SKILLEMALL.ai
RU Sign in

BC a2e-image

a2e.ai full API: Image Gen (Text2Image, NanoBanana, GPT Image, Flux 2), Video Gen (Image2Video with LoRA/FLF2V support, Video2Video, Kling 3.0, Wan 2.6, Sora 2, Veo 3.1, Seedance), Face/Head Swap, TTS + Voice Clone, AI Avatars, Talking Photo/Video, AI Dubbing, Caption Removal, Virtual Try-On, Photobook. A2E models free for max-users, premium models (Wan, Kling, Seedance etc.) cost coins. Use when asked to generate images, videos, swap faces, clone voices, create avatars, dub audio, or any a2e.ai task.

ClawHub Agent Skills author: DanielGrobelny v2.1.0 MIT-0 9 files · 1 script body ≈ 1 309 tokens Open the sourceclawhub.ai↗ analyzed 2 d ago

As a process C 58/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions

IntegrationMedia and videotype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
B
89/100
safety, quality, tests
Safety 60%
91
Quality 40%
85
Run on models
none yet
Process rating
C
58/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
Progress reporting w 2
0
the three weakest of ten parameters · all ten

How to improve

    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 · 9

    ✓ No critical or high findings

    Medium and low: 9
    • low Exfiltration read-dotenv references/api-key.md:7
      Reads a .env file
      source ~/.openclaw/workspace/.env
    • low Secrets in code secret-high-entropy-token references/openapi-spec-raw.txt:1
      High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file; quoted — discussed, not commanded)
      {"/paths/_api_v1_anchor_character_list.json":"{\n  \"get\": {\n    \"summary\": \"List One or All Avatars\",\n    \"deprecated\": false,\n    \"description\": \"Return all the avatars that are uploade
      fixturequoted
    • low Obfuscation obf-base64-blob references/openapi-spec-raw.txt:5
      Long base64-looking blob (security demo / example; test fixture / example file; quoted — discussed, not commanded)
      {"/paths/_api_v1_r2_get_upload_presigned_url.json":"{\n  \"post\": {\n    \"summary\": \"Get R2 Upload Presigned URL\",\n    \"deprecated\": false,\n    \"description\": \"1. Call this API to obtain a
      demofixturequoted
    • low Obfuscation obf-base64-blob references/openapi-spec-raw.txt:9
      Long base64-looking blob (security demo / example; test fixture / example file; quoted — discussed, not commanded)
      {"/paths/_api_v1_userCaptionRemoval_allProcessing.json":"{\n  \"get\": {\n    \"summary\": \"Get Status of All Tasks in Processing\",\n    \"deprecated\": false,\n    \"description\": \"Retrieve the s
      demofixturequoted
    • low Secrets in code secret-high-entropy-token references/openapi-spec-raw.txt:9
      High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file; quoted — discussed, not commanded)
      {"/paths/_api_v1_userCaptionRemoval_allProcessing.json":"{\n  \"get\": {\n    \"summary\": \"Get Status of All Tasks in Processing\",\n    \"deprecated\": false,\n    \"description\": \"Retrieve the s
      fixturequoted
    • low Obfuscation obf-base64-blob references/openapi-spec-raw.txt:13
      Long base64-looking blob (security demo / example; test fixture / example file; quoted — discussed, not commanded)
      {"/paths/_api…ge_%7B_id%7D.json":"{\n  \"delete\": {\n    \"summary\": \"Delete User Face Swap Image\",\n    \"deprecated\": false,\n    \"description\": \"This endpoint is used to d
      demofixturequoted
    • low Obfuscation obf-base64-blob references/openapi-spec-raw.txt:21
      Long base64-looking blob (code comment; security demo / example; test fixture / example file; quoted — discussed, not commanded)
      {"/paths/_api_v1_userVideoTwin_records.json":"{\n  \"get\": {\n    \"summary\": \"Get Status of All Tasks\",\n    \"deprecated\": false,\n    \"description\": \"Get all the records of the user's video
      commentdemofixturequoted
    • low Exfiltration read-dotenv scripts/a2e.sh:6
      Reads a .env file (detector / deny-list definition)
      A2E_KEY="${A2E_KEY:?Set A2E_KEY environment variable (source ~/.openclaw/workspace/.env)}"
      detector
    • low Exfiltration read-dotenv SKILL.md:15
      Reads a .env file
      source ~/.openclaw/workspace/.env  # loads A2E_KEY

    Files scanned: 9. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    • note frontmatter-key unknown frontmatter key "homepage"

    Process rating: all ten parameters 58/100

    • 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
    • 20When it triggers. No condition that starts the skill
    • 50Failures and branches. 0 branches, has a failure section
    • 100Tools and files. No external tools needed
    • 100Steps. 19 steps
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 1309 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
    • +4Description does not say when NOT to use the skill (false activations)
    • +3Output format is not stated: the model decides each time
    • -5TODO / placeholder text left in the skill
    • +1No license
    • +2Single-language instructions
    • +3Description length 506: enough signal without eating the budget
    • +4Structure: 8 headings
    • +3Step-by-step instructions: 19 items
    • +4Has examples (2 code blocks)
    • +4Reference files are cited in the instructions (1 of 5)
    • +3All 1 scripts are documented

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 85.

    External checks

    ClawHub: suspicious
    This is a real A2E media-generation helper, but it exposes face/voice cloning, remote media storage, paid account actions, and deletion commands without enough safety scoping or confirmation guidance.
    LLM: suspicious (high) · VirusTotal: · 29 May 2026