基于 SOC 职业分类
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt;运行前请先检查来源。
npx skills add https://github.com/majiayu000/claude-skill-registry --skill faion-gtm-manifest命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地?可下载 SkillsMP 当前能够提供的文件。
正在显示 SKILL.md
LLM token logprobs and calibration. Per-decision confidence, ECE, Brier, reliability diagrams, low-confidence triage.
Analyze LLM token logprobs and calibration. Use for per-decision confidence, ECE, Brier scores, reliability diagrams, and low-confidence triage.
回顾最近 N 天的 Claude Code 使用记录——扫描原始会话数据,按主题分组汇总"我都做了什么",并从个人操作系统视角输出模式、风险与增删建议。当用户说 /recap、"看看我这几天做了什么"、"回顾一下我最近的会话"、"这两天我用 claude 干了啥"、"活动回顾" 时使用。
| name | faion-gtm-manifest |
| description | GTM Manifest from research data. Triggers: gtm, go-to-market, launch strategy. |
| user-invocable | false |
| allowed-tools | Read, Write, Glob, Task, AskUserQuestion, TodoWrite |
Communication: User's language. Docs: English.
Requires completed research in product_docs/:
If missing → run faion-product-research first.
1. Read product research docs
2. AskUserQuestion: sales model, timeline
3. Generate 12 sections sequentially
4. Combine into gtm-manifest-full.md
product_docs/gtm-manifest/
├── 01-executive-summary.md
├── 02-market-context.md
├── 03-icp.md
├── 04-value-proposition.md
├── 05-positioning.md
├── 06-messaging-framework.md
├── 07-pricing-packaging.md
├── 08-sales-model.md
├── 09-marketing-channels.md
├── 10-launch-plan.md
├── 11-success-metrics.md
├── 12-risks-mitigations.md
└── gtm-manifest-full.md
| # | Section | Key Content |
|---|---|---|
| 01 | Executive Summary | Vision, market opportunity, strategy |
| 02 | Market Context | TAM/SAM/SOM, trends from research |
| 03 | ICP | Ideal Customer Profile from personas |
| 04 | Value Proposition | Core benefits, differentiation |
| 05 | Positioning | vs competitors, unique angle |
| 06 | Messaging | Headlines, taglines, key messages |
| 07 | Pricing | Tiers, packaging from research |
| 08 | Sales Model | PLG/Sales-led/Hybrid |
| 09 | Channels | Marketing channels, priorities |
| 10 | Launch Plan | Timeline, milestones |
| 11 | Metrics | KPIs, success criteria |
| 12 | Risks | Risks and mitigations |
AskUserQuestion(
questions=[
{
"question": "Sales model?",
"options": [
{"label": "PLG", "description": "Product-Led Growth"},
{"label": "Sales-Led", "description": "Enterprise sales"},
{"label": "Hybrid", "description": "PLG + Sales"}
]
},
{
"question": "Launch timeline?",
"options": [
{"label": "MVP", "description": "3-6 months"},
{"label": "Full", "description": "6-12 months"}
]
}
]
)
For each section, use Task with general-purpose agent:
for section in SECTIONS:
Task(
subagent_type="general-purpose",
prompt=f"""
PROJECT: {project}
SECTION: {section.name}
RESEARCH: {research_data}
OUTPUT: product_docs/gtm-manifest/{section.file}
Write {section.name} section using research data.
Follow standard GTM format.
"""
)
# Combine all sections
sections = sorted(glob("product_docs/gtm-manifest/*.md"))
full_content = "\n\n---\n\n".join([read(s) for s in sections])
write("product_docs/gtm-manifest/gtm-manifest-full.md", full_content)