Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/gabelul/stitch-kit/stitch-skill-creatornpx skills add gabelul/stitch-kit --skill stitch-skill-creatorgit clone --depth 1 https://github.com/gabelul/stitch-kitWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/gabelul/stitch-kit/stitch-skill-creator)<a href="https://agentmods.dev/skills/gabelul/stitch-kit/stitch-skill-creator"><img src="https://agentmods.dev/badge/skills/gabelul/stitch-kit/stitch-skill-creator.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00061 | $0.01773 |
| Opus 5 | $0.00030 | $0.00886 |
| Sonnet 5 | $0.00012 | $0.00355 |
| Haiku 4.5 | $0.00006 | $0.00177 |
Grade A, and why
stitch-skill-creator scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 258 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Stitch Skill Creator
A factory for creating new stitch-kit skills. Enforces standard structure, naming conventions, and the plugin's architectural patterns.
When to use this skill
- Adding support for a new framework (e.g. "Astro", "Qwik", "Flutter")
- Creating a domain-specific prompt architect (e.g.
stitch-ui-ecommerce-architect) - Adding a new quality tool (e.g.
stitch-performance,stitch-seo) - Any time you need a new SKILL.md that integrates with the stitch-kit ecosystem
Naming conventions
| Skill type | Name pattern | Example |
|---|---|---|
| Framework conversion | stitch-[framework]-components |
stitch-astro-components |
| Domain prompt architect | stitch-ui-[domain]-architect |
stitch-ui-ecommerce-architect |
| MCP wrapper | stitch-mcp-[tool-name] |
stitch-mcp-edit-screen |
| Quality / analysis tool | stitch-[capability] |
stitch-performance |
| Meta / utility | stitch-[name] |
stitch-setup |
Rules:
- Always kebab-case
- Always starts with
stitch- - Framework conversion skills end with
-components - MCP wrappers follow
stitch-mcp-{snake_case_tool → kebab}fromdocs/mcp-naming-convention.md
Required directory structure
skills/[skill-name]/
├── SKILL.md ← Required: frontmatter + workflow (keep under 500 lines)
├── examples/
│ └── usage.md ← Required: 2+ worked examples
├── resources/ ← Optional: templates, checklists, reference tables
│ ├── component-template.[ext]
│ └── architecture-checklist.md
├── scripts/ ← Optional: bash scripts
│ └── fetch-stitch.sh ← Copy from stitch-mcp-get-screen/scripts/ if needed
└── references/ ← Optional: style guides, contracts, long reference docs
SKILL.md template
---
name: stitch-[skill-name]
description: [One clear sentence — when to use this skill and what it does. This is used for routing by the orchestrator and for marketplace display.]
allowed-tools:
- "stitch*:*" # Include if skill calls Stitch MCP tools
- "Bash" # Include if skill runs shell commands
- "Read" # Usually yes
- "Write" # Usually yes
---
# Stitch → [Target] [Type]
**Constraint:** Only use this skill when the user explicitly mentions "Stitch" [and any additional trigger condition].
[One sentence explaining what this skill does and who the agent "is" while using it.]
## When to use this skill vs. similar skills
[Table comparing this skill to its nearest alternatives — help the orchestrator route correctly]
## Prerequisites
[What the user/environment needs before this skill can run]
## Step 1: Retrieve the design
1. Run `list_tools` → find Stitch MCP prefix
2. Call `[prefix]:get_screen` with numeric `projectId` and `screenId`
3. Download HTML: `bash scripts/fetch-stitch.sh "[htmlCode.downloadUrl]" "temp/source.html"`
## Step 2: [Core conversion / workflow]
[The main logic of this skill]
## Step N: Output
[What the skill produces — files, code, commands]
## Troubleshooting
| Issue | Fix |
|-------|-----|
## References
- `resources/component-template.[ext]` — [description]
- `resources/architecture-checklist.md` — Pre-ship checklist
- `scripts/fetch-stitch.sh` — Reliable GCS HTML downloader
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 6d ago First seen · 258 lines · 61 tokens per session scan A 23bdadbede3d
stitch-skill-creator is a skill published in the GitHub repository gabelul/stitch-kit (43 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 61 tokens to every session and 1,773 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
karakeep
Official skill for how to use karakeep (the bookmark manager) and interact with it programmatically.
design-to-code
Mockup-to-component pipeline using Google Stitch, 21st.dev, and Storybook MCP. Accepts a screenshot, a description, or a URL and produces production-ready React components, checking existing Storybook components before generating anything new. Use when implementing UI from a mockup or screenshot. To call the MCP tool…
kit-montar
Monta um site novo combinando peças já validadas do acervo pessoal do usuário — templates, design systems, componentes, animações, menus, prompts e receitas — em vez de gerar tudo do zero. Acervo vazio: constrói do zero e oferece guardar. Recebe o briefing, decide cor e tipografia antes da identidade, pergunta que…
kit-buscar
Consulta o acervo pessoal de sites do usuário — o que ele já guardou: templates rodáveis, design systems com paleta e tipografia, componentes de UI e de IA, animações de scroll, texto e menu, efeitos WebGL, prompts de página inteira e receitas de composição que já deram certo. Responde "o que eu já tenho pronto pra…
kit-ingerir
Alimenta o acervo pessoal de sites com material novo — prompts, componentes, efeitos, design systems, projetos inteiros ou catálogos servidos por MCP — classificando por conteúdo e escrevendo a ficha que torna a peça encontrável depois. Aceita arquivo, texto colado, pasta de projeto, registro shadcn ou servidor MCP.…
kit-adaptar
Lê um prompt de site que veio de fora — quase sempre em inglês, quase sempre sem contexto — e devolve em português o que ele é: tipo de site, escopo (hero solto ou landing inteira), seção por seção, técnica usada (hover, cursor, scroll, WebGL, vídeo), stack e dependências, e o mapa de assets com o caminho exato de…