Agent skills
Skills for AI coding agents, each with what it costs to load, how much of it is scripts and what it touches on your machine.
How to read a skill
What it costs to keep
Idle in context, in use when it runs, and up to with its linked files.
Scripts or instructions
Script-led, mixed or model-led: how much the model has to work out itself.
What it can reach
Shell, network, file writes, git and credentials, declared or detected.
Quality, security, repo health
Out of 100, each with what it is made of. Turn a card over to see them.
remotion-multimedia
7,648Read audio duration, video duration and video dimensions with Mediabunny in the browser, Node.js or Bun.
remotion-saas
7,648Architecture guidance for apps built on Remotion: templates, the Player, and server or Lambda rendering.
scenario-analyzer
7,430Turns one news headline into an 18-month scenario report with base, bull and bear cases, sector impacts by order and a second-opinion review.
US Market Bubble Detector
7,430Scores US market bubble risk from six measured indicators and a capped qualitative adjustment, then labels a phase from Normal to Critical with a stated risk budget.
US Stock Analysis
7,430Researches a US stock ticker with web search and writes a quick overview, a fundamental or technical analysis, a full report or a side-by-side comparison of several stocks.
Market News Analyst
7,428A six-step method that gathers the last 10 days of market news by web search, scores each event for impact, and writes a ranked Markdown report of how equities and commodities reacted.
Humanize
6,692A slash command that sends Korean text or a file to the Humanize Korean pipeline and reports the status, changes and grade.
Humanize Korean for Copilot CLI
6,692A single-call edition of Humanize Korean for GitHub Copilot CLI that detects, rewrites and self-checks AI-written Korean text in one pass.
Humanize Redo
6,692A slash command that reruns the latest Korean humanizing result for one category, one paragraph or a different strength, up to three rounds.
Humanize Scan
6,692A quick scout for Korean text: checks six AI tells that held up in testing, shows before and after counts, and says whether a full pass is worth it.
n8n Agents
6,686A guide for designing n8n AI agents: which AI node to use, how to name tools, wire memory, force structured output and gate risky actions behind human review.
n8n Binary and Data
6,686A guide to files in n8n: where bytes live, how to read and write them, how to stop transforms from dropping them, and how to pass files to agent tools and chat apps.
n8n Code JavaScript
6,686A guide to writing JavaScript in n8n Code nodes: a gate that checks native nodes first, data access, return format, webhook body, sandbox limits and loop pitfalls.
n8n Code Python
6,686A guide to native Python in n8n 2.x Code nodes: the two input variables, blocked imports, denied builtins, accepted return shapes and how errors interact with onError.
n8n Code Tool
6,686A guide to the n8n Custom Code Tool that AI agents call: string in and string out, the query variable, input schemas, sandbox limits and the three signature errors.
n8n Error Handling
6,686A guide to n8n error handling: the two-step per-node error output, retryOnFail, 4xx and 5xx webhook responses and Error Trigger workflows for unattended runs.
n8n Expression Syntax
6,686A guide to writing correct n8n expressions: double braces, $json and $node, the webhook body trap, a native-node-first order, JMESPath, helpers and silent null errors.
n8n MCP Tools Expert
6,686The main guide to the n8n-mcp tools: which tool to call, the two nodeType formats, validation profiles, iterative workflow edits, test runs, credentials and audits.
n8n Multi-Instance
6,686A guide to working with several n8n instances over MCP: name the target on each call, use switch sparingly, guard credential writes and recover from misrouted calls.
n8n Node Configuration
6,686A guide to configuring n8n nodes: required fields that change with the operation, displayOptions dependencies, get_node detail levels, native data nodes and silent-failure traps.
n8n Sub-workflows
6,686A guide to reusable n8n sub-workflows: typed Define Below inputs, all versus each mode, verb-first names, stateless or stateful design and fire-and-forget parallel runs.
n8n Validation Expert
6,686Teaches an agent to read n8n-mcp validation results, run the validate-and-fix loop, judge which warnings matter and test a workflow once it validates.
n8n Workflow Patterns
6,686Gives an agent six proven n8n workflow architectures, a pattern selection guide, a build checklist and the validate, verify, test, activate sequence.
ip-as-logo
6,653Generate extremely simple, cute, rounded mascot characters with an image model: three proposed directions, six independent candidates, two character colors on one solid background.