setup-api-key
Skill527 starsChanged 14 days agoMITView on GitHub
Fix or hand-configure an existing ElevenLabs API key. Use when a key stopped working (401 or invalid_api_key), when an administrator issued the key, when the user's role cannot create keys, or when the user already has a key and needs it in the right place. Checks whether ELEVENLABS_API_KEY is configured and valid, without reading it into the conversation. Not for first-time setup or adding ElevenLabs to a project (use onboarding).
- Pipes a download into a shell
- Reads credentials
- Installs packages
We split this skill into the rules it gives an agent
7 rules. 0 are common, 2 are distinctive, and 5 are very specific to this project.
0
Common
Most of the 7 edited versions we read keep these.
2
Distinctive
This author's own choices. Worth a look.
5
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 24
A key that stopped working: run the same command from the app's folder.
- Very specific: line 46
Never open, print or cat the env file, and never echo ELEVENLABS_API_KEY.
- Distinctive: line 48
Never ask for an API key in chat, and never accept one pasted there.
- Very specific: line 50
Never put the key in code.
- Distinctive: line 51
Don't run the app (or its start script) or make speech to try it until the user says yes.
- Very specific: line 60
If npx isn't available (Node.js isn't installed), install the CLI (or update it if it's already installed: brew upgrade elevenlabs, or run …
- Very specific: line 68
If elevenlabs isn't found after the installer ran, use ~/.cargo/bin/elevenlabs in its place, here and in every run the CLI gives.
“Common” is measured: kept by at least 6 in 10 of the 7 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
ElevenLabs API Key Setup
For a key the user already has, or one that stopped working. For adding
ElevenLabs to a project from scratch, use the onboarding skill.
A key the user already has (for example from an administrator): don't
sign in for a new one. Tell them to paste it after ELEVENLABS_API_KEY= in
the env file of the app that uses it (.env.local, or .env in a Python
project), never into this chat, and to tell you when it's done. Then check it
(if check finds no key, or ElevenLabs rejects it, and offers to sign in,
ask the user to check the paste instead of signing in):
npx -y @elevenlabs/cli@latest onboard checkA key that stopped working: run the same command from the app's folder.
It finds the key the app would use (the shell, the env file, or a .env up
the tree), checks it with ElevenLabs without printing it, and prints JSON:
next is the step (spelled out in instruction; where the list below differs,
follow the list), run the exact command, and say what to tell the user (tell
them as written). Follow it until the key works; for a rejected key it
signs the user in for a new one. What each next means:
run: runrun.wait: showsay, then runrunagain right away.ask_user, or afixthat needs the user's shell or secrets: ask them whatsaysays, wait for their answer, then runrun, unless they said no.write_code: if the app already readsELEVENLABS_API_KEY(through the SDK or its own requests), don't change its code: afterconnect, runrun; aftercheck, tell the user the key works (notsay) and stop. Otherwise make sure the code uses the SDK, then runrun; if nothing shows what the app should do with ElevenLabs, ask the user first, and don't pick a product for them.offer_test: ask the question insay; runrunonly if they say yes.done: tell the usersay.
Rules
- Never open, print or
catthe env file, and never echoELEVENLABS_API_KEY;onboard checkverifies the key for you. - Never ask for an API key in chat, and never accept one pasted there. If one appears, tell the user to rotate it on the API keys page.
- Never put the key in code; the SDK reads
ELEVENLABS_API_KEY. - Don't run the app (or its start script) or make speech to try it until the
user says yes. API calls that what they asked for needs, like creating an
agent, are fine. Once the code is written, run
onboard checkbefore you finish: it verifies the key and the code. - For browser or client-side apps, keep the key on the server and issue short-lived tokens where the product supports them.
No npx
If npx isn't available (Node.js isn't installed), install the CLI (or
update it if it's already installed: brew upgrade elevenlabs, or run the
installer again), then run elevenlabs onboard check instead:
- macOS or Linux:
brew install elevenlabs/tap/elevenlabs, orcurl --proto '=https' --tlsv1.2 -LsSf https://github.com/elevenlabs/cli/releases/latest/download/elevenlabs-cli-installer.sh | sh - Windows:
powershell -ExecutionPolicy ByPass -c "irm https://github.com/elevenlabs/cli/releases/latest/download/elevenlabs-cli-installer.ps1 | iex"
If elevenlabs isn't found after the installer ran, use
~/.cargo/bin/elevenlabs in its place, here and in every run the CLI gives.
Other versions8 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 8
- calesthio/OpenMontage★ 74ksame name
- sonilo-ai/skills★ 117same name
- VapiAI/skills★ 68same name
- LinHao-city/StoryMind★ 10same name
- elevenlabs/plugin★ 3same name
- Gopyr/gopyr-skills-hub★ 0same name
- Talkif-ai/skills★ 0same name
- thunderphone/skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository12 other files it gives its agents.
- agentsSkill
- update-skills-from-changelogSkill
- dubbingSkill
- musicSkill
- onboardingSkill
- realtimeSkill
- sound-effectsSkill
- speech-engineSkill
- speech-to-textSkill
- text-to-speechSkill
- voice-changerSkill
- voice-isolatorSkill
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

