Agent skill

Tiny Engineer Speech

by jamro in jamro/tiny-engineer

Makes the Tiny Engineer desk robot speak a short WAV clip through its speaker while it gestures, by posting to its /play endpoint with a bundled script.

Custom licenceAuto-check passedMedia & Creative

Install Tiny Engineer Speech

skills CLI
$ npx skills add jamro/tiny-engineer --skill tiny-engineer-play -a claude-code

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

GitHub CLI
$ gh skill install jamro/tiny-engineer tiny-engineer-play --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/jamro/tiny-engineer.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/tiny-engineer-play .claude/skills/tiny-engineer-play && 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
tiny-engineer-play
GitHub stars
548
Token cost
~492 tokens
SKILL.md length
168 words
Files
2 (incl. scripts)
Skills in repo
3
Repo updated
First seen
Licence
Custom licence

At a glance

Makes the Tiny Engineer desk robot speak a short WAV clip through its speaker while it gestures, by posting to its /play endpoint with a bundled script.

  • Works in 2 steps: Make the clip → Play it
  • Having the robot announce a build or test result out loud
  • SKILL.md covers 1. Make the clip, 2. Play it and Errors
  • Calls ffmpeg; needs TINY_ENGINEER_TOKEN

What it does

The skill makes the Tiny Engineer desk robot play a short audio clip while it runs an animation, then go back to what it was doing. You first create the clip with any text-to-speech the machine has, such as espeak-ng on Linux or say on macOS, then convert it with ffmpeg to 16-bit mono PCM at 22050 Hz, which is the only format the robot accepts.

The bundled scripts/play script sends the clip, with an optional animation of talking, typing, reading, thinking or none. It reads the robot's address and access token from the TINY_ENGINEER_URL and TINY_ENGINEER_TOKEN environment variables, needs curl, prints the robot's reply and exits 1 with the reason on any error. Clips should stay short, up to roughly 20 seconds, because the robot handles one request at a time. A table maps replies such as 415, 400, 401 and robot unreachable to their fixes.

When your agent uses it

  • Having the robot announce a build or test result out loud
  • Greeting the user through the desk robot
  • Celebrating a finished task with a spoken clip
  • Debugging /play errors such as 415 or 400 replies

Example prompts

  • “Tell me through the robot that the build passed.”
  • “Have the desk robot say 'deploy finished' while it types.”
  • “The robot answers 415 on /play, so fix the clip format.”

Requirements

  • A Tiny Engineer desk robot on the same network
  • ffmpeg and a text-to-speech tool such as espeak-ng or say
  • curl
  • TINY_ENGINEER_TOKEN set to the robot's access token

Workflow steps

2 steps, taken from the step headings in SKILL.md.

  1. Make the clip
  2. Play it

What it can do on your machine

Read from SKILL.md and the folder at commit ec87ad7. 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

    Ships 1 file in scripts/, which the agent can run.

    Shell commands in SKILL.md call:

    • ffmpeg

    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 these keys or tokens, usually read from environment variables:

    • TINY_ENGINEER_TOKEN

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

Context cost

Tiny Engineer Speech loads about 492 tokens when it runs. Until then it costs about 88 tokens; SKILL.md has 168 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~88
When it runs · the whole SKILL.md, loaded when a task matches
~492

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); the scripts in this folder are not scanned.

SKILL.md

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 168 words (~492 tokens).

“The robot plays a WAV clip on its speaker while it runs an animation, then goes back to what it was doing. Clips must be 16-bit mono PCM at 22050 Hz.”

— opening of SKILL.md by jamro, Custom licence
name
tiny-engineer-play

Read the full SKILL.md on GitHub

Files

SKILL.md and 1 other file (scripts) in skills/tiny-engineer-play of jamro/tiny-engineer.

  • SKILL.md
  • scripts/play

Open the folder on GitHubat commit ec87ad7

Compare with similar skills

Tiny Engineer Speech 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.

Tiny Engineer Speech compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Tiny Engineer Speech this skilljamro/tiny-engineer548—~492Automated safety check: PassCustom licence
Vox DirectorAlisa0808/vox-director2.2k—~5.6kAutomated safety check: PassMIT
Video Podcast Makerdtsola/xiaoyaosearch1k—~3.4kAutomated safety check: PassMIT
AI Presenter VideoNousResearch/hermes-agent252k—~2.3kAutomated safety check: PassMIT
ElevenLabs Voiceover Generatordigitalsamba/claude-code-video-toolkit2.2k1 repos~2.7kAutomated safety check: NotesMIT
KrillinAI Render Verticalkrillinai/OpenCreator13k—~527Automated safety check: PassApache-2.0

Similar skills

  • Vox Director

    Alisa0808/vox-director

    Turn ONE topic into a finished Vox-style paper-collage explainer / ad video, end to end on the Atlas Cloud API + local ffmpeg — script, collage keyframes, motion, voice-over, music, captions, all…

    2.2k GitHub stars~5.6k tokensUpdated yesterday
    Media & CreativeAuto-check passed
  • Video Podcast Maker

    dtsola/xiaoyaosearch

    Turns a topic into a 4K horizontal video podcast through research, scripting, text-to-speech, Remotion rendering and background music, and can learn styles from references.

