One search for your own team's files and the public ecosystem. See how real projects write their agent instructions, and bring the good ideas home.
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
MfrostbutterSkillMfrostbutter/skill-forge/skills/skill-forge/SKILL.md
Crystallize a captured workflow journal into a validated Claude skill. Use this whenever the user says "turn this into a skill", "make this repeatable", "build a skill from this", or when a workflow-capture worklog is ready to become a skill. Also use to improve or extend an existing produced skill from a new worklog.
MfrostbutterSkillMfrostbutter/skill-forge/skills/workflow-capture/SKILL.md
Maintain a durable, tagged journal of a complex workflow so it can later be distilled into a reusable skill. Use this whenever beginning a complex, multi-step workflow (design work, automation build, CAD, RAG pipeline, website work, or anything non-trivial you might want to repeat), even if the user does not say "capture" or "log". If the work has sequencing, corrections, or hard-won discoveries worth keeping, start a worklog. Also use on resume to read an existing worklog after a context reset.
MfrostbutterSkillMfrostbutter/claude-skills/skills/after-effects-extendscript/SKILL.md
Build and edit After Effects motion graphics from scratch with ExtendScript (.jsx) — comps, text, typing-on effects, expression-driven tracking, keyframes with easy-ease, shape/polystar elements (sparkles, glints), and timed audio. Use whenever the task is to author or change an AE script, build a title / splash / lower-third / logo animation, sync animation to a sound effect, or drive layers by expression. Encodes the hard-won rules: ExtendScript is ES3 (no const/let/arrow/template-literals), the property matchname cheatsheet, the sourceRectAtTime layout+tracking pattern, Source Text typing expressions, per-dimension KeyframeEase, server-side font resolution with graceful fallback, AE-can't-import-Opus (convert with ffmpeg), and the ffmpeg silencedetect → audio-sync recipe.
MfrostbutterSkillMfrostbutter/claude-skills/skills/figma-design-build/SKILL.md
Build, design, edit, or read designs in Figma through the Figma MCP (the cloud connector: use_figma plugin-API calls + get_screenshot feedback loop), and do design-to-code. Use whenever the task is to create or change a Figma file, mock up a UI / logo / infographic / design system, build Figma styles or components, or pull a Figma design into code. Encodes the hard-won rules: server-side font limits, load-before-edit, page/layer access, geometry and shear math, styles + components, and organize-as-you-go layer hygiene so the file is clean by construction, not cleaned up after.
MfrostbutterSkillMfrostbutter/claude-skills/skills/langgraph-agent/SKILL.md
Build, extend, or debug production LangGraph agents. Use whenever the task is to author a graph (ReAct tool-loop, parallel fan-out, routing pipeline, or human-in-the-loop), wire interrupt/resume approval, stream a run to a UI, keep a graph importable from LangGraph Studio, or structure agents so one driver can run many. Encodes the LangGraph 1.x API, the pure-factory + injected-effects pattern, interrupt/resume HITL, streaming + topology for a live view, the two-model pattern, a structured report node after a tool loop, static checks then a ranking pass, testing with stub models, and the dependency pins. Triggers include "build a LangGraph agent", "author a graph", "wire human-in-the-loop", "make it importable in Studio", "the run won't stream / won't pause".
MfrostbutterSkillMfrostbutter/claude-skills/skills/n8n-figma-workflow-map/SKILL.md
Review a set of n8n workflows and build a complete, n8n-branded workflow map in Figma: orchestrators as staged rows, sub-workflow calls badged with the n8n mark, standalone and opt-in workflows as lanes, and a data-layer band of the tables each workflow reads and writes. Use when asked to map, diagram, visualize, or document how several n8n workflows fit together, to draw an architecture picture of an n8n project, or to produce a branded map for a handoff, a review, or a post. Dark (n8n brand) and light themes.
