skill-market — community skill-market, community, ide skills, Claude Code, Cursor, Windsurf

v1.0.0

关于此技能

适合需要通过与市场代理集成进行高级市场规模研究能力的AI代理,如Claude Code、AutoGPT和LangChain Market sizing research with TAM/SAM/SOM framework

benbrastmckie benbrastmckie
[435]
[465]
更新于: 3/18/2026

Killer-Skills Review

Decision support comes first. Repository text comes second.

Reference-Only Page Review Score: 9/11

This page remains useful for operators, but Killer-Skills treats it as reference material instead of a primary organic landing page.

Original recommendation layer Concrete use-case guidance Explicit limitations and caution Quality floor passed for review
Review Score
9/11
Quality Score
70
Canonical Locale
en
Detected Body Locale
en

适合需要通过与市场代理集成进行高级市场规模研究能力的AI代理,如Claude Code、AutoGPT和LangChain Market sizing research with TAM/SAM/SOM framework

核心价值

赋予代理高效路由市场规模研究请求的能力,利用技能内部的后飞行模式实现无缝的状态更新、工件链接和git提交,同时利用markdown等协议和文件格式进行子代理返回验证

适用 Agent 类型

适合需要通过与市场代理集成进行高级市场规模研究能力的AI代理,如Claude Code、AutoGPT和LangChain

赋予的主要能力 · skill-market

通过市场代理自动执行市场规模研究请求
使用集成的AI工具,如Avante和Lectic,生成详细的市场分析报告
使用综合内容分析调试市场研究工作流程

! 使用限制与门槛

  • 需要与市场代理集成
  • 实现技能内部的后飞行模式,可能需要额外的设置
  • 仅在子代理执行期间加载上下文指针,如subagent-return.md

Why this page is reference-only

  • - Current locale does not satisfy the locale-governance contract.

Source Boundary

The section below is supporting source material from the upstream repository. Use the Killer-Skills review above as the primary decision layer.

实验室 Demo

Browser Sandbox Environment

⚡️ Ready to unleash?

Experience this Agent in a zero-setup browser environment powered by WebContainers. No installation required.

Boot Container Sandbox

常见问题与安装步骤

以下问题与步骤与页面结构化数据保持一致,便于搜索引擎理解页面内容。

? FAQ

skill-market 是什么?

适合需要通过与市场代理集成进行高级市场规模研究能力的AI代理,如Claude Code、AutoGPT和LangChain Market sizing research with TAM/SAM/SOM framework

如何安装 skill-market?

运行命令:npx killer-skills add benbrastmckie/nvim。支持 Cursor、Windsurf、VS Code、Claude Code 等 19+ IDE/Agent。

skill-market 适用于哪些场景?

典型场景包括:通过市场代理自动执行市场规模研究请求、使用集成的AI工具,如Avante和Lectic,生成详细的市场分析报告、使用综合内容分析调试市场研究工作流程。

skill-market 支持哪些 IDE 或 Agent?

该技能兼容 Cursor, Windsurf, VS Code, Trae, Claude Code, OpenClaw, Aider, Codex, OpenCode, Goose, Cline, Roo Code, Kiro, Augment Code, Continue, GitHub Copilot, Sourcegraph Cody, and Amazon Q Developer。可使用 Killer-Skills CLI 一条命令通用安装。

skill-market 有哪些限制?

需要与市场代理集成;实现技能内部的后飞行模式,可能需要额外的设置;仅在子代理执行期间加载上下文指针,如subagent-return.md。

安装步骤

  1. 1. 打开终端

    在你的项目目录中打开终端或命令行。

  2. 2. 执行安装命令

    运行:npx killer-skills add benbrastmckie/nvim。CLI 会自动识别 IDE 或 AI Agent 并完成配置。

  3. 3. 开始使用技能

    skill-market 已启用,可立即在当前项目中调用。

! 参考页模式

此页面仍可作为安装与查阅参考,但 Killer-Skills 不再把它视为主要可索引落地页。请优先阅读上方评审结论,再决定是否继续查看上游仓库说明。

Imported Repository Instructions

The section below is supporting source material from the upstream repository. Use the Killer-Skills review above as the primary decision layer.

Supporting Evidence

skill-market

安装 skill-market,这是一款面向AI agent workflows and automation的 AI Agent Skill。支持 Claude Code、Cursor、Windsurf,一键安装。

SKILL.md
Readonly
Imported Repository Instructions
The section below is supporting source material from the upstream repository. Use the Killer-Skills review above as the primary decision layer.
Supporting Evidence

Market Skill

Thin wrapper that routes market sizing research requests to the market-agent.

