SKILLEMALL.ai
GitHub ↗ RU Sign in

BF claw-go

Play Claw Go (虾游记), a crayfish travel companion + Buddy-style electronic pet game with deterministic hatching, rarity/species/hat stats, proactive travel stories, image plus voice diary updates, relationship progression, petting, direct-name companion replies, and memory-based destination personalization. ALWAYS trigger this skill when the user says or implies any of: "clawgo", "claw go", "虾游记", "虾游记 去旅行", "虾游记 状态", "虾游记 发消息", "虾游记 孵化搭子", "虾游记 搭子状态", "虾游记 摸摸搭子", "开始玩虾游记", "继续旅行", "buddy", "buddy status", "buddy pet", or any message asking to start, continue, check status, hatch the companion, pet the companion, receive an update, or chat with the travel pet. Prefer plain-text triggering over slash commands because some channels restrict "/".

ClawHub Agent Skills author: airbai v0.6.2 MIT-0 28 files · 2 scripts body ≈ 5 238 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process F 61/100 · Will not run — References files that are not bundled: assets/icon.svg, assets/emojis/

ProcedureInfrastructuretype 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
83/100
safety, quality, tests
Safety 60%
90
Quality 40%
72
Run on models
none yet
Process rating
F
61/100
Will not run
References files that are not bundled: assets/icon.svg, assets/emojis/
Tools and files w 18
0
Inputs and preconditions w 11
30
Running it twice w 4
30
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.
  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 · 2

✓ No critical or high findings

Medium and low: 2
  • medium Exfiltration net-redirectable-api-key scripts/generate_media_bundle.js:199
    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
  • medium Exfiltration net-redirectable-api-key scripts/transcribe_audio.js:73
    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

Files scanned: 28. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 5238 tokens (recommended < 5000); move details to references/
  • warning missing-ref reference to a missing file: assets/icon.svg
  • warning missing-ref reference to a missing file: assets/emojis/

Process rating: all ten parameters 61/100

Will not run. References files that are not bundled: assets/icon.svg, assets/emojis/
  • 0Tools and files. 2 referenced file(s) missing: assets/icon.svg, assets/emojis/
  • 30Inputs and preconditions. Does not say what the process needs to start
  • 30Running it twice. 15 mutating operations with no state check
  • 60Result and completion. Output format stated, no completion criterion
  • 70When it triggers. States when to use, but not when not to
  • 70Execution cost. Instruction body is 5238 tokens
  • 100Steps. 299 steps
  • 100Failures and branches. 18 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 14 top-level sections: this looks like several domains in one skill
  • low The response is described with custom markup (13 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

  • +4Description does not say when NOT to use the skill (false activations)
  • -226 emoji in the instructions: noise for the model
  • -38 of 12 scripts are never mentioned in SKILL.md
  • +1No license
  • +2Single-language instructions
  • +5Description quotes 11 example trigger phrases
  • +3Description length 751: enough signal without eating the budget
  • +4Structure: 22 headings
  • +3Step-by-step instructions: 299 items
  • +3Output format is stated explicitly
  • +4Has examples (3 code blocks)
  • +4Reference files are cited in the instructions (3 of 9)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 72.

External checks

ClawHub: suspicious
Claw Go is a real pet/travel game, but it needs Review because it ships real-looking service secrets and can run local scripts that send user-linked voice, media, location, and posts to external services with weak consent boundaries.
LLM: suspicious (high) · VirusTotal: · 29 May 2026