: wherever the original relied on a specific tool, these versions use a generic placeholder like [YOUR MEETING NOTES TOOL] that you fill in once.
| Skill | What it does |
|---|---|
war-council/SKILL.md | Convenes a panel of opinionated expert personas (ruthless CFO, contrarian board member, customer obsessive, plus experts generated for your specific problem) to stress-test a decision and return a ranked, bet-weighted recommendation. |
meeting-follow-up-pipeline/SKILL.md | Turns a finished meeting into a debrief, decisions, action items, ready-to-send follow-up drafts, and proposed writebacks into your task/CRM systems. |
exec-weekly-agenda-generator/SKILL.md | Sweeps your week across meetings, chat, email, and calendar, then produces a forced-ranked list of 5-10 topics worth the leadership team's time. |
In Claude Code: install as a plugin — claude plugin marketplace add zapier/marketplace then claude plugin install wade-skills@zapier. All three skills become available automatically.
In OpenAI Codex: codex plugin marketplace add zapier/marketplace then codex plugin add wade-skills@zapier. Or open the in-CLI picker with /plugins and toggle it on.
In GitHub Copilot CLI: copilot plugin marketplace add zapier/marketplace then copilot plugin install wade-skills@zapier.
In Cursor or Claude Code (manual): drop a skill's folder into .cursor/skills/ (Cursor) or .claude/skills/ (Claude Code). The YAML frontmatter at the top of each file (name + description) is what tells the agent when to invoke it automatically. You can also just paste the file contents into a chat and say "follow this."
In Claude Projects / a custom GPT / any chatbot: paste the skill file into the system prompt or project knowledge. Then trigger it with the phrases listed under "When to Use."
Fill in the placeholders first. Each file has a short "Setup" section listing the [BRACKETED] placeholders (your meeting-notes tool, your email, your CRM, your leadership team roster, etc.). Set those once and the skill runs against your stack.
These work because of a few principles, not because of any specific vendor:
Shared with the Running Remote community and released by Zapier, Inc. under the MIT License. See LICENSE for the license and NOTICE for trademark, third-party, and use terms. Review NOTICE before use.
This repo is shared as-is. We're not accepting external contributions.
Sign in to join the discussion.
No comments yet. Be the first to say what this is good for.
Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, every edge explained, no vector store.
Topic in, narrated explainer video out. A Claude Code / Codex skill that turns any topic into a black-canvas motion-graphics explainer video with TTS voiceover, subtitles and a chapter progress bar. Chinese or English; every frame drawn in code with Remotion.
Public repository for Agent Skills
Open-source AI job search: scan job portals, evaluate listings into a structured A-H report with a global 1-5 score, tailor your CV, track applications — runs locally in your AI coding CLI (Claude Code, Codex, OpenCode, Antigravity…)
Agent skill for beautiful, verifiable architecture, workflow, sequence, data-flow, and lifecycle diagrams—self-contained HTML with motion and crisp export.
A skill to stop your coding agent from burying the answer. ADHD-friendly output.
