github.com/penpot/penpot (link)

{
    "layout": "layouts/mcp.njk",
    "tags": "mcp"
}

---
name: taiga
description: Fetch information from Taiga public API for the Penpot project (id 345963) — issues, user stories, and tasks, without authentication.
metadata: {"clawdbot":{"requires":{"bins":["python3"]}}}
---

# Taiga API Skill

Fetch information from Taiga public API for the **Penpot** project
(project id: `345963`, slug: `penpot`).

**No authentication required** — only public project data is accessed.

## Prerequisites

- `python3` — the `scripts/taiga.py` CLI script is self-containe

---
name: security-and-hardening
description: Hardens code against vulnerabilities. Use when handling user input, authentication, data storage, or external integrations. Use when building any feature that accepts untrusted data, manages user sessions, or interacts with third-party services.
---

# Security and Hardening

## Overview

Security-first development practices for web applications. Treat every external input as hostile, every secret as sacred, and every authorization check as mandatory. Security i

---
name: testing
description: Enforce TDD workflow and testing best practices for Penpot. Use when implementing features, fixing bugs, or modifying behavior. Reads testing memory for full guidance.
---

# Testing Skill

Enforces test-driven development and Penpot testing conventions.

## When to Use

- Implementing new logic or behavior
- Fixing any bug (reproduction test required)
- Modifying existing functionality
- Adding edge case handling

**Skip:** Pure configuration changes, documentation updates, o

---
name: code-review
description: Conducts multi-axis code review. Use before merging any change. Use when reviewing code written by yourself, another agent, or a human. Use when you need to assess code quality across multiple dimensions before it enters the main branch.
---

# Code Review and Quality

## Overview

Multi-dimensional code review with quality gates. Every change gets reviewed before merge — no exceptions. Review covers five axes: correctness, readability, architecture, security, and perfor

---
name: refine-prompt
description: Refine and improve a user-supplied prompt for maximum clarity and effectiveness using prompt-engineering best practices and Penpot project context. Outputs a rewritten prompt (and brief rationale); never executes the prompt.
---

# Refine Prompt

Expert prompt-engineering pass on a user-supplied prompt. Takes a draft prompt
and returns a clearer, more effective, well-structured version — ready to be
used with any AI model. Never executes the prompt itself.

## When to 

---
name: create-pr
description: Create or update a GitHub PR following Penpot conventions.
---

# Skill: create-pr

Create or update a GitHub PR. Read and follow:
- `mem:workflow/creating-prs` — title format, description structure, writing principles
- `mem:workflow/creating-commits` — commit type emojis

## When to Use

- Creating a new PR from a feature branch
- Updating an existing PR's title or description to match conventions

## Prerequisites

- `gh` CLI authenticated (`gh auth status`)

## Comma

---
name: nrepl-eval
description: Evaluate Clojure code via nREPL using the standalone scripts/nrepl-eval.mjs CLI tool.
---

# nREPL Eval

Evaluate Clojure (or ClojureScript) code via a running nREPL server using
`scripts/nrepl-eval.mjs`.

Full documentation: `mem:scripts/nrepl-eval` (file: `.serena/memories/scripts/nrepl-eval.md`)

## Quick Reference

```bash
./scripts/nrepl-eval.mjs [options] [<code>]
```

| Flag | Description | Default |
|------|-------------|---------|
| `--backend` | Connect to backend

---
name: update-changelog
description: Update the project CHANGES.md with issues from a given GitHub milestone, with correct categorization and references.
---

# Skill: update-changelog

Update `CHANGES.md` with entries for all issues and PRs in a given GitHub
milestone. Each entry references the user-facing issue (not the PR) as the
primary link, with the fix PR inline on the same line.

## When to Use

- Before a new release, to populate the changelog with all fixed issues
- When new issues are added to

---
name: plan-review
description: Reviews implementation plans for quality, completeness, and actionability. Use after a plan is produced by the planner skill, before starting implementation. Use when evaluating a plan written by yourself, another agent, or a human.
---

# Plan Review

## Overview

Multi-dimensional plan review with quality gates. Every plan gets reviewed before implementation starts — no exceptions. Review covers six axes: completeness, task quality, architecture & sequencing, risk cove

---
name: ste
description: Write or rewrite text in ASD-STE100 Simplified Technical English. ONLY use this skill when the user explicitly invokes it by name — i.e. they type "/ste" or literally write "use the ste skill" / "apply ASD-STE100". Do NOT trigger it on paraphrased intent such as "simplify this", "make it clearer", "write technical documentation", or "shorter sentences please" — the user has deliberately scoped this skill to explicit invocation only. For those requests, respond normally without

