factorialco

Audits AI configuration files (AGENTS.md, copilot-instructions.md, SKILL.md files) for instruction duplication. Load when modifying any AI config file, adding a new skill, or reviewing whether instructions have drifted out of sync.

Code review checklist for the F0 React component library. Use when reviewing PRs, auditing component code quality, or checking compliance with F0 conventions before merging. Covers component structure, TypeScript strictness, testing standards, styling, accessibility, and Storybook requirements.

Use when someone wants to add or change something in F0 (a component, prop, token, icon, or pattern). Covers the filter, the alignment, and the build in experimental/. You (the agent) are the door — you search, filter, and guide. For promotion to stable, use f0-component-promotion.

Detailed reference for F0 React component architecture, context/state, styling, testing, i18n, and animation patterns with code examples. Load when building or modifying components in the F0 design system.

Use when promoting an F0 component from experimental/ to stable (Phases 4–5 of the lifecycle). Owned by Foundations team. For building a new component, use f0-component-contribution.

Guide for migrating components from experimental to stable locations (components/, sds/, ui/). Trigger when the user wants to migrate, promote, or move an experimental component, or asks about deprecating experimental exports.

Create pull requests for the F0 design system monorepo using gh CLI. Use when opening a PR from the f0 repo — handles title format, PR body mapped to PULL_REQUEST_TEMPLATE.md, conventional commit change list, and interactive clarification for missing context.

Create Storybook story files (.stories.tsx) for F0 React components. Use when adding or updating stories, snapshot stories, argTypes, decorators, play functions, or internal stories. For MDX documentation files, use the global factorial-f0-component-documentation skill instead.

Use the Factorial Code CLI (fcode) for local development and cloud sync — the pull → add → dependencies:install → run → push flow, when to run each command, --force safety, worked examples, and the workspace config files (process metadata.json with webhook/form/appRole/visibility, team.json, variables.meta.json). Use when running fcode CLI commands, testing a Factorial Code process locally, deploying/syncing Factorial Code (fcode) resources to the cloud, or activating a process's webhook, form, or visibility settings.

Embed a Factorial Code process's input-parameter form on a webpage — the three embed methods (data attributes, Fcode.initForm, FcodeForm React component), driving behavior from the process return value (message/formErrors/redirect/jsCallback/nextProcessId), styling/themes, i18n, multi-step flows, and automatic file uploads to Storage. Use when embedding, configuring, styling, or wiring up submission callbacks for a Factorial Code (fcode) form.

Factorial Code platform architecture and core concepts — processes, modules, execution context, team variables, datastore, file storage, workspace structure, and naming conventions. Use when building, editing, or reasoning about any Factorial Code (fcode) process, module, or workspace; start here before writing process or module code.

Write JavaScript (Node.js v22) for Factorial Code processes and modules — the async main() entry point with module.exports = { main }, fcode.context.parameters, fcode.import(), datastore/storage/env helpers, auto-installed dependencies, and return-value formats. Use when creating or editing .js process or module code for Factorial Code (fcode).

Write Python 3.13 for Factorial Code processes and modules — the main() entry point, fcode.context.parameters, fcode.import_module(), datastore/storage/env helpers, PEP 8 / snake_case, auto-installed dependencies, and return-value formats. Use when creating or editing .py process or module code for Factorial Code (fcode).

Iterative, confirmation-driven workflow for building Factorial Code processes and modules end to end — plan-and-confirm, discovery scripts, incremental implementation validated with the run_code MCP tool, exposing processes as MCP tools, plus security and error-handling practices. Use when asked to build, automate, or integrate something on Factorial Code (fcode) and you need the recommended working method.

Reference implementations for Factorial Code — a complete marketplace payroll integration (outbound sync with file-export and API-push delivery flavors), a multi-process custom app lifecycle (multi-step setup form, webhook + schedule install, polling, uninstall), and utility processes (CSV export with signed URL + email, XML enrichment from an uploaded file). Use when building a Factorial Code (fcode) integration, custom app, or automation end to end and you want a proven, working pattern to adapt — read the matching reference before writing code.

Author Factorial Code process input-parameter schemas (parametersSchema.json) — every supported input type and validation option, with a complete annotated sample. Use when creating or editing a parametersSchema.json, or defining a Factorial Code (fcode) process's input parameters or form fields.

Build integrations with the Factorial HR API using the official TypeScript (@factorialco/api-client) and Python (factorial-api-client) SDKs. Use when authenticating, calling endpoints, paginating list results, subscribing to webhooks, or typing webhook handler payloads against the Factorial API.

Regenerate the Factorial TypeScript and Python SDKs against a new dated API version and open the release PR. Use when a new Factorial API version ships (e.g. "regenerate the SDKs for 2026-07-01", "release the new API version", "cut a new SDK release"). Covers the full pipeline: fetch spec, regenerate, validate, version_map, READMEs, and the release-please handoff.