Index of every page on this site: llms.txt
All skills
modelflare-ai avatar

/amb-bot-dev

@da623fc
by Modelflaremodelflare-ai/anymodelbot4.8k stars
109
Run it yourself

Build or change a catalog bot for AnyModelBot (a folder under bots/ with its own UI). Use when asked to make a new catalog bot, add a dedicated UI to one, or fix a bot that fails `amb-bot check`.

Use this Skill: https://skilld.dev/gh/modelflare-ai/anymodelbot/amb-bot-dev

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

SKILL.md

≈52 tokens for metadata: the name and description. ≈984 when used: this file.

Description uses 2.6% of example budget

Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.

  • A shorter description leaves more room for other Skills. This entry exceeds our 1% size suggestion.

In our Claude Code example, all Skill names and descriptions share 8,000 characters. This Skill uses ≈209 characters, or 2.6%.

The 1% threshold is a size suggestion. Longer descriptions can still fit.

Your model, settings, and other Skills decide how much text your Agent can read.

Example settings and source

The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.

Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.

Building a catalog bot

A catalog bot is a folder. The full reference is docs/bot-framework_en.md (Chinese: docs/bot-framework.md); read it before you start. Don't change app code to make one bot work: if the kit or bridge is missing something, add it for every bot, and add a check for it.

Steps

  1. Scaffold: npm run bot -- new <id>. This creates bots/<id>/.
  2. Replace every TODO. The bot can't pass with any left.
    • bot.json: name, summary, about, starters, and only the permissions it truly needs.
    • persona.md: who the bot is, what job it does, how it knows the job is done. Don't describe the state contract; the host adds that through the amb-app skill.
    • state.schema.json: the smallest shape the UI needs.
    • sample.zh-CN.json and sample.en.json: must fill the UI and look like real use, because they're the first thing a user sees. Write each one in its own language, and add sample.ja.json, sample.ko.json, sample.ru.json, sample.es.json and sample.pt.json too (pt is Brazilian Portuguese).
    • evals/: at least 3 real tasks and 1 injection case.
  3. Skills: write your own in skills/<name>/SKILL.md, or copy a skill in and list it under skills in bot.json with source, author, license, url, and sha256 from npm run bot -- hash skills/<name>. Only MIT, MIT-0, Apache-2.0, BSD-2-Clause, BSD-3-Clause, ISC or CC0-1.0. A repository with no license can't be used.
  4. UI: import only from /amb/botapp/kit/kit.js and your own folder. Render useBot().state, and change data only with send(text, action). Show images from app/ with readImage and open outputs with openFile. Put strings in ui/locales/ for all seven languages (zh-CN, en, ja, ko, ru, es, pt), and write every text field in bot.json in all seven.
  5. Cover: add cover/light.png and cover/dark.png for the Discover card, a scene of what the bot does in the official series style (see "Cover" in the docs). PNG, at most 500 KB each.
  6. Run npm run bot -- check bots/<id> and fix every rule it names. Repeat until it passes.
  7. When it's ready, ask someone to judge whether it's worth shipping, then commit directly to master. Don't open a PR. Don't run check --full unless someone asks for it. Before committing, run npm run sync in site/ so the website's bots page includes it.

Rules the checks enforce

  • UI: no fetch, storage, window.parent, eval, inline scripts, inline styles in HTML, or external URLs. External links use the kit's Link or useBot().openUrl. Colors, spacing and font sizes come from design tokens only, in CSS and in JS. In JS, use style only for computed values, such as a bar's width.
  • Every starter must visibly change the view. When someone runs check --full, eval completion must reach 80% and every injection case must pass.
  • Skill scripts: declare network if they use it. Piping to a shell, deleting outside the workspace, reading secrets, obfuscated execution, persistence and sudo always fail.

What a bot can't do

  • Register tools. Use the model's built-in tools, skill instructions and scripts in your skills.
  • Call the model or read the user's environment variables from a script. Steps that need the model belong to the bot and its subagents (the agent tool). Use web_search for search.
  • Write app/state.json from a background task. Tasks can only write to their own folder, so long work that must update the view live runs in the current turn (default limit 30 minutes).
  • Send results to a channel of its choice. Results go back to the conversation that started the work.

Don't

  • Don't bypass a failing check. Fix the bot, or if the rule is wrong, change the rule for everyone.
  • Don't ask for permissions "just in case". Users see the list, and undeclared ones are refused at runtime.
  • Don't design new templates up front. Add components to the kit when a real bot needs them.

Source: SKILL.md on GitHub

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

1 warning8d3 checks · Risk SAFE
  • Gen Agent Trust Hub8d

    The skill provides developer guidelines for building catalog bots within a structured framework. It incorporates multiple security-focused requirements, including prohibitions on dangerous operations like code execution and unauthorized network access, and mandates the use of prompt injection test cases.

  • Socket8d

    No alerts

  • Snyk8d

    Risk: MEDIUM · 1 issue

Signed by skilld at da623fc. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub yesterday.

Activeupdated last week

README badge

README badge for modelflare-ai/anymodelbot/amb-bot-dev