SKILLEMALL.ai
GitHub ↗ RU Sign in

DD wechat-studio

Launch a local WeChat article workbench for Markdown import, WeChat HTML preview, theme tuning, image selection, and optional draft push. Use when Codex needs a browser-based preview and manual QA layer before publishing.

Not recommendedlow grade D
ClawHub Agent Skills author: Abigale-cyber v1.0.1 MIT-0 64 files body ≈ 544 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process D 38/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions

GeneratorWriting and documentsInfrastructureSoftware developmenttype 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
D
48/100
safety, quality, tests
Safety 60%
25
Quality 40%
82
Run on models
none yet
Process rating
D
38/100
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

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Obfuscation medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The files contain invisible characters, encoded commands or comments hidden from readers but visible to the model. What you read differs from what the agent sees.

For the author

Remove invisible characters (they usually sneak in through copy-paste) and encoded strings: no catalog will pass them. Instructions for the model must be readable by a human too.

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 · 43

    ✓ No critical or high findings

    Medium and low: 43
    • medium Obfuscation obf-hex-escape-chain content/articles/2026-04-06-harness-engineering-2/doocs.md:31
      Escaped/char-code string obfuscation
      5. [电动汽车的五大趋势及其对线束设计的影响 - Cadonix](https://www.cadonix.com/zh-hans/%E7%94%B5%E5%8A%A8%E6%B1%BD%E8%BD%A6%E7%BA%BF%E6%9D%9F%E8%AE%BE%E8%AE%A1%E7%9A%84%E4%BA%94%E5%A4%A7%E8%B6%8B%E5%8A%BF)
    • medium Obfuscation obf-hex-escape-chain content/articles/2026-04-06-harness-engineering-2/doocs.md:32
      Escaped/char-code string obfuscation
      6. [线束培训资料网站及视频资源 – 知默 | 一个线束工程师的资源站](http://www.…com/2025/04/30/%E7%BA%BF%E6%9D%9F%E5%9F%B9%E8%AE%AD%E8%B5%84%E6%96%99%E7%BD%91%E7%AB%99%E5%8F%8A%E8%A7%86%E9%A2%91%E8%B5%84%E6%BA%90/)
    • medium Obfuscation obf-hex-escape-chain content/articles/2026-04-06-harness-engineering-2/doocs.md:46
      Escaped/char-code string obfuscation
      - [电动汽车的五大趋势及其对线束设计的影响 - Cadonix](https://www.cadonix.com/zh-hans/%E7%94%B5%E5%8A%A8%E6%B1%BD%E8%BD%A6%E7%BA%BF%E6%9D%9F%E8%AE%BE%E8%AE%A1%E7%9A%84%E4%BA%94%E5%A4%A7%E8%B6%8B%E5%8A%BF)
    • medium Obfuscation obf-hex-escape-chain content/articles/2026-04-06-harness-engineering-2/doocs.md:47
      Escaped/char-code string obfuscation
      - [线束培训资料网站及视频资源 – 知默 | 一个线束工程师的资源站](http://www.…com/2025/04/30/%E7%BA%BF%E6%9D%9F%E5%9F%B9%E8%AE%AD%E8%B5%84%E6%96%99%E7%BD%91%E7%AB%99%E5%8F%8A%E8%A7%86%E9%A2%91%E8%B5%84%E6%BA%90/)
    • medium Obfuscation obf-hex-escape-chain content/articles/2026-04-06-harness-engineering-2/source.md:26
      Escaped/char-code string obfuscation
      5. [电动汽车的五大趋势及其对线束设计的影响 - Cadonix](https://www.cadonix.com/zh-hans/%E7%94%B5%E5%8A%A8%E6%B1%BD%E8%BD%A6%E7%BA%BF%E6%9D%9F%E8%AE%BE%E8%AE%A1%E7%9A%84%E4%BA%94%E5%A4%A7%E8%B6%8B%E5%8A%BF)
    • medium Obfuscation obf-hex-escape-chain content/articles/2026-04-06-harness-engineering-2/source.md:27
      Escaped/char-code string obfuscation
      6. [线束培训资料网站及视频资源 – 知默 | 一个线束工程师的资源站](http://www.…com/2025/04/30/%E7%BA%BF%E6%9D%9F%E5%9F%B9%E8%AE%AD%E8%B5%84%E6%96%99%E7%BD%91%E7%AB%99%E5%8F%8A%E8%A7%86%E9%A2%91%E8%B5%84%E6%BA%90/)
    • medium Obfuscation obf-hex-escape-chain content/articles/2026-04-06-harness-engineering-2/source.md:41
      Escaped/char-code string obfuscation
      - [电动汽车的五大趋势及其对线束设计的影响 - Cadonix](https://www.cadonix.com/zh-hans/%E7%94%B5%E5%8A%A8%E6%B1%BD%E8%BD%A6%E7%BA%BF%E6%9D%9F%E8%AE%BE%E8%AE%A1%E7%9A%84%E4%BA%94%E5%A4%A7%E8%B6%8B%E5%8A%BF)