---
name: ripgrep
description: Blazingly fast text search tool - recursively searches directories for regex patterns with respect to gitignore rules.
homepage: https://github.com/BurntSushi/ripgrep
metadata: {"clawdbot":{"emoji":"🔎","requires":{"bins":["rg"]},"install":[{"id":"brew","kind":"brew","formula":"ripgrep","bins":["rg"],"label":"Install ripgrep (brew)"},{"id":"apt","kind":"apt","package":"ripgrep","bins":["rg"],"label":"Install ripgrep (apt)"}]}}
---

# ripgrep (rg)

Fast, smart recursive searc

---
name: create-issue
description: Create or update GitHub issues (from PR, from draft body, retitle existing). Routes to the canonical flow in `mem:workflow/creating-issues`.
---

# Skill: create-issue

Entry point for all GitHub issue work. All rules (title derivation, metadata,
body templates, Issue Type IDs), all flows, and all `gh` / GraphQL commands
live in `mem:workflow/creating-issues` (file:
`.serena/memories/workflow/creating-issues.md`). This skill routes to the
right flow.

## When to Use

- **

---
name: jq-json-processor
description: Process, filter, and transform JSON data using jq - the lightweight and flexible command-line JSON processor.
homepage: https://jqlang.github.io/jq/
metadata: {"clawdbot":{"emoji":"🔍","requires":{"bins":["jq"]},"install":[{"id":"brew","kind":"brew","formula":"jq","bins":["jq"],"label":"Install jq (brew)"},{"id":"apt","kind":"apt","package":"jq","bins":["jq"],"label":"Install jq (apt)"}]}}
---

# jq JSON Processor

Process, filter, and transform JSON data with jq.

---
name: bat-cat
description: A cat clone with syntax highlighting, line numbers, and Git integration - a modern replacement for cat.
homepage: https://github.com/sharkdp/bat
metadata: {"clawdbot":{"emoji":"🦇","requires":{"bins":["bat"]},"install":[{"id":"brew","kind":"brew","formula":"bat","bins":["bat"],"label":"Install bat (brew)"},{"id":"apt","kind":"apt","package":"bat","bins":["bat"],"label":"Install bat (apt)"}]}}
---

# bat - Better cat

`cat` with syntax highlighting, line numbers, and Git inte

---
name: planner
description: Read-only planning and architecture analysis for Penpot — produce a structured implementation plan (Context, Affected modules, Approach, Risks, Testing). Always output to the user; additionally save to .opencode/plans/YYYY-MM-DD-<title>.md.
---

# Planner

Read-only senior software architect role for Penpot. Produces structured
implementation plans that engineers or other agents can execute. Never writes
or modifies code.

## When to Use

- The user asks for a plan, design, 

---
name: fd-find
description: A fast and user-friendly alternative to 'find' - simple syntax, smart defaults, respects gitignore.
homepage: https://github.com/sharkdp/fd
metadata: {"clawdbot":{"emoji":"📂","requires":{"bins":["fd"]},"install":[{"id":"brew","kind":"brew","formula":"fd","bins":["fd"],"label":"Install fd (brew)"},{"id":"apt","kind":"apt","package":"fd-find","bins":["fd"],"label":"Install fd (apt)"}]}}
---

# fd - Fast File Finder

User-friendly alternative to `find` with smart defaults.

##

---
name: create-commit
description: Stage, review, and commit files following Penpot commit conventions.
---

# Skill: create-commit

Produce a git commit that follows Penpot's commit message conventions. This
skill owns the commit format, staging review, and safety checks — it does not
implement features or push.

## When to Use

- After code changes are complete and files need to be committed
- When delegated by a workflow step (e.g. implement-plan) to handle the commit

## Required Reading

Before dra

{
  "mcp": {
    "playwright": {
      "type": "local",
      "command": ["npx", "@playwright/mcp@latest", "--cdp-endpoint=http://127.0.0.1:9222"],
      "enabled": true
    }
  }
}

{
  "mcp": {
    "penpot": {
      "type": "remote",
      "url": "http://localhost:${PENPOT_MCP_PORT}/mcp",
      "enabled": true
    },
    "serena-devenv": {
      "type": "remote",
      "url": "http://localhost:${SERENA_MCP_PORT}/mcp",
      "enabled": true
    }
  }
}

# AI AGENT GUIDE

## HARD RULES (always apply — no exceptions)

- **Never `git push`, force-push, or modify `git origin`** (or any other remote).
  The user pushes from their own shell. If a push is required to surface the
  agent's work (e.g. force-push after an amend), state this in the response and
  wait for the user to push. Do not change the remote URL, do not switch SSH↔HTTPS.
- **Never amend a commit that has been pushed** unless the user explicitly asks.
  If the user pushes, treat that commit