SKILLEMALL.ai
GitHub ↗ RU Sign in

BD coze-power

Bridge your Coze bots to local machine capabilities. Coze bots run in the cloud and can't access local files, run commands, or control your machine — Coze-Power fixes that with a lightweight HTTP server + Coze-compatible OpenAPI plugin. 10-minute setup: web search, file operations, command execution, clipboard, desktop notifications, and more. Use this skill when: - You want your Coze bot to read/write local files - You need a Coze bot to execute shell commands on your machine - Your Coze bot should search the web and return structured results - You want to give Coze bots local data access (clipboard, directory listings, system info) - You're building a two-way bridge between Coze cloud agents and your local environment - You need to expose OpenClaw agent capabilities to Coze through a webhook/API

ClawHub Agent Skills author: homesickjava v1.0.5 MIT-0 8 files body ≈ 12 881 tokens Open the sourceclawhub.ai↗ analyzed 28 h ago

Bridge your Coze bots to local machine capabilities.

As a process D 40/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions

IntegrationAI 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
86/100
safety, quality, tests
Safety 60%
93
Quality 40%
76
Run on models
none yet
Process rating
D
40/100
Unfinished process
Result and completion w 14
0
Inputs and preconditions w 11
0
Failures and branches w 10
0
the three weakest of ten parameters · all ten

How to improve

  1. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
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 · 7

✓ No critical or high findings

Medium and low: 7
  • low Exfiltration exfil-webhook-url references/coze-plugin-setup.md:38
    Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)
    Copy the forwarding URL: `https://xxxx.ngrok-free.app`
    placeholder
  • low Exfiltration exfil-webhook-url references/coze-plugin-setup.md:47
    Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)
    Copy the URL: `https://xxxx.trycloudflare.com`
    placeholder
  • low Exfiltration exfil-webhook-url references/coze-plugin-setup.md:69
    Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)
    - **Server URL**: Paste your ngrok/cloudflare URL (e.g. `https://xxxx.ngrok-free.app`)
    placeholder
  • low Exfiltration exfil-webhook-url references/coze-plugin-setup.md:102
    Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)
    - Test with curl: `curl https://xxxx.ngrok-free.app/health`
    placeholder
  • low Secrets in code secret-high-entropy-token SKILL.md:23
    High-entropy token-like string (may be an id, hash or a credential)
    ![Coze-Power Architecture](data:image/jpeg;base64,/9j/4AAQ…AAD/4gHY…AAQ
  • low Exfiltration exfil-webhook-url SKILL.md:42
    Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)
    # → https://xxxx.ngrok.io  (copy this URL)
    placeholder
  • low Exfiltration exfil-webhook-url SKILL.md:52
    Webhook / callback URL commonly used for exfiltration (verify the destination) (placeholder value)
    3. Set **Server URL** to your ngrok/cloudflare URL (e.g. `https://xxxx.ngrok.io`)
    placeholder

Files scanned: 8. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 12881 tokens (recommended < 5000); move details to references/

Process rating: all ten parameters 40/100

  • 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. 4 mutating operations with no state check
  • 40Execution cost. Instruction body is 12881 tokens: crowds the task out of the window
  • 60Tools and files. Uses tools (bash, write, web) that frontmatter does not declare
  • 100Steps. 11 steps
  • 100Consistency. Name and required fields are in place
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing

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)
  • +3Description length 809: 120–800 characters recommended
  • +3Output format is not stated: the model decides each time
  • -2localhost URLs: will not work for another user
  • +1No license
  • +2Single-language instructions
  • +4Structure: 14 headings
  • +3Step-by-step instructions: 11 items
  • +4Has examples (3 code blocks)
  • +4Reference files are cited in the instructions (3 of 3)
  • +3All 1 scripts are documented

Quality base 70; lint remarks subtract, signals add up to 100. Result: 76.

External checks

ClawHub: suspicious
This is a disclosed Coze-to-local bridge, but it exposes local file writes, clipboard access, and shell commands over a public tunnel with weak defaults and unsafe command handling.
LLM: suspicious (high) · 5 Jun 2026