ESP-Claw is an AI agent framework that runs on Espressif IoT chips and lets people define device behavior through conversation. It handles local sensing, decision-making, and execution for connected devices, with support for event-driven actions, structured memory, and MCP communication.
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 skills add espressif/esp-claw --skill skill_creatorgit clone --depth 1 https://github.com/espressif/esp-clawWrote 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/espressif/esp-claw/skill_creator)<a href="https://agentmods.dev/skills/espressif/esp-claw/skill_creator"><img src="https://agentmods.dev/badge/skills/espressif/esp-claw/skill_creator/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/espressif/esp-claw/skill_creator"><img src="https://agentmods.dev/badge/skills/espressif/esp-claw/skill_creator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00037 | $0.00822 |
| Opus 5.5 | $0.00015 | $0.00329 |
| Sonnet 5.5 | $0.00007 | $0.00164 |
| Haiku 4.5 | $0.00004 | $0.00082 |
Grade A, and why
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 today.
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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Creator
Use this skill only when the user explicitly asks to create, update, or remove an on-device runtime Skill.
Do not activate it for a generic request such as "add a feature" or "support X". First use an existing domain Skill when one covers the request. Use app_creator for launcher-visible Apps. If the request needs a new C capability, driver, Kconfig option, firmware component, or build-time SYSTEM Skill, explain that firmware development is required and use plan_mode when available.
This workflow manages runtime Skills under the writable DATA root. It does not edit firmware source files or create native capabilities.
Resolve The Runtime Skills Root
Before reading or writing a runtime Skill, run:
{"path":"{CUR_SKILL_DIR}/scripts/resolve_skills_root.lua","args":{}}
Treat the returned absolute path as <SKILLS_ROOT>. Do not assume /fatfs; DATA may be mounted on an SD card. If the path cannot be resolved, report the error and stop.
Choose The Skill Shape
- Use an instruction-only Skill when existing capabilities already provide the required operations.
- Add references when substantial guidance is needed only for part of the workflow.
- Add one or more Lua scripts when reusable or deterministic logic is needed and the required Lua modules already exist.
- Do not claim that a Skill or Lua script adds firmware support that is not already compiled into the device.
For Lua-backed Skills, also activate lua_package_authoring and follow its Skill-script rules. Keep this skill responsible for the package layout and final publication.
Skill Contract
Before creating or updating a Skill, read {CUR_SKILL_DIR}/references/skill-package-spec.md and follow the complete package contract. Do not load the reference for removal-only requests.
Store each runtime Skill under <SKILLS_ROOT>/<skill_id>/. Do not create or overwrite a Skill whose id already exists unless the user explicitly requested that exact update.
Minimal document:
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.
- today Changed · -138 lines · +15 tokens per session 585b4b44ceed
- 1mo ago First seen · 228 lines · 22 tokens per session scan A 6c11556d816d
skill_creator is a skill published in the GitHub repository espressif/esp-claw (2,260 stars, last pushed yesterday), licensed Apache-2.0. It adds 37 tokens to every session and 822 once invoked, about $0.0001 per session on Opus 5.5. 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
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Optimize the meaningful UI available immediately from a Next.js route on an initial load (hard navigation) or named client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route and entry point at a time; the shipped test then guards…