mcpField
F
Formhug

Formhug

Remote
github.com/FormHugProductivity0Updated 20w ago
Repository

About Formhug

Formhug Skills is a collection of Agent Skills for agents that work with FormHug. It covers MCP setup, form creation and review, submission analysis, and survey methodology through automatically activated procedural guides.

Key features

  1. 01Configure agent access to FormHug MCP
  2. 02Recreate forms from documents or platforms
  3. 03Analyze form submissions
  4. 04Audit forms and apply approved fixes
  5. 05Apply survey design methodology

Use cases

  1. 01Connect an agent to FormHug
  2. 02Rebuild a form from a PDF or spreadsheet
  3. 03Review submissions and aggregate response types
  4. 04Check a live form against a checklist

MCP support

The skills complement the FormHug MCP server at https://formhug.ai/mcp with setup flows and procedural guidance. The server provides reference resources, while the skills guide agents through workflows.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://formhug.ai/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Tools

Details

From the project README

FormHug Skills

Agent Skills for working with FormHug — connecting to its MCP server, building good forms, applying recommended patterns. Built to the Agent Skills open standard, so they work with any agent that reads SKILL.md: Claude Code, Codex CLI, Cursor, Windsurf, Claude Desktop, OpenClaw, Hermes, and others.

The MCP server itself (https://formhug.ai/mcp) ships its own reference resources (formhug://guide, formhug://field-types, …) covering tool usage. This repository complements them with skills that the agent proactively activates from triggers — installation flows, workflow guides, opinionated best practices — material that's better delivered as procedural skills than as on-demand reference docs.

Available skills

SkillWhat it does
setup-formhug-mcpConfigure the current agent to talk to https://formhug.ai/mcp. Picks OAuth (local agents) or Personal Access Token (remote/chat agents) automatically, writes the right config for that agent, and verifies with get_me.
migrate-form-to-formhugRecreate an existing form in FormHug from another platform or a document (Word/PDF/Excel/screenshot). Inventory-first workflow with a field-type mapping table and post-create verification.
analyze-formhug-entriesAnalyze a form's submissions: full pagination, api_code→label decoding, per-type aggregation (NPS, likert, checkbox), and honest reporting rules.
audit-formhug-formReview an existing form against a fixed checklist (field-type fit, required discipline, structure, settings, privacy) and apply approved fixes safely on live forms.
formhug-survey-methodologySurvey design methodology — question wording, scale design, structure, response-quality safeguards — mapped to the FormHug fields that implement each pattern.

Install

The recommended way is the skills CLI from Vercel Labs — it detects which agents you have installed and copies the skills to the right place for each:

npx skills add formhug/skills

Install only specific skills, or only to specific agents:

npx skills add formhug/skills --skill setup-formhug-mcp
npx skills add formhug/skills -a claude-code -a cursor
Manual install

If you'd rather not use the CLI, copy a skill directory into your agent's skills location. Path varies by agent:

AgentSkills directory
Claude Code~/.claude/skills/ (user) or .claude/skills/ (project)
Codex CLI~/.codex/skills/
Cursor~/.cursor/skills/
Gemini CLI~/.gemini/skills/
OpenClawvia clawhub install <skill>
git clone https://github.com/formhug/skills.git
cp -r skills/skills/setup-formhug-mcp ~/.claude/skills/

Usage

After installation, skills activate automatically when the agent recognises a matching request (each skill declares its triggers in its frontmatter). Agents that expose skills as slash commands can also invoke them directly, e.g. /setup-formhug-mcp.

Repository layout

skills/
  <skill-name>/
    SKILL.md          # frontmatter (name, description) + instructions
    references/       # optional — files the skill pulls in on demand
    scripts/          # optional — executable helpers

Each skill is a self-contained directory. The agent only loads SKILL.md up front; everything else is referenced from inside it and read on demand (progressive disclosure).

What kinds of skills belong here

  • Setup / integration — connecting agents to FormHug (setup-formhug-mcp)
  • Workflow guides — opinionated, agent-driven flows (e.g. "design a registration form from a description", "audit an existing form's entries")
  • Best practices — codified conventions agents should follow when using FormHug tools (field naming, scoring rubrics, theme choices, webhook patterns)

Reference material that the agent needs only after it's already decided what to do (field type catalogues, theme tokens, error code tables) generally belongs in the MCP server's resources rather than here.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.