SKILLEMALL.ai
GitHub ↗ RU Sign in

CF zeelin-writing

自媒体写作助手，提供完整的10步创作流程：需求分析→知识搜索→选题讨论→风格学习→创作初稿→三遍审校(降AI味)→封面配图→HTML排版→发布草稿箱→归档。当用户说"写一篇文章"、"帮我创作"、"改一下这篇文章"、"审校"、"降AI味"、"降重"、"选题讨论"、"我想写"时触发。支持公众号、小红书、视频逐字稿多平台，自动生成封面图并发布到公众号草稿箱。支持微信公众号顶级排版规范和小红书一键自动发布。

ClawHub Agent Skills author: kelcey2023 v0.1.0 MIT-0 11 files · 3 scripts body ≈ 1 376 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process F 28/100 · Will not run — References files that are not bundled: references/style.md, references/wechat-style.md

GeneratorInfrastructuretype 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
C
70/100
safety, quality, tests
Safety 60%
75
Quality 40%
62
Run on models
none yet
Process rating
F
28/100
Will not run
References files that are not bundled: references/style.md, references/wechat-style.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

What is at stake

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

Dangerous commands 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 skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.

For the author

Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.

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 · 5

✓ No critical or high findings

Medium and low: 5
  • medium Dangerous commands cmd-shell-rc scripts/初始化.sh:107
    Writes to a shell startup file
    echo "export GOOGLE_API_KEY=\"$API_KEY\"" >> "$HOME/.zshrc"
  • medium Dangerous commands cmd-shell-rc scripts/初始化.sh:108
    Writes to a shell startup file
    echo -e "${GREEN}✅ 已添加到 ~/.zshrc${NC}"
  • medium Dangerous commands cmd-shell-rc scripts/初始化.sh:109
    Writes to a shell startup file
    echo "   请运行: source ~/.zshrc"
  • medium Dangerous commands cmd-shell-rc scripts/初始化.sh:111
    Writes to a shell startup file
    echo "export GOOGLE_API_KEY=\"$API_KEY\"" >> "$HOME/.bashrc"
  • medium Dangerous commands cmd-shell-rc scripts/初始化.sh:112
    Writes to a shell startup file
    echo -e "${GREEN}✅ 已添加到 ~/.bashrc${NC}"

Files scanned: 11. 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: references/style.md
  • warning missing-ref reference to a missing file: references/wechat-style.md

Process rating: all ten parameters 28/100

Will not run. References files that are not bundled: references/style.md, references/wechat-style.md
  • 0Tools and files. 2 referenced file(s) missing: references/style.md, references/wechat-style.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. 1 mutating operations with no state check
  • 40Consistency. Frontmatter name (zeelin-writing) differs from the folder (zeelin-writing-v2)
  • 100Steps. 48 steps
  • 100Execution cost. Instruction body is 1376 tokens

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
  • -215 emoji in the instructions: noise for the model
  • -33 of 4 scripts are never mentioned in SKILL.md
  • +1No license
  • +2Single-language instructions
  • +3Description length 201: enough signal without eating the budget
  • +4Structure: 23 headings
  • +3Step-by-step instructions: 48 items
  • +4Has examples (10 code blocks)
  • +4Reference files are cited in the instructions (1 of 3)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 62.

External checks

ClawHub: suspicious
This writing assistant is mostly relevant to its purpose, but it can read local content, store credentials, install packages, and prepare publishing actions with too little user control.
LLM: suspicious (high) · VirusTotal: · 29 May 2026