skills_lab_downloader

skills_lab_downloader is a skill for Claude Code, Codex from espressif/esp-claw. It costs 38 tokens per session (1,147 once invoked), scanned A, original, Apache-2.0.

A downloader for installing skills from the ESP-Skill hub onto an ESP-Claw device. It uses the skill's exact name and checks required device capabilities before saving it.

In plain words
What is it for?
Use it to fetch a known skill, inspect its metadata, verify required peripherals, and save the skill in the device's skills directory.
Why use it?
It avoids installing the wrong item and identifies missing hardware or software requirements before download.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to fetch a known skill, inspect its metadata, verify required peripherals, and save the skill in the device's skills directory.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/espressif/esp-claw/skills_lab_downloader
About the project

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.

espressif/esp-claw · 2,104 stars · on GitHub · esp-claw.com

Install

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.

Any agent
npx skills add espressif/esp-claw --skill skills_lab_downloader
Clone the repo
git clone --depth 1 https://github.com/espressif/esp-claw

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for skills_lab_downloader

README.md
[![agentmods](https://agentmods.dev/badge/skills/espressif/esp-claw/skills_lab_downloader/github.svg)](https://agentmods.dev/skills/espressif/esp-claw/skills_lab_downloader)
Your own site
<a href="https://agentmods.dev/skills/espressif/esp-claw/skills_lab_downloader"><img src="https://agentmods.dev/badge/skills/espressif/esp-claw/skills_lab_downloader/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.

agentmods 80×15 button for skills_lab_downloader

Your own site · 80×15
<a href="https://agentmods.dev/skills/espressif/esp-claw/skills_lab_downloader"><img src="https://agentmods.dev/badge/skills/espressif/esp-claw/skills_lab_downloader.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,147 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Excessive Agency · line 32
    Skill grants unrestricted tool access without appropriate constraints. An agent with unfettered tool access can perform arbitrary actions including file modification, network requests, and code execution.
    Fix: Restrict tool access to only the tools required for the skill's stated purpose. Use an explicit allowlist rather than granting blanket access.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00038 $0.01147
Opus 5 $0.00019 $0.00574
Sonnet 5 $0.00008 $0.00229
Haiku 4.5 $0.00004 $0.00115

Measured 11d ago against content hash 1e29bad840d8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

skills_lab_downloader 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 11d 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.

components/common/skill_builder/skills/skills_lab_downloader/SKILL.md · 96 lines

How it starts

The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skills Lab Downloader

Use this skill when the user wants to install a skill from the ESP-Claw's Skill hub at skills-lab.esp-claw.com.

When to use

  • The user wants to download or install a skill from the ESP-Claw's Skill hub.
  • The user already knows the exact skill name, or needs a reminder that installation requires the exact skill name instead of the visible title.

Hard rules

  1. Installation requires the exact skill name, not the skill title.
  2. A valid skill name contains only A-Z, a-z, 0-9, _, or -.
  3. Before downloading, make sure cap_http_request is enabled and available. If it is unavailable, stop and tell the user to enable HTTP request first.
  4. Use {CUR_SKILL_DIR}/scripts/download_skill.lua for hub download requests. Do not manually recreate the HTTP flow outside this script.
  5. First fetch _metadata.json and return it to yourself as a raw JSON string. Treat that string as the source of truth for install decisions.
  6. If metadata fetch returns a 404 result, tell the user the skill does not exist and stop.
  7. If metadata fetch fails with an allowlist error such as HTTP allowlist is empty or host 'skills-lab.esp-claw.com' is not in allowlist, tell the user to add *.esp-claw.com to the Web Console allowlist and stop.
  8. Before installation, inspect metadata.peripherals. If it is non-empty, activate board_hardware_info and compare every listed peripheral against the current board device inventory.
  9. If one or more required peripherals are unavailable, do not install by default. Tell the user which peripherals are missing and stop unless the user explicitly asks to force install.
  10. Only after compatibility is confirmed, or the user explicitly approves force install, run the install step.
  11. After the install script succeeds, registration is optional: call register_skill only when the user or workflow needs the skill to be available to activate_skill immediately.
  12. If register_skill is called and succeeds, tell the user the skill has been installed and registered. If it is skipped, tell the user the skill has been installed and will become available after the next registry reload or device restart.
  13. Do not ask Lua to parse _metadata.json. The model must read the JSON string, make the install decision, and pass the file lists to Lua as structured args.

Read the full file on GitHub · 96 lines

Files

What ships with it

1 file 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.

Changes

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.

  1. 11d ago First seen · 96 lines · 38 tokens per session scan A 1e29bad840d8

Subscribe to this mod's changes

skills_lab_downloader is a skill published in the GitHub repository espressif/esp-claw (2,104 stars, last pushed 2d ago), licensed Apache-2.0. It adds 38 tokens to every session and 1,147 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

gke-compute-classes

Configures, optimizes, and troubleshoots GKE ComputeClasses. Use when configuring Spot VMs with on-demand fallback, targeting specific accelerators (GPUs/TPUs) or machine families, restricting ComputeClass access, or debugging pending pods related to node pool auto-creation. Do not use for cluster-level Node Auto…

google/skills · 83 tokens

jetson-diagnostic

Read-only Jetson health snapshot for identity, memory, GPU, thermal, power, storage, services, and top processes.

NVIDIA/skills · 30 tokens

doca-socket-relay

Use this skill when the operator is driving the DOCA Socket Relay to bridge a socket-oriented host application onto a BlueField DPU peer without rewriting it — picking the deployment shape (in-process, sidecar, or BlueField service container), configuring the host-side socket and the DPU-side forwarding endpoint…

NVIDIA/skills · 236 tokens

offensive-z-wave

Z-Wave attack methodology — sniffing with Z-Force / EZ-Wave / RTL-SDR + ZniffMobile, S0 (legacy) network-key derivation flaw and key reuse, S2 (modern) ECDH commissioning analysis, replay/injection on unauthenticated nodes, default-key brute-force on test deployments, and home-automation hub pivots. Use when targeting…

SnailSploit/Claude-Red · 113 tokens

hsb-flash

Flash the FPGA on an HSB board connected to an NVIDIA devkit. Supports HSB Lattice boards (FPGA versions 2407, 2412, 2507, 2510) and Leopard Imaging VB1940 "all-in-one" cameras (FPGA versions 2507, 2510). Uses release-specific YAML manifests and board-type-specific program commands. Lattice and VB1940 commands must…

NVIDIA/skills · 94 tokens

jetson-validate-image

Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.

NVIDIA/skills · 50 tokens