heygen
Prepare guarded HeyGen Direct API requests for avatar video generation, video translation, asset discovery, and status polling.
Skill by HybridAIOne
Chalk Labs
Need help deploying heygen?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/hybridaione-heygen
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: backend
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/heygen
What's inside
- Skill name
heygen- Description
- Prepare guarded HeyGen Direct API requests for avatar video generation, video translation, asset discovery, and status polling.
- License
- MIT
- Instructions
- 220 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
Files (6)
- SKILL.md
- client.cjs
- eval.cjs
- heygen.cjs
- index.cjs
- common.cjs · lib/
SKILL.md (first lines)
# HeyGen
Use this skill for HeyGen Direct API work: avatar and voice discovery, guarded
avatar video generation from approved scripts, video translation with lip-sync,
and polling asynchronous generation or translation status.
## Scope
- list available avatars, voices, and video-translation target languages
- create gateway-proxied requests for `POST /v2/videos`
- create gateway-proxied requests for `POST /v2/video_translate`
- poll `GET /v1/video_status.get` and `GET /v2/video_translate/{id}`
- classify and retry HeyGen 429, quota, and transient upstream responses with
bounded `Retry-After` aware backoff
- block private or internal media URLs before asking HeyGen to fetch them
- require explicit operator grant before credit-consuming generate/translate calls
Custom avatar training, live streaming, real-time avatars, public publishing,
and distribution to external channels are outside this adapter slice.
## Credential Rules
HeyGen Direct API uses an API key sent as `X-API-KEY`. Store it in HybridClaw
encrypted runtime secrets; never paste it into the prompt.
Recommended setup order:
1. Browser admin: open the active HybridClaw admin URL ending in `/admin/secrets` and set
`HEYGEN_API_KEY`.
2. Browser `/chat` or TUI fallback: `/secret set HEYGEN_API_KEY "<api-key>"`.
3. Local console fallback:
```bash
hybridclaw secret set HEYGEN_API_KEY "<api-key>"
```
For live API calls inside HybridClaw, prefer the helper's `request` command. It
sends the secret-backed payload through the local gateway, retries bounded
429/5xx responses, summarizes large asset lists by default, and fails clearly
if the gateway truncates a response.
Use `http-request` only when you need to inspect or hand off the generated
payload wrapper to the built-in `http_request` tool. The helper sets
`secretHeaders: [{ "name": "X-API-KEY", "secretName": "HEYGEN_API_KEY",
"prefix": "" }]` so the gateway injects the API key server-side.
Do not try to verify `HEYGEN_API_KEY` with bash, environment inspection, or by
asking the model whether the secret exists. The model cannot inspect the
gateway secret store. If the operator says the secret was set, attempt the
`http_request` call with the emitted `secretHeaders`. Only say the secret is
missing if `http_request` returns a gateway error that explicitly says
`HEYGEN_API_KEY` is not set, unavailable, missing, or unresolved.
## Default Workflow
1. Start with `request list-avatars` and `request list-voices` unless the
avatar and voice ids are already known. These commands return concise
summaries by default; use `--limit <count>` to show more candidates. Asset
ids are opaque values; never use display names as `--avatar-id` or
`--voice-id`.
2. Run the script through `/brand-voice` before generating avatar video from
marketing, sales, training, or public-facing copy.
3. Use `plan` for natural-language generation or translation requests so the
stakes tier and required grant are explicit.
4. Do not emit `generate-video` or `translate-video` requests unless the user
has granted that exact credit-consuming operation in the current task or
through an approved F8 escalation.
5. Poll status with `request video-status --watch` or
`request translation-status --watch`. Use a bounded polling budget, respect
`Retry-After`, avoid parallel polling loops, and stop if HeyGen reports
quota, credit, or rate-limit failure.
6. Treat auto-publish to public channels as red tier and escalate before any
upload, share link, social post, or public channel message.
## Command Contract
Run the colocated helper with Node:
```bash
node skills/heygen/heygen.cjs --help
```
Plan a request without contacting HeyGen:
```bash
node skills/heygen/heygen.cjs plan "Create an approved onboarding video from this script"
```
List avatars, voices, or translation languages. Asset lists use compact summary
output by default:
```bash
node skills/heygen/heygen.cjs request list-avatars --limit 10
node skills/heygen/heygen.cjs request list-voices --limit 10
node skills/heygen/heygen.cjs request list-translation-languages
```
Generate an avatar video only after explicit operator grant:
```bash
node skills/heygen/heygen.cjs http-request generate-video \
--avatar-id avatar_123 \
--voice-id voice_123 \
--script "Approved script text" \
--title "Quarterly enablement update" \
--resolution 1080p \
--aspect-ratio 16:9 \
--operator-grant
```
Translate a video only after explicit operator grant:
```bash
node skills/heygen/heygen.cjs http-request translate-video \
--video-url https://example.com/source.mp4 \
--output-language de \
--mode fast \
--operator-grant
```From HybridAIOne/hybridclaw, MIT.
