SKILLEMALL.ai
GitHub ↗ RU Sign in

BC datawhale-learning

Navigate the Chinese Datawhale Easy Vibe and Hello Agents tutorials and apply an AI-native software delivery lifecycle. Use to find original lessons, diagnose learning gaps, build project-based study plans, or design intent-to-production workflows with versioned artifacts, continuous evaluation, review gates, deployment controls, and incident feedback loops.

ClawHub Agent Skills author: Blink Hsu v1.1.0 MIT-0 9 files body ≈ 845 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

Navigate the Chinese Datawhale Easy Vibe and Hello Agents tutorials and apply an AI-native software delivery lifecycle.

As a process C 54/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions

ProcedureLearningInfrastructuretype 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%
75
Quality 40%
87
Run on models
none yet
Process rating
C
54/100
Has gaps
Inputs and preconditions w 11
0
Progress reporting w 2
0
When it triggers w 12
20
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 · 5

    ✓ No critical or high findings

    Medium and low: 5
    • medium Obfuscation obf-hex-escape-chain references/source-catalog.md:237
      Escaped/char-code string obfuscation
      - [第一章 初识智能体](https://github.com/datawhalechina/hello-agents/blob/45dd…c6e/docs/chapter1/%E7%AC%AC%E4%B8%80%E7%AB%A0%20%E5%88%9D%E8%AF%86%E6%99%BA%E8%83%BD%E4%BD%93.md)
    • medium Obfuscation obf-hex-escape-chain references/source-catalog.md:238
      Escaped/char-code string obfuscation
      - [第十章 智能体通信协议](https://github.com/datawhalechina/hello-agents/blob/45dd…c6e/docs/chapter10/%E7%AC%AC%E5%8D%81%E7%AB%A0%20%E6%99%BA%E8%83%BD%E4%BD%93%E9%80%9A%E4%BF%A1%
    • medium Obfuscation obf-hex-escape-chain references/source-catalog.md:240
      Escaped/char-code string obfuscation
      - [第十二章 智能体性能评估](https://github.com/datawhalechina/hello-agents/blob/45dd…c6e/docs/chapter12/%E7%AC%AC%E5%8D%81%E4%BA%8C%E7%AB%A0%20%E6%99%BA%E8%83%BD%E4%BD%93%E6%80%A7
    • medium Obfuscation obf-hex-escape-chain references/source-catalog.md:241
      Escaped/char-code string obfuscation
      - [第十三章 智能旅行助手](https://github.com/datawhalechina/hello-agents/blob/45dd…c6e/docs/chapter13/%E7%AC%AC%E5%8D%81%E4%B8%89%E7%AB%A0%20%E6%99%BA%E8%83%BD%E6%97%85%E8%A1%8C%
    • medium Obfuscation obf-hex-escape-chain references/source-catalog.md:242
      Escaped/char-code string obfuscation
      - [第十四章 自动化深度研究智能体](https://github.com/datawhalechina/hello-agents/blob/45dd…c6e/docs/chapter14/%E7%AC%AC%E5%8D%81%E5%9B%9B%E7%AB%A0%20%E8%87%AA%E5%8A%A8%E5%8C%96%E6%B7

    Files scanned: 9. 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 54/100

    • 0Inputs and preconditions. Does not say what the process needs to start
    • 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
    • 40Result and completion. Does not say what the result is
    • 50Failures and branches. 0 branches, has a failure section
    • 60Tools and files. Uses tools (python) that frontmatter does not declare
    • 100Steps. 16 steps
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 845 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
    • +4No input/output examples
    • +1No license
    • +2Single-language instructions
    • +3Description length 360: enough signal without eating the budget
    • +4Structure: 5 headings
    • +3Step-by-step instructions: 16 items
    • +4Reference files are cited in the instructions (5 of 5)
    • +3All 1 scripts are documented

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 87.

    External checks

    ClawHub: clean
    This skill is a disclosed learning navigator that searches a bundled source catalog and links users to original tutorial materials.
    LLM: benign (high) · VirusTotal: · 26 Aug 2026