Agency Icm Builder

Build or audit an AI-runnable workspace for a client-service agency (marketing, PPC, design, consulting, dev shops). Folder structure does the orchestration - one agent, routing files, per-client folders, session capture. Use when the user wants to (1) set up an agency workspace an AI agent can operate ("build me an agency workspace", "structure my agency for AI"), (2) audit an existing agency folder against these conventions ("audit my workspace", "why does my agent keep mixing up clients"), or (3) restructure a grown-wild agency folder into this shape ("restructure this", "ICM my agency").

12 starsAI, LLMs & Agents

Install

skills CLI (Claude Code, Cursor, Codex and more)

npx skills add krsnczky/agency-icm-builder --skill agency-icm-builder

Manual install

git clone --depth 1 https://github.com/krsnczky/agency-icm-builder.git /tmp/agency-icm-builder
mkdir -p ~/.claude/skills
cp -r /tmp/agency-icm-builder/. ~/.claude/skills/agency-icm-builder

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Agency ICM Builder

Build workspaces where the folder structure runs the agency. One AI agent, reading the right files at the right moment, coordinates client work across services: the routing files decide what loads, per-client folders guarantee client data never mixes, and a session-end capture protocol turns daily work into durable memory.

This is not theory. The conventions here run a real agency: 15 client folders, 5 service departments, daily production use. Everything below was extracted from that system, then genericized.

The term ICM (Interpretable Context Methodology, folder structure as agent architecture) comes from Van Clief & McDermott, arXiv:2603.16021.

## The ten rules

Every workspace this skill builds or audits follows these. In audit mode, each rule is a check.

1. **The root file routes, it does not teach.** The root `CLAUDE.md` holds identity plus a routing table (task keyword to file path) and nothing else. Content lives in the files it points to. When the root file grows, it is absorbing payload that belongs on a shelf.
2. **Every client is one folder.** Nothing about a client lives outside `clients/<name>/`. This is the no-mixing guarantee: the agent always knows which client it is working on, so client facts always land in the right folder. Cross-client insight goes to a shared patterns file, stripped of client identity.

Read the full skill on GitHub

Details

Skill name: agency-icm-builder
Repository: krsnczky/agency-icm-builder
License: MIT
Repo updated: 12 October 2026

FAQ

What does the Agency Icm Builder skill do?

How do I install the Agency Icm Builder skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add krsnczky/agency-icm-builder --skill agency-icm-builder. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Agency Icm Builder popular?

It lives in krsnczky/agency-icm-builder, which has 12 GitHub stars and 0 forks.

Related skills

AI Md

sstklen/ai-md

AI.MD — Convert any human-written CLAUDE.md into AI-native structured format. Your CLAUDE.md is read by AI every single turn, not by you — so write it in AI's language. Battle-tested: 5 rounds, 4 models (GPT-5.3, Gemini 2.5 Pro, Grok-4, Claude Opus 4.6). Structured-label format raised Codex compliance from 6/8 → 8/8 on identical content. Same rules, fewer tokens, higher precision. This skill contains the complete methodology: how to take natural language instructions and convert them into a format that LLMs actually follow better. Run with: "distill my CLAUDE.md" or "rewrite my MD for AI" or "

AI, LLMs & Agents

Wise Men Flash

Ali-expandings/wise-men-flash

Use when the user asks for a "flash council", "quick council", "fast panel", "wise men flash", "quick second opinion from a panel", or invokes /wise-men-flash — and when they want a council-quality answer to a hard question fast (four subagent calls and about a third of the full council's time, a median 16.7 minutes in its own pre-registered round) rather than the full wise-men protocol. A three-member council of a practitioner anchor named for the job the question belongs to, one domain member, and a Devil's Advocate — each reasoning down a different path, spawned in parallel. No peer-review

AI, LLMs & AgentsIn 1 list

Cc Port

Ling-ye/cc-port

Inspect, compare, plan, transfer, and verify AI agent resources across configured Codex, Claude Code, Cursor, Windows, and WSL profiles through CC Port. Use when an AI must discover or synchronize skills, MCP configurations, rules, prompts, plugins, instructions, or memories; compare local and repository state; upload or download selected resources; resolve profile-specific targets; or safely operate CC Port through MCP tools or its machine-readable CLI. Triggers include cc-port, AI resource sync, asset inventory, upload or download agent resources, migrate Codex or Claude configuration, sync

AI, LLMs & Agents

Seedance 25 Prompting

gbeyrouti/seedance-prompting-claude-skill

Expert prompt engineering pour Seedance 2.5 (ByteDance / Dreamina / Jimeng / Doubao), modèle vidéo 30 s en une passe, audio natif, 50 références max. Utiliser dès que l'utilisateur veut écrire, optimiser ou déboguer un prompt Seedance (2.5 ou 2.0), générer une vidéo avec Seedance/Dreamina/Jimeng, faire du text-to-video, image-to-video, first/last frame, multi-keyframes, storyboard, blockout ou clay render, utiliser des références @Image/@Video/@Audio, éditer ou étendre une vidéo, une transition seamless, du multi-plans timecodé, du dialogue lip-syncé (notamment en français) ou une vidéo longue

AI, LLMs & AgentsIn 1 list

Gemini

pcx-wave/gemini-skill

Delegate a coding task to Gemini CLI and supervise the result via git diff. Trigger: /gemini <instruction>. Claude orchestrates, Gemini codes. Also handles /gemini-report [--since N] [--project NAME] [--fails] — token/cost/failure report.

AI, LLMs & Agents

Moufa Xingyun Avatar

lewislulu/moufa-xingyun-avatar

给任意 Agent 接上一个魔珐星云(Xmov)实时 3D 数字人前端——网页里 new 一个数字人,把 Agent 的文字输出喂给 speak(),它就实时说话、配口型、做动作。当用户想"给 Agent / 聊天机器人 / LLM 加一个会说话的虚拟形象、数字人、虚拟主播、3D avatar 前台",或要接入魔珐星云 / 星云 / Xmov / XmovAvatar SDK 时使用本技能。

AI, LLMs & Agents

Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.