SKILLEMALL.ai
GitHub ↗ RU Sign in

BC skill-perf

测量 OpenClaw 环境中 Skill 的 token 消耗和性能开销（仅适用于 OpenClaw Agent 环境）。当用户提到「测量」「测试」「性能」「token 消耗」「多少 token」「开销」「成本」「效率」或想要评估、对比、优化某个 skill 的资源使用时，立即使用此 skill。也适用于 skill 发布前的性能验证、多轮测试对比、热/冷缓存分析、以及分析两个 skill 之间消耗差异。英文触发词：measure token cost, performance test, how many tokens, benchmark skill。即使用户没有明确说「skill-perf」，只要涉及 OpenClaw skill 性能分析就应触发。技术实现：通过 OpenClaw 的 sessions_spawn 启动双 subagent 并发测量，自动扣除系统底噪，生成 HTML 报告和置信度评级。

ClawHub Agent Skills author: kincaidwoo v1.0.2 MIT-0 11 files · 1 script body ≈ 896 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process C 53/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions

ProcedureInfrastructureAI 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
82/100
safety, quality, tests
Safety 60%
90
Quality 40%
71
Run on models
none yet
Process rating
C
53/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
Failures and branches w 10
0
the three weakest of ten parameters · all ten

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 · 10

✓ No critical or high findings

Medium and low: 10
  • low Obfuscation obf-base64-blob scripts/report_html.py:40
    Long base64-looking blob (quoted — discussed, not commanded)
    "iVBO…AAB"
    quoted
  • low Obfuscation obf-base64-blob scripts/report_html.py:41
    Long base64-looking blob (quoted — discussed, not commanded)
    "AAAA…dbv"
    quoted
  • low Obfuscation obf-base64-blob scripts/report_html.py:42
    Long base64-looking blob (quoted — discussed, not commanded)
    "6jQz…ZyH+nnGM…ur4/V9Vz+4CgyIb"
    quoted
  • low Secrets in code secret-high-entropy-token scripts/report_html.py:42
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "6jQz…ZyH+nnGM…ur4/V9Vz+4CgyIb"
    quoted
  • low Obfuscation obf-base64-blob scripts/report_html.py:43
    Long base64-looking blob (detector / deny-list definition)
    "Zvx+W6493dXVVa/+79Wr…S2g"
    detector
  • low Obfuscation obf-base64-blob scripts/report_html.py:44
    Long base64-looking blob (quoted — discussed, not commanded)
    "ngEJ…WNu/Vb"
    quoted
  • low Secrets in code secret-high-entropy-token scripts/report_html.py:45
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "KX+P5Ni…1zD+2TFE…ZEl"
    quoted
  • low Secrets in code secret-high-entropy-token scripts/report_html.py:46
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "WXYj…ahq+fvsj…7q7+y1i9…7qr+y3Hp…FCG"
    quoted
  • low Secrets in code secret-high-entropy-token scripts/report_html.py:50
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "bzPd…Sz1+jVFH+Nc0A…w2a"
    quoted
  • low Secrets in code secret-high-entropy-token scripts/report_html.py:55
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "0oxJ…uMF+5X7I…Jlc/6AXw…Wum"
    quoted

Files scanned: 11. 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 53/100

  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Failures and branches. Linear process with no failure handling
  • 0Progress reporting. Says nothing while it works
  • 20When it triggers. No condition that starts the skill
  • 100Tools and files. No external tools needed
  • 100Steps. 10 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 896 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)
  • +3Output format is not stated: the model decides each time
  • -2localhost URLs: will not work for another user
  • -33 of 5 scripts are never mentioned in SKILL.md
  • +1No license
  • +2Single-language instructions
  • +3Description length 411: enough signal without eating the budget
  • +4Structure: 8 headings
  • +3Step-by-step instructions: 10 items
  • +4Has examples (7 code blocks)
  • +4Reference files are cited in the instructions (1 of 3)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 71.

External checks

ClawHub: suspicious
This is a real benchmarking skill, but it reads detailed local agent session data and automatically serves generated reports in ways users should review before installing.
LLM: suspicious (high) · VirusTotal: · 29 May 2026