SKILLEMALL.ai
RU Sign in

BF mktclaw

营销虾 (MktClaw) — Demand-to-Delivery AI Agency. 直接扮演 10 种代理商角色交付品牌方案/Campaign/投放策略/直播脚本/危机应对。务必在用户提到品牌规划、Campaign、营销方案、投放策略、KOL、直播、危机公关、舆情应对等需求时触发，即使没明确说'agency'。

ClawHub Agent Skills author: qomob v1.0.1 MIT-0 65 files body ≈ 1 762 tokens Open the sourceclawhub.ai↗ analyzed 2 d ago

As a process F 35/100 · Will not run — References files that are not bundled: references/industries/{id}.md

ProcedureMarketingInfrastructuretype 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
77/100
safety, quality, tests
Safety 60%
83
Quality 40%
67
Run on models
none yet
Process rating
F
35/100
Will not run
References files that are not bundled: references/industries/{id}.md
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

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 text references files that are not there: add them or drop the references.
For the model run — optional
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 17

✓ No critical or high findings

Medium and low: 17
  • low Risky intent intent-offensive-security agents/types/brand-design/main-agent.md:359
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    ### 领域专属 Red Team 攻击（叠加在通用攻击之上）
  • low Risky intent intent-offensive-security agents/types/content-production/main-agent.md:158
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    ### 领域专属 Red Team 攻击（叠加在通用攻击之上）
  • low Risky intent intent-offensive-security agents/types/creative-agency/main-agent.md:465
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    ### 领域专属 Red Team 攻击（叠加在通用攻击之上）
  • low Risky intent intent-offensive-security agents/types/crisis-pr/main-agent.md:402
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    ### 领域专属 Red Team 攻击（叠加在通用攻击之上）
  • low Risky intent intent-offensive-security agents/types/data-analytics/main-agent.md:255
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    ### 领域专属 Red Team 攻击（叠加在通用攻击之上）
  • low Risky intent intent-offensive-security agents/types/kol-agency/main-agent.md:182
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    ### 领域专属 Red Team 攻击（叠加在通用攻击之上）
  • low Risky intent intent-offensive-security agents/types/live-streaming/main-agent.md:523
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    ### 领域专属 Red Team 攻击（叠加在通用攻击之上）
  • low Risky intent intent-offensive-security agents/types/mcn/main-agent.md:459
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    ### 领域专属 Red Team 攻击（叠加在通用攻击之上）
  • low Risky intent intent-offensive-security agents/types/media-agency/main-agent.md:179
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    ### 领域专属 Red Team 攻击（叠加在通用攻击之上）
  • low Risky intent intent-offensive-security agents/types/strategy-consulting/main-agent.md:408
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    当前模式: **红队 (Red Team)** — 主动攻击本方案的漏洞
  • low Risky intent intent-offensive-security agents/types/strategy-consulting/main-agent.md:471
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    ### 领域专属 Red Team 攻击（叠加在通用攻击之上）
  • low Risky intent intent-offensive-security README.md:86
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    | **Tournament + Adversarial** | Swiss-System 多方案 PK + Red Team 对抗式自检 + LLM-as-Judge 语义评分 |
  • low Risky intent intent-offensive-security README.md:266
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    - **Tournament + Adversarial**: Swiss-System pairwise PK + Red Team attack + LLM-as-Judge
  • low Risky intent intent-offensive-security references/_shared/quality-protocol.md:256
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    ### 🔴 Red Team 通用攻击（4 项必做）
  • low Risky intent intent-offensive-security references/_shared/quality-protocol.md:305
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    ## 领域专属 Red Team 攻击（叠加在 quality-protocol.md 通用攻击之上）
  • low Risky intent intent-offensive-security references/_shared/quality-protocol.md:356
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    ### 🔴 Red Team 结果
  • low Risky intent intent-offensive-security references/_shared/quality-protocol.md:390
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    - 领域专属攻击：见本文档 § 领域专属 Red Team 攻击

Files scanned: 63. 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 missing-ref reference to a missing file: references/industries/{id}.md

Process rating: all ten parameters 35/100

Will not run. References files that are not bundled: references/industries/{id}.md
  • 0Tools and files. 1 referenced file(s) missing: references/industries/{id}.md
  • 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
  • 100Steps. 19 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 1762 tokens
  • 100Running it twice. No mutating operations
  • low The response is described with custom markup (6 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
  • -31 of 1 scripts are never mentioned in SKILL.md
  • +1No license
  • +2Single-language instructions
  • +3Description length 160: enough signal without eating the budget
  • +4Structure: 25 headings
  • +3Step-by-step instructions: 19 items
  • +4Has examples (5 code blocks)
  • +4Reference files are cited in the instructions (14 of 15)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 67.

External checks

ClawHub: clean
This is a mostly read-only Chinese marketing planning skill; it has stale and overbroad documentation, but I found no artifact-backed exfiltration, destructive behavior, or hidden credential use.
LLM: benign (high) · VirusTotal: · 15 Jun 2026