SKILLEMALL.ai
RU Sign in

BC pitch-skill

必赢逻辑引擎（Pitch Skill）— 专为广告/营销Agency的比稿竞标场景设计的AI影子智囊团。把资深策略总监脑子里的「玄学感悟」拆解为可计算的赢标逻辑。当用户需要在竞争性提案中赢下客户（多个供应商竞标、客户发RFP选Agency、评审团打分选方案）时使用此技能。6个Agent协作：Intake → Information → Strategy → Decision → Expression → Delivery，覆盖Brief穿透与需求解构、决策者深度画像、竞标对手逻辑真空区推演、第一性原理策略推导、逻辑链自检、胜率计算、决策模拟、情绪引擎优化提案表达、AIGC具象化震撼Demo、Q&A压力训练。触发场景：比稿、竞标、pitch、提案竞标、agency pitch、RFP响应、招标方案、赢标策略、竞标方案、pitch deck准备、选代理商、换代理商、年度比稿、创意比稿、媒介比稿。也适用于客户要求正式presentation给管理层评审的场景。即使用户只说'帮我做个提案''有个比稿''要去pitch''客户要方案''准备比稿材料''要去竞标''帮我们赢下这个客户''怎么才能赢'等模糊表述，只要涉及向客户竞争性展示方案就应触发。不适用于：内部营销方案、融资路演、PPT美化、竞品调研、品牌定位、培训汇报等非竞争性场景。

ClawHub Agent Skills author: qomob v2.2.0 MIT-0 18 files body ≈ 721 tokens Open the sourceclawhub.ai↗ analyzed 2 d ago

As a process C 54/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions

ProcedureProcurementInfrastructuretype 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
86/100
safety, quality, tests
Safety 60%
93
Quality 40%
76
Run on models
none yet
Process rating
C
54/100
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
This is a copy of a skill from another catalog; the rating counts the canonical one: pitch-skill (ClawHub)

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
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 7

✓ No critical or high findings

Medium and low: 7
  • low Risky intent intent-offensive-security agents/__init__.md:68
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    + Q&A Red Team
  • low Risky intent intent-offensive-security agents/expression-agent.md:12
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    **语言规则：** 输出语言必须与提案的最终受众语言一致。如果评审团使用英文，即使分析过程是中文，Pitch Structure、Opening Hooks、Emotion Engine、AIGC Demo、Q&A Red Team 必须英文输出。英文模板见 references/bilingual-templates.md。
  • low Risky intent intent-offensive-security agents/expression-agent.md:80
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    ### Phase 5: Q&A压力训练（Red Team）
  • low Risky intent intent-offensive-security agents/expression-agent.md:150
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    **5. Q&A Red Team**
  • low Risky intent intent-offensive-security references/bilingual-templates.md:33
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    | Q&A压力训练 | Q&A Red Team | Hostile question preparation |
  • low Risky intent intent-offensive-security references/bilingual-templates.md:171
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    ### Q&A Red Team (Expression Agent)
  • low Risky intent intent-offensive-security references/bilingual-templates.md:174
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    Q&A Red Team — {decision_mode} Mode Optimized

Files scanned: 16. 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 54/100

  • 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
  • 40Consistency. Frontmatter name (pitch-skill) differs from the folder (pitchskill)
  • 50Failures and branches. 0 branches, has a failure section
  • 100Tools and files. No external tools needed
  • 100Steps. 16 steps
  • 100Execution cost. Instruction body is 721 tokens
  • 100Running it twice. No mutating operations
  • medium 10 test cases, all positive: not one "should refuse" or "should ask first"
  • low No test case covers injection arriving through data

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
  • +1No license
  • +2Single-language instructions
  • +3Description length 571: enough signal without eating the budget
  • +4Structure: 10 headings
  • +3Step-by-step instructions: 16 items
  • +4Has examples (3 code blocks)
  • +4Reference files are cited in the instructions (4 of 4)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 76.

External checks

ClawHub: suspicious
This is a coherent pitch-preparation skill, but it needs review because it encourages under-scoped stakeholder and insider-information use and may trigger on vague pitch-related phrases.
LLM: suspicious (high) · VirusTotal: · 15 Jun 2026