    • medium Obfuscation obf-hex-escape-chain content/articles/2026-04-06-harness-engineering-2/source.md:42
      Escaped/char-code string obfuscation
      - [线束培训资料网站及视频资源 – 知默 | 一个线束工程师的资源站](http://www.…com/2025/04/30/%E7%BA%BF%E6%9D%9F%E5%9F%B9%E8%AE%AD%E8%B5%84%E6%96%99%E7%BD%91%E7%AB%99%E5%8F%8A%E8%A7%86%E9%A2%91%E8%B5%84%E6%BA%90/)
    • low Obfuscation obf-base64-blob content/articles/2026-03-28-ai-art-advantage/studio-state.json:39
      Long base64-looking blob (quoted — discussed, not commanded)
      "previewUrl": "https://s3.s….cn/default/outputs/2pnp…png?X-Amz-Algorithm=…&X-Amz-Credential=…
      quoted
    • low Secrets in code secret-aws-key content/articles/2026-03-28-ai-art-advantage/studio-state.json:39
      AWS access key ID (placeholder value)
      "previewUrl": "https://s3.s….cn/default/outputs/2pnp…png?X-Amz-Algorithm=…&X-Amz-Credential=…
      placeholder
    • low Obfuscation obf-base64-blob content/articles/2026-03-28-ai-art-advantage/studio-state.json:40
      Long base64-looking blob (detector / deny-list definition)
      "draftUrl": "http://mmbiz.qpic.cn/sz_mmbiz_png/TTkq…jPg/0?wx_fmt=png",
      detector
    • low Obfuscation obf-base64-blob content/articles/2026-03-28-ai-art-advantage/studio-state.json:52
      Long base64-looking blob (quoted — discussed, not commanded)
      "previewUrl": "https://s3.s….cn/default/outputs/2pnp…png?X-Amz-Algorithm=…&X-Amz-Credential=…
      quoted
    • low Secrets in code secret-aws-key content/articles/2026-03-28-ai-art-advantage/studio-state.json:52
      AWS access key ID (placeholder value)
      "previewUrl": "https://s3.s….cn/default/outputs/2pnp…png?X-Amz-Algorithm=…&X-Amz-Credential=…
      placeholder
    • low Obfuscation obf-base64-blob content/articles/2026-03-28-ai-art-advantage/studio-state.json:53
      Long base64-looking blob (detector / deny-list definition)
      "draftUrl": "http://mmbiz.qpic.cn/sz_mmbiz_png/TTkq…jPg/0?wx_fmt=png",
      detector
    • low Obfuscation obf-base64-blob content/articles/2026-03-28-ai-art-advantage/studio-state.json:81
      Long base64-looking blob (quoted — discussed, not commanded)
      "previewUrl": "http://mmbiz.qpic.cn/sz_mmbiz_jpg/TTkq…kdw/0?wx_fmt=jpeg",
      quoted
    • low Secrets in code secret-aws-key content/articles/2026-03-28-ai-art-advantage/studio-state.json:147
      AWS access key ID (placeholder value)
      "previewUrl": "https://s3.s….cn/default/outputs/2snh…png?X-Amz-Algorithm=…&X-Amz-Credential=…
      placeholder
    • low Secrets in code secret-aws-key content/articles/2026-03-28-ai-art-advantage/studio-state.json:185
      AWS access key ID (placeholder value)
      "previewUrl": "https://s3.s….cn/default/outputs/24nm…png?X-Amz-Algorithm=…&X-Amz-Credential=…
      placeholder
    • low Secrets in code secret-aws-key content/articles/2026-03-28-ai-art-advantage/studio-state.json:260
      AWS access key ID (placeholder value)
      "previewUrl": "https://s3.s….cn/default/outputs/2snh…png?X-Amz-Algorithm=…&X-Amz-Credential=…
      placeholder
    • low Obfuscation obf-base64-blob content/articles/2026-03-29-ai-agent-rag/studio-state.json:39
      Long base64-looking blob (quoted — discussed, not commanded)
      "previewUrl": "http://mmbiz.qpic.cn/mmbiz_jpg/TTkq…yT0/0?wx_fmt=jpeg",
      quoted
    • low Obfuscation obf-base64-blob content/articles/2026-03-29-ai-agent-rag/studio-state.json:40
      Long base64-looking blob (quoted — discussed, not commanded)
      "draftUrl": "http://mmbiz.qpic.cn/mmbiz_jpg/TTkq…yT0/0?wx_fmt=jpeg",
      quoted
    • low Obfuscation obf-base64-blob content/articles/2026-03-29-ai-agent-rag/studio-state.json:55
      Long base64-looking blob (quoted — discussed, not commanded)
