New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Supported Devices

by gweslab in gweslab/cerf

Update the supported-boards list after work on a board (only user triggered, no agent self-invocation).

MITAuto-check passed

Install Supported Devices

skills CLI
$ npx skills add gweslab/cerf --skill supported-devices -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install gweslab/cerf supported-devices --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/gweslab/cerf.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/supported-devices .claude/skills/supported-devices && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
supported-devices
GitHub stars
105
Token cost
~682 tokens
SKILL.md length
390 words
Files
1
Skills in repo
10
Repo updated
First seen
Licence
MIT

At a glance

Update the supported-boards list after work on a board (only user triggered, no agent self-invocation).

  • Works in 4 steps: Open bundled/db.json and read a… → Whole-board bring-up: append the board's… → Feature work (also part of case 2… → …
  • SKILL.md covers Procedure, What to flip - and what not to and Git
  • Calls python

What it does

Supported Devices is an agent skill from gweslab/cerf. Update the supported-boards list after work on a board (only user triggered, no agent self-invocation).

Its SKILL.md is about 680 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: Universal Windows CE Emulator - CE Runtime Foundation. The licence is MIT.

Example prompts

  • “/supported-devices”

Requirements

  • Python 3

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. Open bundled/db.json and read a neighbouring devices row. That row is the schema - it is current, and any column list written elsewhere…
  2. Whole-board bring-up: append the board's row to devices if absent, copying the shape of a neighbouring row rather than a field list from…
  3. Feature work (also part of case 2 above): sync device_features to reality. Three states, apply them exactly
  4. Run python compile_readme.py (from repo root) to regenerate README.md. Confirm it prints README.md compiled (vX.Y).

What it can do on your machine

Read from SKILL.md and the folder at commit 6b8df83. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • python

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Supported Devices loads about 682 tokens when it runs. Until then it costs about 30 tokens; SKILL.md has 390 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~30
When it runs · the whole SKILL.md, loaded when a task matches
~682

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from gweslab/cerf at commit 6b8df83, republished under its MIT licence (© gweslab). 390 words, ~682 tokens.

Download SKILL.mdSave it as .claude/skills/supported-devices/SKILL.md (or your agent's skills folder).
name
supported-devices
description
Update the supported-boards list after work on a board (only user triggered, no agent self-invocation).

supported-devices - sync the boards list with what just landed

The user invoked /supported-devices. Update the board's row in bundled/db.json to match the board work done this session, then regenerate the README.

User-invoked only. Only the user triggers this skill by typing /supported-devices. An agent never invokes it on its own initiative - landing board work is not a license to edit the boards list.

Procedure

  1. Open bundled/db.json and read a neighbouring devices row. That row is the schema - it is current, and any column list written elsewhere goes stale. agent_docs/database.md covers the rule for what belongs in the database at all, not the columns.

  2. Whole-board bring-up: append the board's row to devices if absent, copying the shape of a neighbouring row rather than a field list from memory - the neighbour is current, any list written here goes stale the next time the schema grows. Its id is exactly what cerf.json board.id names, and operating_system_ids covers the OSes the board actually boots in this cerf version. Set "supported": true if the board is now user-ready (false = early WIP, hidden by default). Add the socs and soc_families rows too when the SoC is new.

  3. Feature work (also part of case 2 above): sync device_features to reality. Three states, apply them exactly:

    • { "feature_id": "x", "supported": true } - hardware present AND working in CERF
    • { "feature_id": "x", "supported": false } - hardware present on the real board but unsupported in CERF
    • entry absent - the board has no such hardware (never write false for hardware that doesn't exist)

    Only feature_id values declared in the device_features table are valid.

  4. Run python compile_readme.py (from repo root) to regenerate README.md. Confirm it prints README.md compiled (vX.Y).

Show full SKILL.md (113 more words)Show less

What to flip - and what not to

  • Flip only what you know. You worked on the board/feature, so you know which features you brought up, which exist but stay unsupported, and which the hardware simply lacks. Do not guess states for features you didn't touch and can't verify - leave them as they are.
  • notes stay blank. Never write or propose notes from this skill - a new device row carries an empty notes array, and existing rows' notes are left untouched.

Git

Do not run any git command unless the user explicitly asks (e.g. "stage your changes", "commit"). When they do, bundled/db.json and the regenerated README.md are both part of the changeset - include both.

© gweslab, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .claude/skills/supported-devices of gweslab/cerf.

Open the folder on GitHubat commit 6b8df83

Compare with similar skills

Supported Devices next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Supported Devices compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Supported Devices this skillgweslab/cerf105—~682Automated safety check: PassMIT
Boardalirezarezvani/claude-skills28k—~610Automated safety check: PassMIT
Paperclip Boardpaperclipai/paperclip99k—~5.3kAutomated safety check: PassMIT
Persona Customer Supportgoogleworkspace/cli31k—~303Automated safety check: PassApache-2.0
Foundation Models On Deviceaffaan-m/ECC276k4 repos~2.1kAutomated safety check: PassMIT
Customer Support Agentmastra-ai/mastra29k—~2.2kAutomated safety check: PassCustom licence

Similar skills

  • Board

    alirezarezvani/claude-skills

    Read, write, and browse the AgentHub message board for agent coordination.

