SKILLEMALL.ai
GitHub ↗ RU Sign in

BC content-engine-en

Content Engine (Xiaohongshu). Two modes: ① Deconstruct (v1) — input a viral XHS link, get an 18-field structured card. ② Generate (v2) — combine the deconstruction with your brand info and use Ofox (LLM + Nano Banana) to produce your own version: script / caption / cover / desc / tags / reference frames. v0.3.0: real video generation via Volcengine Ark Seedance 2.0 (multi-shot + ffmpeg auto-concat). Maintains a shared graph/ knowledge graph across modes so the system gets smarter over time. Architecture inspired by Ronin's Skill Graph. Chinese version: ~/.agents/skills/content-engine/

ClawHub Agent Skills author: dizhu v0.3.1 MIT-0 53 files body ≈ 7 906 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process C 63/100 · Has gaps — weak spots: when it triggers, consistency, running it twice

GeneratorAI and agentsMarketingMedia 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
87/100
safety, quality, tests
Safety 60%
94
Quality 40%
77
Run on models
none yet
Process rating
C
63/100
Has gaps
When it triggers w 12
20
Running it twice w 4
30
Consistency w 8
40
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.

Exfiltration 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 instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".

For the author

If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.

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 · 2

✓ No critical or high findings

Medium and low: 2
  • medium Exfiltration net-redirectable-api-key scripts/content_engine/client.py:95
    Helper sends the API key to a host configured by an environment variable — the key can be redirected to another server
    API key + configurable base URL from environment
  • low Secrets in code secret-high-entropy-token SKILL.md:318
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    Final naming: `{id}-{slug}` (e.g., `AIC-…ive`).
    quoted

Files scanned: 43. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 7906 tokens (recommended < 5000); move details to references/

Process rating: all ten parameters 63/100

  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 19 mutating operations with no state check
  • 40Consistency. Frontmatter name (content-engine-en) differs from the folder (qianxun-content-engine-en)
  • 60Tools and files. Uses tools (bash, web, python) that frontmatter does not declare
  • 60Result and completion. Output format stated, no completion criterion
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 70Execution cost. Instruction body is 7906 tokens
  • 85Steps. 112 steps, 1 vague phrases
  • 100Failures and branches. 3 branches, has a failure section
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 17 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)
  • -5TODO / placeholder text left in the skill
  • -228 emoji in the instructions: noise for the model
  • +1No license
  • +2Single-language instructions
  • +3Description length 591: enough signal without eating the budget
  • +4Structure: 52 headings
  • +3Step-by-step instructions: 112 items
  • +3Output format is stated explicitly
  • +4Has examples (16 code blocks)
  • +4Reference files are cited in the instructions (3 of 3)
  • +3All 2 scripts are documented

Quality base 70; lint remarks subtract, signals add up to 100. Result: 77.

External checks

ClawHub: clean
This skill is a disclosed content generation workflow that uses third-party APIs and local output files in ways that match its stated purpose.
LLM: benign (high) · VirusTotal: · 29 May 2026