      "previewUrl": "http://mmbiz.qpic.cn/sz_mmbiz_jpg/TTkq…wBU/0?wx_fmt=jpeg",
      quoted
    • low Obfuscation obf-base64-blob content/articles/2026-03-29-ai-agent-rag/studio-state.json:56
      Long base64-looking blob (quoted — discussed, not commanded)
      "draftUrl": "http://mmbiz.qpic.cn/sz_mmbiz_jpg/TTkq…wBU/0?wx_fmt=jpeg",
      quoted
    • low Obfuscation obf-base64-blob content/articles/2026-03-29-ai-agent-rag/studio-state.json:70
      Long base64-looking blob (quoted — discussed, not commanded)
      "previewUrl": "http://mmbiz.qpic.cn/sz_mmbiz_jpg/TTkq…cYU/0?wx_fmt=jpeg",
      quoted
    • low Obfuscation obf-base64-blob content/articles/2026-03-29-ai/studio-state.json:39
      Long base64-looking blob (quoted — discussed, not commanded)
      "previewUrl": "http://mmbiz.qpic.cn/mmbiz_jpg/TTkq…azg/0?wx_fmt=jpeg",
      quoted
    • low Obfuscation obf-base64-blob content/articles/2026-03-29-ai/studio-state.json:40
      Long base64-looking blob (quoted — discussed, not commanded)
      "draftUrl": "http://mmbiz.qpic.cn/mmbiz_jpg/TTkq…azg/0?wx_fmt=jpeg",
      quoted
    • low Obfuscation obf-base64-blob content/articles/2026-03-29-ai/studio-state.json:55
      Long base64-looking blob (quoted — discussed, not commanded)
      "previewUrl": "http://mmbiz.qpic.cn/mmbiz_jpg/TTkq…aBY/0?wx_fmt=jpeg",
      quoted
    • low Obfuscation obf-base64-blob content/articles/2026-03-29-ai/studio-state.json:56
      Long base64-looking blob (quoted — discussed, not commanded)
      "draftUrl": "http://mmbiz.qpic.cn/mmbiz_jpg/TTkq…aBY/0?wx_fmt=jpeg",
      quoted
    • low Obfuscation obf-base64-blob content/articles/2026-03-29-ai/studio-state.json:70
      Long base64-looking blob (quoted — discussed, not commanded)
      "previewUrl": "http://mmbiz.qpic.cn/mmbiz_jpg/TTkq…azg/0?wx_fmt=jpeg",
      quoted
    • low Obfuscation obf-base64-blob content/articles/2026-04-06-harness-engineering-2/studio-state.json:41
      Long base64-looking blob (quoted — discussed, not commanded)
      "previewUrl": "http://mmbiz.qpic.cn/sz_mmbiz_jpg/TTkq…jKs/0?wx_fmt=jpeg",
      quoted
    • low Obfuscation obf-base64-blob content/articles/2026-04-06-harness-engineering-2/studio-state.json:42
      Long base64-looking blob (quoted — discussed, not commanded)
      "draftUrl": "http://mmbiz.qpic.cn/sz_mmbiz_jpg/TTkq…jKs/0?wx_fmt=jpeg",
      quoted
    • low Obfuscation obf-base64-blob content/articles/2026-04-06-harness-engineering-2/studio-state.json:58
      Long base64-looking blob (quoted — discussed, not commanded)
      "previewUrl": "http://mmbiz.qpic.cn/sz_mmbiz_jpg/TTkq…O3M/0?wx_fmt=jpeg",
      quoted
    • low Obfuscation obf-base64-blob content/articles/2026-04-06-harness-engineering-2/studio-state.json:59
      Long base64-looking blob (quoted — discussed, not commanded)
      "draftUrl": "http://mmbiz.qpic.cn/sz_mmbiz_jpg/TTkq…O3M/0?wx_fmt=jpeg",
      quoted
    • low Obfuscation obf-base64-blob content/articles/2026-04-06-harness-engineering-2/studio-state.json:74
      Long base64-looking blob (quoted — discussed, not commanded)
      "previewUrl": "http://mmbiz.qpic.cn/sz_mmbiz_jpg/TTkq…WK0/0?wx_fmt=jpeg",
      quoted
    • low Obfuscation obf-base64-blob content/articles/2026-04-07-vibe-coding-harness-engineering/studio-state.json:41
      Long base64-looking blob (quoted — discussed, not commanded)
      "previewUrl": "http://mmbiz.qpic.cn/sz_mmbiz_jpg/TTkq…g0c/0?wx_fmt=jpeg",
      quoted
    • low Obfuscation obf-base64-blob content/articles/2026-04-07-vibe-coding-harness-engineering/studio-state.json:42
      Long base64-looking blob (quoted — discussed, not commanded)
      "draftUrl": "http://mmbiz.qpic.cn/sz_mmbiz_jpg/TTkq…g0c/0?wx_fmt=jpeg",
      quoted
