SKILLEMALL.ai
GitHub ↗ RU Sign in

CF rdk-yolo-toolkit

端到端 YOLO 训练 → 地瓜 RDK X5 BPU 量化部署：Monkey Patch ONNX 导出 → hb_mapper 量化 → 板端 hbm_runtime 推理 → TROS HobotDnn ROS2 实时检测。支持 YOLOv5u~YOLOv13 和 YOLO26 全系列。内含工艺原理速查（why this ONNX, why this yaml）。

ClawHub Agent Skills author: Chao.Ma v1.0.0 MIT-0 7 files · 2 scripts body ≈ 9 204 tokens Open the sourceclawhub.ai↗ analyzed 2 d ago

端到端 YOLO 训练 → 地瓜 RDK X5 BPU 量化部署：Monkey Patch ONNX 导出 → hbmapper 量化 → 板端 hbmruntime 推理 → TROS HobotDnn ROS2 实时检测。支持 YOLOv5u~YOLOv13 和 YOLO26 全系列。内含工艺原理速查（why…

As a process F 36/100 · Will not run — References files that are not bundled: x[i]

ProcedureSoftware developmentAI 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
C
73/100
safety, quality, tests
Safety 60%
94
Quality 40%
42
Run on models
none yet
Process rating
F
36/100
Will not run
References files that are not bundled: x[i]
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 SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
  3. 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 · 2

✓ No critical or high findings

Medium and low: 2
  • medium Dangerous commands cmd-shell-rc scripts/install_train_env.sh:52
    Writes to a shell startup file
    echo 'export PATH=/usr/lib/wsl/lib:$PATH' >> ~/.bashrc
  • low Dangerous commands cmd-privilege SKILL.md:828
    Privilege escalation / world-writable permissions (quoted — discussed, not commanded)
    ⚠️ **`/dev/hbmem*` 设备权限**：默认 root 才能写 hbmem。非 root 用户需 `sudo chmod 666 /dev/hbmem*` 或加入对应 group。
    quoted

Files scanned: 7. 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 body-long SKILL.md body ≈ 9204 tokens (recommended < 5000); move details to references/
  • warning missing-ref reference to a missing file: x[i]

Process rating: all ten parameters 36/100

Will not run. References files that are not bundled: x[i]
  • 0Tools and files. 1 referenced file(s) missing: x[i]
  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 7 mutating operations with no state check
  • 40Execution cost. Instruction body is 9204 tokens: crowds the task out of the window
  • 50Failures and branches. 0 branches, has a failure section
  • 100Steps. 89 steps
  • 100Consistency. Name and required fields are in place
  • 100Progress reporting. Reports progress
  • low 11 top-level sections: this looks like several domains in one skill
  • low The response is described with custom markup (4 tags): a typed call is more reliable

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
  • -5TODO / placeholder text left in the skill
  • -4Absolute local paths (C:\Users, /home/…): not portable
  • -246 emoji in the instructions: noise for the model
  • -32 of 2 scripts are never mentioned in SKILL.md
  • +1No license
  • +2Single-language instructions
  • +3Description length 186: enough signal without eating the budget
  • +4Structure: 41 headings
  • +3Step-by-step instructions: 89 items
  • +4Has examples (32 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 42.

External checks

ClawHub: suspicious
This skill is a coherent RDK X5 YOLO deployment helper, but it gives agents broad local and remote command authority with persistent background execution and unsafe permission examples that users should review before installing.
LLM: suspicious (high) · 8 Sept 2026