    1k GitHub stars~3.4k tokensUpdated 5 days ago
    Media & CreativeAuto-check passed
  • AI Presenter Video

    NousResearch/hermes-agent

    Produces a presenter-led video from a topic or script plus one authorized presenter image, with captions, lip-sync checks and acceptance reports.

    252k GitHub stars~2.3k tokensUpdated today
    Media & CreativeAuto-check passed
  • ElevenLabs Voiceover Generator

    digitalsamba/claude-code-video-toolkit

    Generates narration, sound effects and cloned voices through the ElevenLabs API, with model and setting choices tuned to the content's style.

    2.2k GitHub starsUsed in 1 repo~2.7k tokens
    Media & CreativeAuto-check: notes
  • KrillinAI Render Vertical

    krillinai/OpenCreator

    Renders a source video as a portrait video with the KrillinAI CLI, with short bilingual subtitles or a dubbed audio track, then checks the result.

    13k GitHub stars~527 tokensUpdated 2 days ago
    Media & CreativeAuto-check passed
  • Explain Video

    limin112/min-skill

    Build a narrated explainer video from a concept — discussion → structure → HTML slide deck → narration script → TTS voice → subtitles → background music → Playwright screen recording → ffmpeg…

    359 GitHub stars~2.4k tokensUpdated 14 days ago
    Media & CreativeAuto-check passed

More from jamro/tiny-engineer

  • EasyEDA to KiCad Importer

    jamro/tiny-engineer

    Imports an LCSC part into a Tiny Engineer KiCad board as library files (symbol, footprint, 3D model) using easyeda2kicad and a bundled script.

    548 GitHub stars~569 tokensUpdated today
    Auto-check passed
  • JLCPCB BOM Verifier

    jamro/tiny-engineer

    Checks a KiCad board's production BOM against the schematic, PCB footprints and JLCPCB's parts catalog, then explains which failures are real.

    548 GitHub stars~2k tokensUpdated today
    Auto-check passed

Works with

Questions about Tiny Engineer Speech

What does Tiny Engineer Speech do?

Makes the Tiny Engineer desk robot speak a short WAV clip through its speaker while it gestures, by posting to its /play endpoint with a bundled script. The skill makes the Tiny Engineer desk robot play a short audio clip while it runs an animation, then go back to what it was doing. You first create the clip with any text-to-speech the machine has, such as espeak-ng on Linux or say on macOS, then convert it with ffmpeg to 16-bit mono PCM at 22050 Hz, which is the only format the robot accepts.

When should I use Tiny Engineer Speech?

Tiny Engineer Speech fits situations like: having the robot announce a build or test result out loud; greeting the user through the desk robot; celebrating a finished task with a spoken clip; debugging /play errors such as 415 or 400 replies.

How do I install Tiny Engineer Speech in Claude Code?

Run `npx skills add jamro/tiny-engineer --skill tiny-engineer-play -a claude-code`. Or copy the skill folder (skills/tiny-engineer-play in jamro/tiny-engineer) into .claude/skills/tiny-engineer-play in your project. Claude Code loads it when a task matches its description.

How do I install Tiny Engineer Speech in Codex?

Run `npx skills add jamro/tiny-engineer --skill tiny-engineer-play -a codex`. Or copy the skill folder (skills/tiny-engineer-play in jamro/tiny-engineer) into .agents/skills/tiny-engineer-play in your project. Codex loads it when a task matches its description.

Can I use Tiny Engineer Speech 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 jamro/tiny-engineer --skill tiny-engineer-play -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/tiny-engineer-play, .gemini/skills/tiny-engineer-play, .github/skills/tiny-engineer-play and .opencode/skills/tiny-engineer-play in your project.

What does Tiny Engineer Speech need to run?

Going by SKILL.md and its folder, Tiny Engineer Speech needs the command-line tools its instructions call (ffmpeg) and credentials named TINY_ENGINEER_TOKEN. Our summary lists: A Tiny Engineer desk robot on the same network; ffmpeg and a text-to-speech tool such as espeak-ng or say; curl; TINY_ENGINEER_TOKEN set to the robot's access token.

Does Tiny Engineer Speech 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 Tiny Engineer Speech 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Tiny Engineer Speech use?

Tiny Engineer Speech has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does Tiny Engineer Speech use?

About 492 tokens (SKILL.md is roughly 2k 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 Tiny Engineer Speech?

Skills that share tags, products or a category with Tiny Engineer Speech: Vox Director (Alisa0808/vox-director, 2.2k stars), Video Podcast Maker (dtsola/xiaoyaosearch, 1k stars), AI Presenter Video (NousResearch/hermes-agent, 252k stars) and ElevenLabs Voiceover Generator (digitalsamba/claude-code-video-toolkit, 2.2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Tiny Engineer Speech?

jamro (a GitHub user) maintains it in jamro/tiny-engineer, which has 548 GitHub stars. The repository holds 3 skills in this directory. The repository was last updated on October 6, 2026.

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