    • low Obfuscation obf-base64-blob content/articles/2026-04-07-vibe-coding-harness-engineering/studio-state.json:58
      Long base64-looking blob (quoted — discussed, not commanded)
      "previewUrl": "http://mmbiz.qpic.cn/sz_mmbiz_jpg/TTkq…g0c/0?wx_fmt=jpeg",
      quoted
    • low Obfuscation obf-base64-blob content/articles/2026-04-07-vibe-coding-harness-engineering/studio-state.json:59
      Long base64-looking blob (quoted — discussed, not commanded)
      "draftUrl": "http://mmbiz.qpic.cn/sz_mmbiz_jpg/TTkq…g0c/0?wx_fmt=jpeg",
      quoted
    • low Obfuscation obf-base64-blob content/articles/2026-04-07-vibe-coding-harness-engineering/studio-state.json:74
      Long base64-looking blob (quoted — discussed, not commanded)
      "previewUrl": "http://mmbiz.qpic.cn/mmbiz_jpg/TTkq…90k/0?wx_fmt=jpeg",
      quoted
    • low Secrets in code secret-high-entropy-token frontend/package-lock.json:18
      High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
      "integrity": "sha5…uWm+fFRcIOgKBMiOBP+eXiy…9ab+DDKA==",
      detector
    • low Obfuscation obf-base64-blob frontend/tmp-spring-preview.html:1
      Long base64-looking blob (quoted — discussed, not commanded)
      <!doctype html><html lang="zh-CN"><head><meta charset="utf-8" /><meta name="viewport" content="width=device-width, initial-scale=1" /><title>当 AI 越会执行，艺术生的优势反而越明显</title></head><body style="margin:0;b
      quoted
    • low Secrets in code secret-aws-key frontend/tmp-spring-preview.html:1
      AWS access key ID (placeholder value)
      <!doctype html><html lang="zh-CN"><head><meta charset="utf-8" /><meta name="viewport" content="width=device-width, initial-scale=1" /><title>当 AI 越会执行，艺术生的优势反而越明显</title></head><body style="margin:0;b
      placeholder
    • low Obfuscation obf-base64-blob frontend/tmp-wechat-safe-check.html:1
      Long base64-looking blob (quoted — discussed, not commanded)
      <!doctype html><html lang="zh-CN"><head><meta charset="utf-8" /><meta name="viewport" content="width=device-width, initial-scale=1" /><title>当 AI 越会执行，艺术生的优势反而越明显</title></head><body style="margin:0;b
      quoted
    • low Secrets in code secret-aws-key frontend/tmp-wechat-safe-check.html:1
      AWS access key ID (placeholder value)
      <!doctype html><html lang="zh-CN"><head><meta charset="utf-8" /><meta name="viewport" content="width=device-width, initial-scale=1" /><title>当 AI 越会执行，艺术生的优势反而越明显</title></head><body style="margin:0;b
      placeholder

    Files scanned: 64. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    ✓ No remarks against the Agent Skills spec

    Process rating: all ten parameters 38/100

    • 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
    • 20When it triggers. No condition that starts the skill
    • 30Running it twice. 7 mutating operations with no state check
    • 40Consistency. Frontmatter name (wechat-studio) differs from the folder (content-system-wechat-studio)
    • 60Tools and files. Uses tools (python) that frontmatter does not declare
    • 85Steps. 20 steps, 1 vague phrases
    • 100Execution cost. Instruction body is 544 tokens
    • 100Progress reporting. Reports progress

    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
    • +1No license
    • +2Single-language instructions
    • +3Description length 221: enough signal without eating the budget
    • +4Structure: 6 headings
    • +3Step-by-step instructions: 20 items
    • +4Has examples (4 code blocks)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 82.

    External checks

    ClawHub: suspicious
    This appears to be a real WeChat article workbench, but it needs review because it can expose local workspace files and send draft/article data to external services with limited in-tool warnings.
    LLM: suspicious (high) · VirusTotal: · 29 May 2026