    28k GitHub stars~610 tokensUpdated 1 mo ago
    Agent WorkflowsAuto-check passed

  • Paperclip Board

    paperclipai/paperclip

    Manage a Paperclip company as a board member via chat. An agent skill from paperclipai/paperclip.

    99k GitHub stars~5.3k tokensUpdated today
    Auto-check passed

  • Persona Customer Support

    googleworkspace/cli

    Manage customer support — track tickets, respond, escalate issues.

    31k GitHub stars~303 tokensUpdated 2 days ago
    Sales & SupportAuto-check passed

  • Foundation Models On Device

    affaan-m/ECC

    Apple FoundationModels framework for on-device LLM — text generation, guided generation with @Generable, tool calling, and snapshot streaming in iOS 26+.

    276k GitHub starsUsed in 4 repos~2.1k tokens
    AI & LLM EngineeringAuto-check passed

  • Customer Support Agent

    mastra-ai/mastra

    Authoring playbook for building agents that triage and reply to customer messages — support tickets, email inquiries, chat questions, refund requests, or product issues.

    29k GitHub stars~2.2k tokensUpdated today
    Sales & SupportAuto-check passed

  • Setting Up Support Slack Locally

    PostHog/posthog

    Official

    Connect a real Slack workspace to local PostHog Conversations (the SupportHog Slack app) so Slack messages become support tickets and replies post back.

    40k GitHub stars~2.3k tokensUpdated today
    Backend & APIsAuto-check: notes

More from gweslab/cerf

All 10 skills in this repo

  • Cerf

    gweslab/cerf

    List the project skills and offer the environment doctor. An agent skill from gweslab/cerf.

    105 GitHub stars~1.2k tokensUpdated yesterday
    Auto-check passed

  • Changelog Append

    gweslab/cerf

    Add a changelog entry for a change that was just made (only user triggered, no agent self-invocation).

    105 GitHub stars~864 tokensUpdated yesterday
    Auto-check passed

  • Commit

    gweslab/cerf

    Create a git commit with a short message that describes the diff.

    105 GitHub stars~1.2k tokensUpdated yesterday
    Auto-check passed

  • Start Board Implementation

    gweslab/cerf

    Start the bring-up of a new board or ROM in CERF. An agent skill from gweslab/cerf.

    105 GitHub stars~3.2k tokensUpdated yesterday
    Auto-check passed

  • Tracking

    gweslab/cerf

    Manage the cross-session tracking document with restore, create, update, or compact (only user triggered, no agent self-invocation).

    105 GitHub stars~22k tokensUpdated yesterday
    Auto-check passed

  • Verify

    gweslab/cerf

    Spawn a hostile reviewer that checks a claim or a diff against the project rules.

    105 GitHub stars~5.4k tokensUpdated yesterday
    Auto-check passed

Questions about Supported Devices

What does Supported Devices do?

Update the supported-boards list after work on a board (only user triggered, no agent self-invocation). Supported Devices is an agent skill from gweslab/cerf. Update the supported-boards list after work on a board (only user triggered, no agent self-invocation).

How do I install Supported Devices in Claude Code?

Run `npx skills add gweslab/cerf --skill supported-devices -a claude-code`. Or copy the skill folder (.claude/skills/supported-devices in gweslab/cerf) into .claude/skills/supported-devices in your project. Claude Code loads it when a task matches its description.

How do I install Supported Devices in Codex?

Run `npx skills add gweslab/cerf --skill supported-devices -a codex`. Or copy the skill folder (.claude/skills/supported-devices in gweslab/cerf) into .agents/skills/supported-devices in your project. Codex loads it when a task matches its description.

Can I use Supported Devices in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add gweslab/cerf --skill supported-devices -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/supported-devices, .gemini/skills/supported-devices, .github/skills/supported-devices and .opencode/skills/supported-devices in your project.

What does Supported Devices need to run?

Going by SKILL.md and its folder, Supported Devices needs the command-line tools its instructions call (python). Our summary lists: Python 3.

Does Supported Devices access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Supported Devices safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Supported Devices use?

Supported Devices is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Supported Devices use?

About 682 tokens (SKILL.md is roughly 2.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Supported Devices?

Skills that share tags, products or a category with Supported Devices: Board (alirezarezvani/claude-skills, 28k stars), Paperclip Board (paperclipai/paperclip, 99k stars), Persona Customer Support (googleworkspace/cli, 31k stars) and Foundation Models On Device (affaan-m/ECC, 276k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Supported Devices?

gweslab (a GitHub organization) maintains it in gweslab/cerf, which has 105 GitHub stars. The repository holds 10 skills in this directory. The repository was last updated on October 7, 2026.

Source: gweslab/cerf on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.