More from HybridAIOne/hybridclaw
- 0.720score
manim-video
HybridAIOne
Plan, script, render, and stitch Manim Community Edition videos in Python.
SkillAFreshness: A★ 159Claude Code +9 - 0.720score
datalion
HybridAIOne
Use for DataLion workflows such as listing, reading, creating, or editing projects, inspecting data sources, importing Excel or CSV data, working with reports…
SkillAFreshness: A★ 159Claude Code +9 - 0.720score
langfuse
HybridAIOne
Use Langfuse for LLM observability and evaluation and look up Langfuse documentation.
SkillAFreshness: A★ 159Claude Code +9 - 0.720score
hermes3000-writing
HybridAIOne
Use Hermes3000 to plan, draft, revise, save, check consistency, and export long-form manuscripts through the Hermes3000 AI writing portal API.
SkillAFreshness: A★ 159Claude Code +9 - 0.720score
human-distill
HybridAIOne
Distill a real person into a hireable coworker agent from their source material — chat exports, emails, meeting transcripts, documents, interviews, and live…
SkillAFreshness: A★ 159Claude Code +9 - 0.716score
ga4
HybridAIOne
Run production Google Analytics 4 Data API reports with gateway-injected bearer auth, safe request review, traffic source, landing-page, time-series, revenue…
SkillAFreshness: A★ 159Claude Code +9 - 0.716score
meme-generation
HybridAIOne
Generate meme images from curated classic templates, dynamic imgflip templates, or a custom image.
SkillAFreshness: A★ 159Claude Code +9 - 0.716score
excalidraw
HybridAIOne
Create and revise editable `.excalidraw` diagrams as Excalidraw JSON for architecture diagrams, flowcharts, sequence diagrams, concept maps, and other…
SkillAFreshness: A★ 159Claude Code +9 - 0.716score
diagram
HybridAIOne
Create, validate, update, and render diagram-as-code artifacts with Mermaid-first schema awareness plus PlantUML, Graphviz DOT, and Excalidraw JSON adapters.
SkillAFreshness: A★ 159Claude Code +9 - 0.716score
agentic-tpm
HybridAIOne
Coordinate cross-functional project delivery by tracking commitments, dependencies, decisions, and risks; maintain project context and prepare bounded…
SkillAFreshness: A★ 159Claude Code +9 - 0.716score
distil-pii-redactor
HybridAIOne
Redact, anonymize, sanitize, or remove PII locally with Distil-PII and llama.cpp; keep personal data and secret values out of model context, logs, and chat.
SkillAFreshness: A★ 159Claude Code +9 - 0.716score
google-ads
HybridAIOne
Manage Google Ads accounts with safe GAQL reporting, campaign planning, guarded mutations, and gateway-proxied REST API calls.
SkillAFreshness: A★ 159Claude Code +9
Signals
- Stars
- 159
- Forks
- 17
- Open issues
- 323
- Last commit (this folder)
- Jul 2, 2026 (4 months ago)
- Last release
- Oct 24, 2026 (6 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/HybridAIOne/hybridclaw
- Website
- www.hybridclaw.io/
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from HybridAIOne
- 0.720score
human-distill
HybridAIOne
Distill a real person into a hireable coworker agent from their source material — chat exports, emails, meeting transcripts, documents, interviews, and live…
SkillAFreshness: A★ 159Claude Code +9 - 0.720score
manim-video
HybridAIOne
Plan, script, render, and stitch Manim Community Edition videos in Python.
SkillAFreshness: A★ 159Claude Code +9 - 0.720score
datalion
HybridAIOne
Use for DataLion workflows such as listing, reading, creating, or editing projects, inspecting data sources, importing Excel or CSV data, working with reports…
SkillAFreshness: A★ 159Claude Code +9 - 0.720score
hermes3000-writing
HybridAIOne
Use Hermes3000 to plan, draft, revise, save, check consistency, and export long-form manuscripts through the Hermes3000 AI writing portal API.
SkillAFreshness: A★ 159Claude Code +9 - 0.720score
langfuse
HybridAIOne
Use Langfuse for LLM observability and evaluation and look up Langfuse documentation.
SkillAFreshness: A★ 159Claude Code +9 - 0.716score
meme-generation
HybridAIOne
Generate meme images from curated classic templates, dynamic imgflip templates, or a custom image.
SkillAFreshness: A★ 159Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get heygen running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
heygen skill. Agent Mart. https://agentmart.dev/skills/hybridaione-heygen (last updated 2026-10-24)