IMPORTANT: This skill implements the skill-internal postflight pattern. After the subagent returns, this skill handles all postflight operations (status update, artifact linking, git commit) before returning.

Context Pointers

Reference (do not load eagerly):

  • Path: .claude/context/core/formats/subagent-return.md
  • Purpose: Return validation
  • Load at: Subagent execution only

Note: This skill is a thin wrapper. Context is loaded by the delegated agent, not this skill.

Trigger Conditions

This skill activates when:

Direct Invocation

  • User explicitly runs /market command
  • User requests market sizing in conversation

Implicit Invocation (during task implementation)

When an implementing agent encounters any of these patterns:

Plan step language patterns:

  • "Analyze market size"
  • "Calculate TAM/SAM/SOM"
  • "Market sizing analysis"
  • "Estimate addressable market"

Target mentions:

  • "TAM", "SAM", "SOM"
  • "total addressable market"
  • "market opportunity"
  • "market sizing"

When NOT to trigger

Do not invoke for:

  • Competitive analysis (use skill-analyze)
  • GTM strategy (use skill-strategy)
  • General business research (use skill-researcher)
  • Revenue projections (not market sizing)

Execution Flow

Stage 1: Input Validation

Validate required inputs:

  • task_number - Must be provided and exist in state.json
  • industry - Optional, string
  • segment - Optional, string
  • mode - Optional, one of: VALIDATE, SIZE, SEGMENT, DEFEND
bash
1# Lookup task 2task_data=$(jq -r --argjson num "$task_number" \ 3 '.active_projects[] | select(.project_number == $num)' \ 4 specs/state.json) 5 6# Validate exists 7if [ -z "$task_data" ]; then 8 return error "Task $task_number not found" 9fi 10 11# Extract fields 12language=$(echo "$task_data" | jq -r '.language // "founder"') 13status=$(echo "$task_data" | jq -r '.status') 14project_name=$(echo "$task_data" | jq -r '.project_name') 15description=$(echo "$task_data" | jq -r '.description // ""') 16 17# Validate mode if provided 18if [ -n "$mode" ]; then 19 case "$mode" in 20 VALIDATE|SIZE|SEGMENT|DEFEND) ;; 21 *) return error "Invalid mode: $mode. Must be VALIDATE, SIZE, SEGMENT, or DEFEND" ;; 22 esac 23fi

Stage 2: Preflight Status Update

Update task status to "researching" BEFORE invoking subagent.

Update state.json:

bash
1jq --arg ts "$(date -u +%Y-%m-%dT%H:%M:%SZ)" \ 2 --arg status "researching" \ 3 --arg sid "$session_id" \ 4 '(.active_projects[] | select(.project_number == '$task_number')) |= . + { 5 status: $status, 6 last_updated: $ts, 7 session_id: $sid 8 }' specs/state.json > specs/tmp/state.json && mv specs/tmp/state.json specs/state.json

Update TODO.md: Use Edit tool to change status marker to [RESEARCHING].


Stage 3: Create Postflight Marker

bash
1padded_num=$(printf "%03d" "$task_number") 2mkdir -p "specs/${padded_num}_${project_name}" 3 4cat > "specs/${padded_num}_${project_name}/.postflight-pending" << EOF 5{ 6 "session_id": "${session_id}", 7 "skill": "skill-market", 8 "task_number": ${task_number}, 9 "operation": "research", 10 "reason": "Postflight pending: status update, artifact linking, git commit", 11 "created": "$(date -u +%Y-%m-%dT%H:%M:%SZ)" 12} 13EOF

Stage 4: Prepare Delegation Context

json
1{ 2 "task_context": { 3 "task_number": N, 4 "project_name": "{project_name}", 5 "description": "{description}", 6 "language": "founder" 7 }, 8 "industry": "optional industry hint", 9 "segment": "optional segment hint", 10 "mode": "VALIDATE|SIZE|SEGMENT|DEFEND or null", 11 "metadata_file_path": "specs/{NNN}_{SLUG}/.return-meta.json", 12 "metadata": { 13 "session_id": "sess_{timestamp}_{random}", 14 "delegation_depth": 1, 15 "delegation_path": ["orchestrator", "market", "skill-market"] 16 } 17}

Stage 5: Invoke Agent

CRITICAL: You MUST use the Task tool to spawn the agent.

