SKILLEMALL.ai
GitHub ↗ RU Sign in

BF openclaw-agent-live

将 OpenClaw Agent 的完整推理链路实时推流到 TRTC 房间，支持虚拟形象叠加（浏览器端渲染）、TTS 语音播报 Agent 状态、双向交互（timbot IM 单聊触发 Agent 执行），支持公网 Lighthouse IP 访问。

ClawHub Agent Skills author: Jerryang v1.0.2 MIT-0 19 files body ≈ 3 925 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process F 28/100 · Will not run — References files that are not bundled: assets/fonts/Symbols.ttf, references/architecture.md

ProcedureAI and agentstype 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
80/100
safety, quality, tests
Safety 60%
96
Quality 40%
56
Run on models
none yet
Process rating
F
28/100
Will not run
References files that are not bundled: assets/fonts/Symbols.ttf, references/architecture.md
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. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
  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 · 4

✓ No critical or high findings

Medium and low: 4
  • low Dangerous commands cmd-background-process scripts/platform_utils.py:292
    Starts a background / autostarted process (string literal in code, not executed)
    Linux  : 经典双 fork + setsid
    code literal
  • low Dangerous commands cmd-background-process scripts/platform_utils.py:302
    Starts a background / autostarted process
    os.setsid()
  • low Exfiltration net-credential-use SKILL.md:225
    Credential used in a network call (verify the destination is the intended service) (documentation table row)
    | `$CALLBACK_TOKEN` | [IM 控制台回调配置](https://console.cloud.tencent.com/im) | ⚠️ 强烈推荐 | IM 消息回调鉴权 Token（**必须与 IM 控制台中配置的回调 URL Token 完全一致**） |
    table
  • low Exfiltration net-credential-use SKILL.md:226
    Credential used in a network call (verify the destination is the intended service) (documentation table row)
    | `$CAM_SECRET_ID` | [CAM 密钥管理](https://console.cloud.tencent.com/cam/capi) | 推荐 | 腾讯云 API 密钥 ID（格式 `AKIDxxxxxxxx`） |
    table

Files scanned: 19. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-no-when description does not say WHEN to use the skill (no "use when")
  • warning missing-ref reference to a missing file: assets/fonts/Symbols.ttf
  • warning missing-ref reference to a missing file: references/architecture.md

Process rating: all ten parameters 28/100

Will not run. References files that are not bundled: assets/fonts/Symbols.ttf, references/architecture.md
  • 0Tools and files. 2 referenced file(s) missing: assets/fonts/Symbols.ttf, references/architecture.md
  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Failures and branches. Linear process with no failure handling
  • 0Progress reporting. Says nothing while it works
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 2 mutating operations with no state check
  • 40Consistency. Frontmatter name (openclaw-agent-live) differs from the folder (liveclaw)
  • 100Steps. 103 steps
  • 100Execution cost. Instruction body is 3925 tokens
  • low 11 top-level sections: this looks like several domains in one skill

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
  • -2localhost URLs: will not work for another user
  • -244 emoji in the instructions: noise for the model
  • -35 of 10 scripts are never mentioned in SKILL.md
  • +1No license
  • +2Single-language instructions
  • +3Description length 125: enough signal without eating the budget
  • +4Structure: 29 headings
  • +3Step-by-step instructions: 103 items
  • +4Has examples (18 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 56.

External checks

ClawHub: suspicious
This live-streaming skill is not clearly malicious, but it makes broad persistent platform changes and exposes sensitive live-control functions that need review before installation.
LLM: suspicious (high) · VirusTotal: · 29 May 2026