SKILLEMALL.ai
GitHub ↗ RU Sign in

BF openclaw-plugin-heygen

Official HeyGen plugin for OpenClaw — adds HeyGen as a first-class provider for the built-in video_generate tool. Identity-first avatar videos: pick an avatar_id, a voice, a script, and get an on-brand presenter video back. Use when: (1) generating a video where a specific avatar/person speaks specific lines, (2) "make a video of me / our brand presenter", (3) outreach, announcements, pitch decks, product walkthroughs, or any presenter-led video, (4) needing landscape or portrait output with deterministic aspect ratios, (5) integrating HeyGen into an OpenClaw agent through the standard provider interface (no bespoke REST glue required). Covers: HeyGen v3 Video Agent (api.heygen.com), avatar-presenter video, identity-preserving video, talking-head AI video, scripted avatar narration, brand spokesperson video. NOT for: cinematic b-roll (use Veo / Runway / Kling), video translation, TTS-only, streaming avatars, or photo-to-talking-head v2 pipelines.

ClawHub Hermes author: Eve v0.1.2 MIT-0 14 files body ≈ 745 tokens Open the sourceclawhub.ai↗ analyzed 4 d ago

As a process F 41/100 · Will not run — References files that are not bundled: LICENSE

ProcedureMedia and videotype and topics are labelled automatically from the skill text
Runs in: OpenClaw Hermes Agent
JSON
Technical rating
B
84/100
safety, quality, tests
Safety 60%
95
Quality 40%
68
Run on models
none yet
Process rating
F
41/100
Will not run
References files that are not bundled: LICENSE
Tools and files w 18
0
Result and completion w 14
0
Inputs and preconditions w 11
0
the three weakest of ten parameters · all ten

How to improve

  1. For Hermes the description must be one sentence under 60 characters; move the conditions to a "When to Use" section.
  2. The text references files that are not there: add them or drop the references.
For the model run — optional
  • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 5

✓ No critical or high findings

Medium and low: 5
  • low Secrets in code secret-high-entropy-token package-lock.json:768
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    "integrity": "sha5…RNq/mC+16R1…A0M+/s6ny…wFA==",
    detector
  • low Secrets in code secret-high-entropy-token package-lock.json:897
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    "integrity": "sha5…QYA+ISs0/2l3T9/kj42…aQT/dfNXWX/ZZCQ==",
    detector
  • low Secrets in code secret-high-entropy-token package-lock.json:1099
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    "integrity": "sha512-6+gjmF…uh8+uw3mnrvgs+dSPQ…dZG+D4garKg==",
    detector
  • low Secrets in code secret-high-entropy-token package-lock.json:1116
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    "integrity": "sha5…DUr+vOv8…A8A==",
    detector
  • low Secrets in code secret-high-entropy-token package-lock.json:1281
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    "integrity": "sha5…byA+l3XtsAj+Q8tf…oOo+X6HZ…Q8A==",
    detector

Files scanned: 14. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-long-hermes description is 961 chars; the Hermes authoring standard requires ≤ 60 (one sentence, ending with a period)
  • warning missing-ref reference to a missing file: LICENSE
  • note frontmatter-key unknown frontmatter key "display_name"
  • note frontmatter-key unknown frontmatter key "homepage"

Process rating: all ten parameters 41/100

Will not run. References files that are not bundled: LICENSE
  • 0Tools and files. 1 referenced file(s) missing: LICENSE
  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Progress reporting. Says nothing while it works
  • 50When it triggers. No condition that starts the skill
  • 50Failures and branches. 0 branches, has a failure section
  • 60Consistency. The Hermes dialect needs category and tags
  • 100Steps. 11 steps
  • 100Execution cost. Instruction body is 745 tokens
  • 100Running it twice. No mutating operations

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +5Description has no quoted example phrases that should trigger the skill
  • +3Description length 960: 120–800 characters recommended
  • +3Output format is not stated: the model decides each time
  • -41 reference files, but SKILL.md never points to them: the model will not open them
  • +2Single-language instructions
  • +4Description says when NOT to use the skill
  • +4Structure: 9 headings
  • +3Step-by-step instructions: 11 items
  • +4Has examples (2 code blocks)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 68.

External checks

ClawHub: clean
This is a coherent HeyGen video-generation plugin, with normal API-key, billing, webhook, and third-party data-sharing caveats.
LLM: benign (high) · VirusTotal: · 29 May 2026