MfrostbutterAGENTS.mdMfrostbutter/n8n-workflow-harness/AGENTS.md
Instructions for any AI coding agent (Codex, Cursor, Zed, Gemini CLI, and others that read AGENTS.md) working in this repository. A harness for building n8n workflows. Workflow JSON under workflows/<env>/ is the source of truth; the n8n canvas is a view of it. Two MCP servers, both running the n8n-mcp package pinned in package.json (https://github.com/czlonkowski/n8n-mcp): - n8n-docs — node schemas, validators, 2,700+ templates. No credentials, cannot reach an instance. Tools: searchnodes, getnode, validatenode, validateworkflow, searchtemplates, gettemplate, tools_documentation. - n8n —…
MfrostbutterCLAUDE.mdMfrostbutter/n8n-workflow-harness/CLAUDE.md
Claude Code reads this file automatically. It is the operating contract for building n8n workflows in this repository. A build harness. Workflow JSON under workflows/<env>/ is the source of truth; the n8n canvas is a view of it. Both MCP servers run n8n-mcp, pinned in package.json and installed into nodemodules/. It is the source of every node schema, validator, and template here, and it is why you configure from the live schema rather than from memory. n8n-docs carries no credentials…
MfrostbutterSkillMfrostbutter/n8n-workflow-harness/.claude/skills/n8n-agents/SKILL.md
Design n8n AI agents the right way. Use when building or editing any @n8n/n8n-nodes-langchain.* AI node — an AI Agent, LLM chain, Text Classifier, or Information Extractor — and whenever the user mentions AI agents, LLM with tools, tool calling, $fromAI, system prompts, agent memory, sessionId, structured/JSON output, output parser, RAG, vector store, a chat assistant/bot, or human-in-the-loop review. Covers Agent-vs-chain-vs-classifier choice, the model/memory/tools/outputParser slots, tool names/descriptions as prompt, structured output with autoFix, memory, RAG, human review, and chat topologies.
MfrostbutterSkillMfrostbutter/n8n-workflow-harness/.claude/skills/n8n-binary-and-data/SKILL.md
Handle files and binary data in n8n correctly. Use when working with files, images, PDFs, attachments, uploads or downloads, base64, vision/multimodal input, or when an AI agent needs a file as tool input or output — and whenever the user mentions $binary, binaryPropertyName, "read the PDF", "attach the file", "send the image", Merge losing binary, or a CDN for chat images. Covers the $binary vs $json split, reading/writing binary, keeping binary alive across transforms with Merge, the agent-tool binary boundary, and the CDN/URL requirement for chat surfaces.
MfrostbutterSkillMfrostbutter/n8n-workflow-harness/.claude/skills/n8n-canvas-docs/SKILL.md
Document an n8n workflow canvas with sticky notes and canvas groups accurately, no overlaps and no truncated text. Use whenever adding or fixing sticky notes, zone labels, or node groups (nodeGroups) on an n8n workflow (via the REST API or n8n-mcp). Covers the groups-vs-stickies routing decision, the two sticky layout patterns, the sizing math, the sticky node schema, and a construction-time checker plus the screenshot verification loop.
MfrostbutterSkillMfrostbutter/n8n-workflow-harness/.claude/skills/n8n-code-javascript/SKILL.md
Write JavaScript code in n8n Code nodes. Use when writing JavaScript in n8n, using $input/$json/$node syntax, making HTTP requests with this.helpers / the $helpers global, working with dates using DateTime, troubleshooting Code node errors, choosing between Code node modes, or doing any custom data transformation in n8n. Always use this skill when a workflow needs a Code node — whether for data aggregation, filtering, API calls, format conversion, batch processing logic, or any custom JavaScript. Covers SplitInBatches loop patterns, cross-iteration data, pairedItem, and real-world production patterns. Also use when asked why a Code node or workflow is slow, which execution mode is faster, or how to cut per-item overhead on large datasets. EXCEPTION — for the AI-agent-callable Custom Code Tool (@n8n/n8n-nodes-langchain.toolCode, a tool attached to an AI Agent), use the n8n-code-tool skill instead; it has a different runtime contract.
MfrostbutterSkillMfrostbutter/n8n-workflow-harness/.claude/skills/n8n-code-python/SKILL.md
Write Python code in n8n Code nodes. Use when writing Python in n8n, using _input/_json/_node syntax, working with standard library, or need to understand Python limitations in n8n Code nodes. Use this skill when the user specifically requests Python for an n8n Code node. Note — JavaScript is recommended for 95% of use cases — only use Python when the user explicitly prefers it or the task requires Python-specific standard library capabilities (regex, hashlib, statistics). EXCEPTION — for Python in the AI-agent-callable Custom Code Tool (@n8n/n8n-nodes-langchain.toolCode), use the n8n-code-tool skill instead (input is _query, return must be a string).
MfrostbutterSkillMfrostbutter/n8n-workflow-harness/.claude/skills/n8n-code-tool/SKILL.md
Write JavaScript or Python for the n8n Custom Code Tool (@n8n/n8n-nodes-langchain.toolCode) — the AI-agent-callable tool, NOT the workflow Code node. Use when building a Code Tool attached to an AI Agent, writing code that an LLM will invoke, parsing the `query` input, returning a string result, defining an input schema for structured arguments (specifyInputSchema, jsonSchemaExample, DynamicStructuredTool), or troubleshooting errors like \"Wrong output type returned\", \"No execution data available\", \"The response property should be a string, but it is an object\", \"Cannot assign to read only property 'name'\", or an AI agent that refuses to call the tool. Covers the critical differences between Code node and Code Tool: return format (string vs `[{json:{...}}]`), unavailability of `$fromAI`/`$input`/`$helpers` in the Code Tool sandbox, naming rules for AI invocation, and when to use `toolWorkflow`/HTTP Request Tool instead.