Required Tool Invocation:

Tool: Task (NOT Skill)
Parameters:
  - subagent_type: "market-agent"
  - prompt: [Include task_context, industry, segment, mode, metadata_file_path, metadata]
  - description: "Market sizing research with TAM/SAM/SOM"

The agent will:

  • Present mode selection if not pre-selected
  • Use forcing questions to gather market data
  • Create research report at specs/{NNN}_{SLUG}/reports/
  • Write metadata file
  • Return brief text summary

Stage 6: Parse Subagent Return

bash
1padded_num=$(printf "%03d" "$task_number") 2metadata_file="specs/${padded_num}_${project_name}/.return-meta.json" 3 4if [ -f "$metadata_file" ] && jq empty "$metadata_file" 2>/dev/null; then 5 status=$(jq -r '.status' "$metadata_file") 6 artifact_path=$(jq -r '.artifacts[0].path // ""' "$metadata_file") 7 artifact_type=$(jq -r '.artifacts[0].type // ""' "$metadata_file") 8 artifact_summary=$(jq -r '.artifacts[0].summary // ""' "$metadata_file") 9else 10 status="failed" 11fi

Stage 7: Update Task Status (Postflight)

If status is "researched", update state.json and TODO.md.

Update state.json:

bash
1jq --arg ts "$(date -u +%Y-%m-%dT%H:%M:%SZ)" \ 2 --arg status "researched" \ 3 '(.active_projects[] | select(.project_number == '$task_number')) |= . + { 4 status: $status, 5 last_updated: $ts 6 }' specs/state.json > specs/tmp/state.json && mv specs/tmp/state.json specs/state.json

Update TODO.md: Use Edit tool to change status marker to [RESEARCHED].


Add artifact to state.json with summary.

IMPORTANT: Use two-step jq pattern to avoid escaping issues.

bash
1if [ -n "$artifact_path" ]; then 2 # Step 1: Filter out existing research artifacts (use "| not" pattern) 3 jq '(.active_projects[] | select(.project_number == '$task_number')).artifacts = 4 [(.active_projects[] | select(.project_number == '$task_number')).artifacts // [] | .[] | select(.type == "research" | not)]' \ 5 specs/state.json > specs/tmp/state.json && mv specs/tmp/state.json specs/state.json 6 7 # Step 2: Add new research artifact 8 jq --arg path "$artifact_path" \ 9 --arg type "$artifact_type" \ 10 --arg summary "$artifact_summary" \ 11 '(.active_projects[] | select(.project_number == '$task_number')).artifacts += [{"path": $path, "type": $type, "summary": $summary}]' \ 12 specs/state.json > specs/tmp/state.json && mv specs/tmp/state.json specs/state.json 13fi

Update TODO.md: Add research artifact link using count-aware format.

Strip specs/ prefix for TODO.md (TODO.md is inside specs/): todo_link_path="${artifact_path#specs/}"

Use count-aware artifact linking format per .claude/rules/state-management.md "Artifact Linking Format".


Stage 9: Git Commit

bash
1git add -A 2git commit -m "task ${task_number}: complete research 3 4Session: ${session_id} 5 6Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>"

Stage 10: Cleanup

bash
1rm -f "specs/${padded_num}_${project_name}/.postflight-pending" 2rm -f "specs/${padded_num}_${project_name}/.postflight-loop-guard" 3rm -f "specs/${padded_num}_${project_name}/.return-meta.json"

Stage 11: Return Brief Summary

Market sizing research completed for task {N}:
- Mode: {mode}, {questions_asked} forcing questions completed
- Problem: {brief problem statement}
- Entity count: {value} from {source}
- Research report: specs/{NNN}_{SLUG}/reports/01_{short-slug}.md
- Status updated to [RESEARCHED]
- Changes committed
- Next: Run /plan {N} to create implementation plan

Return Format

Brief text summary (NOT JSON).

Expected successful return:

Market sizing research completed for task 234:
- Mode: SIZE, 8 forcing questions completed
- Problem: Streamline deploy coordination for mid-market SaaS
- Entity count: 500,000 mid-market SaaS companies globally (Gartner)
- Research report: specs/234_market_sizing_fintech/reports/01_market-sizing.md
- Status updated to [RESEARCHED]
- Changes committed with session sess_1736700000_abc123
- Next: Run /plan 234 to create implementation plan

Error Handling

Input Validation Errors

Return immediately if task not found.

Metadata File Missing

Keep status as "researching" for resume.

User Abandonment

Return partial status with progress made.

Git Commit Failure

Non-blocking: Log failure but continue.

相关技能

寻找 skill-market 的替代方案 (Alternative) 或可搭配使用的同类 community Skill?探索以下相关开源技能。

查看全部

openclaw-release-maintainer

Logo of openclaw
openclaw

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

333.8k
0
AI

widget-generator

Logo of f
f

为prompts.chat的信息反馈系统生成可定制的插件小部件

149.6k
0
AI

flags

Logo of vercel
vercel

React 框架

138.4k
0
浏览器

pr-review

Logo of pytorch
pytorch

Python中具有强大GPU加速的张量和动态神经网络

98.6k
0
开发者工具