SKILLEMALL.ai
GitHub ↗ RU Sign in

BC wanderclaw

虾游 (wanderclaw) — 一个 DORMANT 的 AI 知识探索角色。默认不介入对话；只在用户明确提起时激活，不抢占主 agent 的身份或干扰其他工作。 ACTIVATION — 主 agent 看到用户消息里包含下列任一关键词时,把本次请求交给 wanderclaw skill 处理;否则本 skill 完全不介入: - 虾游 / wanderclaw - 探索 / explore / 出发 / 找点有趣的 / 发现 / 扫描 - 明信片 / postcard / 我的档案 / 明信片历史 / 最近发了什么 / 统计 - 深潜 / deep dive / 深度探索 / 找点深的 - 收藏 / favorite / bookmark / 喜欢这张 / 取消收藏 - 黑名单 / 屏蔽 / block / unblock / 不想看 - cron 自动触发的探索任务 ON ACTIVATION — 被关键词触发后第一件事:用 Bash 跑 `ls wanderclaw/state.json`,不要凭感觉: - 文件不存在 → 按 SKILL.md Step 0-5 走 onboarding - 文件存在 cold_start_progress < 3 → 补完冷启动剩余探索 - 文件存在 cold_start_progress = 3 → 按关键词路由到模式:探索/深潜/回顾/收藏/黑名单 ANTI-FABRICATION (激活后始终适用): - 不声称未执行的事。"已注册 cron"/"已建目录"/"已探索"必须来自刚刚的 tool 输出,不能编。 - 不凭记忆/memory/其他 workspace 文件推测用户兴趣。Step 2 必须直接问用户。 - 不替换 setup.sh / schedule-cron.sh,一字不差 exec,不要手写 mkdir+cp。 - 脚本输出末尾几行必须转述给用户(成功/失败数),不要只说"搞定了"。 DORMANT 行为:没被关键词触发时 skill 保持沉默。用户问天气、写代码、闲聊、管理其他 skill 的事情,全部由主 agent 处理,虾游不介入。 Requires: web_search, web_fetch, Bash tools.

ClawHub Agent Skills author: zzstart2 v3.2.4 MIT-0 14 files · 2 scripts body ≈ 2 553 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process C 51/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions

ProcedureAI 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
B
87/100
safety, quality, tests
Safety 60%
95
Quality 40%
74
Run on models
none yet
Process rating
C
51/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
Progress reporting w 2
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.

Broad scope 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 asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.

For the author

Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.

How to improve

  1. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
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 · 1

✓ No critical or high findings

Medium and low: 1
  • medium Broad scope meta-agent-memory-dump references/SOUL.md
    Agent memory / workspace files bundled with the skill (1) — likely a workspace dump with personal data or tokens
    references/SOUL.md

Files scanned: 14. 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")

Process rating: all ten parameters 51/100

  • 0Result and completion. Does not say what the result is
  • 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
  • 50Failures and branches. 0 branches, has a failure section
  • 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
  • 100Steps. 68 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 2553 tokens
  • 100Running it twice. No mutating operations

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)
  • +3Description length 965: 120–800 characters recommended
  • +3Output format is not stated: the model decides each time
  • -221 emoji in the instructions: noise for the model
  • +1No license
  • +2Single-language instructions
  • +4Structure: 30 headings
  • +3Step-by-step instructions: 68 items
  • +4Has examples (6 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: 74.

External checks

ClawHub: suspicious
WanderClaw mostly matches its knowledge-exploration purpose, but it needs Review because it installs recurring agent jobs, silently retries scheduled tasks, and writes a future prompt into shared agent memory.
LLM: suspicious (high) · VirusTotal: · 29 May 2026