Surging4 mentions in 2 weeks
4 projects use a version of this
MfrostbutterSkillMfrostbutter/n8n-workflow-harness/.claude/skills/n8n-enterprise-delivery/SKILL.md
Deliver n8n inside an enterprise: environments and git-backed source control, projects and RBAC, external secrets, queue mode and scaling, log streaming and audit, SSO effects on delivery, licensing and the air-gap question, multi-tenancy architecture, embed/OEM shape, and the build-validate-eval-promote loop. Use when the task involves promoting a workflow between environments, scoping workflows or credentials to a project or role, wiring an external secrets vault, sizing or splitting an instance for load, answering a security or compliance objection (air-gap, egress, audit trail, tenant isolation), planning a customer's n8n architecture, or writing a handoff. Not for building a workflow (authoring skills) or operating one (n8n-instance-ops).
MfrostbutterSkillMfrostbutter/n8n-workflow-harness/.claude/skills/n8n-error-handling/SKILL.md
Wire n8n error handling so failures are loud, structured, and recoverable. Use when building any webhook/API workflow, a scheduled or unattended workflow, or any path where a silent failure would drop user-visible work — and whenever the user mentions error handling, onError, continueErrorOutput, error branches/outputs, retries, retryOnFail, Respond to Webhook status codes, 4xx/5xx, Error Trigger, or "my workflow fails silently". Covers per-node error outputs and wiring, retry/self-healing, error-trigger workflows, and 4xx/5xx response shapes.
MfrostbutterSkillMfrostbutter/n8n-workflow-harness/.claude/skills/n8n-gotchas/SKILL.md
Field-discovered n8n behaviors that are correct-looking but wrong, collected from real builds. Use as a lookup when something in n8n "succeeded" but did not actually take effect, when a workflow behaves differently than its JSON says, when an edit does not reach the running trigger, when a node returns success with no result, or when an error message points at the wrong cause. Also read it before a first build on a new instance so the known traps are already loaded. Complements the authoring skills (which cover correct usage); this file covers the places where correct usage still surprises you.
MfrostbutterSkillMfrostbutter/n8n-workflow-harness/.claude/skills/n8n-multi-instance/SKILL.md
Use when an n8n-mcp account targets more than one n8n instance — i.e. the `n8n_instances` tool is available, the user mentions multiple n8n instances or environments (prod vs staging, several teams or clients), a workflow / datatable / credential / execution call returns an unexpected NOT_FOUND or reads data you don't recognize, or a credential create/update/delete is refused with an `INSTANCE_AMBIGUOUS` error. Covers choosing and switching which instance this MCP session targets, verifying the target before high-stakes work — credential writes above all — and recovering from misroutes and ambiguous-write fail-closes. Always consult this skill before operating on a specific instance, before any credential create/update/delete on a multi-instance account, or when a call hits the wrong/empty data or an `INSTANCE_AMBIGUOUS` error.
MfrostbutterSkillMfrostbutter/n8n-workflow-harness/.claude/skills/n8n-node-configuration/SKILL.md
Operation-aware node configuration guidance. Use when configuring nodes, understanding property dependencies, determining required fields, choosing between get_node detail levels, or learning common configuration patterns by node type. Always use this skill when setting up node parameters — it explains which fields are required for each operation, how displayOptions control field visibility, and when to use patchNodeField for surgical edits vs full node updates.
MfrostbutterSkillMfrostbutter/n8n-workflow-harness/.claude/skills/n8n-node-dev/SKILL.md
Get a custom n8n node into a customer's running instance and keep it there: choosing between a private npm registry, a mounted extensions directory, and a baked Docker image; the queue-mode requirement that every worker carries the install; air-gapped installation; the verified-community-node requirements; and what n8n Cloud will and will not accept. Use when an engagement needs a connector that does not exist, when a customer asks how to distribute an internal node, when a custom node works on one process but not another, or when planning the packaging and release path for a node. Authoring depth (declarative vs programmatic node design, credential types, UI descriptions) is deliberately thin here and routes to the node engineering collaboration.
Plain text files in a repository that tell a coding agent how the project works: commands to run, conventions to follow and things to avoid. CLAUDE.md, AGENTS.md, cursor rules and skills are the common kinds.
CLAUDE.md is read by Claude Code. AGENTS.md is an open format that Codex, Cursor and other agents read. Many projects keep one and point the other at it.
A folder with a SKILL.md that describes one capability, such as filling PDFs or reviewing code. The agent loads it only when the task calls for it.
Your agents already can, over MCP, limited to the files you're allowed to read. Searching them from this page is coming.
