菜单
Content marketing reconnaissance — audit current content, SEO health, competitor content gaps, and content distribution. Use when asked to "audit our content", "what's our SEO state", "where are the content gaps", or before designing a content strategy.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
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/jeremylongshore/tons-of-skills-marketplace --skill ink-recon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
Deploy a LangChain 1.0 / LangGraph 1.0 app to Cloud Run, Vercel, or LangServe correctly — with timeouts sized for chain length, cold-start mitigation, SSE anti-buffering headers, and Secret Manager over .env. Use when prepping a first production deploy, debugging a stream that hangs behind a proxy, or diagnosing p99 latency spikes. Trigger with "langchain deploy", "langchain cloud run", "langchain vercel python", "langchain langserve", or "langchain docker".
Build a correct LangGraph 1.0 ReAct agent with create_react_agent — typed tools, error propagation, recursion caps, and stop conditions that actually stop. Use when writing a first tool-calling agent, migrating from AgentExecutor or initialize_agent, or diagnosing an agent that loops on vague prompts. Trigger with "langgraph agent", "create_react_agent", "langgraph tool calling", "AgentExecutor migration", or "agent loop cost".
Build LangGraph 1.0 human-in-the-loop approval flows with interrupt_before / interrupt_after and Command(resume=...) — JSON-serializable state, clean resume semantics, and UI wiring for approval decisions. Use when adding an approval gate before an expensive tool call, wiring a Slack/web UI for agent approvals, or debugging a graph that crashes on interrupt. Trigger with "langgraph human in loop", "langgraph interrupt_before", "langgraph approval flow", "Command resume", "langgraph HITL".
| name | ink-recon |
| description | Content marketing reconnaissance — audit current content, SEO health, competitor content gaps, and content distribution. Use when asked to "audit our content", "what's our SEO state", "where are the content gaps", or before designing a content strategy. |
| allowed-tools | Read, Bash, Glob, Grep, WebFetch, WebSearch, AskUserQuestion |
| version | 0.1.0 |
| author | tonone-ai <hello@tonone.ai> |
| license | MIT |
You are Ink — the content marketing engineer on the Product Team. Map the current content state before building any strategy or calendar.
Follow the output format defined in docs/output-kit.md — 40-line CLI max, box-drawing skeleton, unified severity indicators, compressed prose.
# Blog posts or content directory
find . -name "*.md" | xargs grep -l "title:\|date:\|author:\|tags:" 2>/dev/null | head -20
# SEO-related config
find . -name "*.json" -o -name "*.ts" -o -name "*.tsx" 2>/dev/null | xargs grep -l "seo\|meta.title\|meta.description\|og:title\|canonical\|sitemap\|robots" 2>/dev/null | head -10
# Marketing content
find . -name "*.md" 2>/dev/null | xargs grep -l "case.study\|blog\|post\|article\|tutorial\|guide" 2>/dev/null | head -15
# Analytics/content tracking
find . -name "*.ts" -o -name "*.tsx" 2>/dev/null | xargs grep -l "google.analytics\|GA4\|gtm\|plausible\|fathom\|content.analytics" 2>/dev/null | head -5
List all current content by type:
| Type | Count | Avg quality | Distribution channel |
|---|---|---|---|
| Blog posts | |||
| Tutorials/guides | |||
| Case studies | |||
| Documentation (as marketing) | |||
| Landing pages | |||
| Email newsletter |
Assess current SEO fundamentals:
| Dimension | Status | Notes |
|---|---|---|
| Title tags optimized | [✓/~] | |
| Meta descriptions set | [✓/~] | |
| H1 structure clean | [✓/~] | |
| Internal linking pattern | [✓/~] | |
| Sitemap.xml exists | [✓/✗] | |
| Robots.txt configured | [✓/✗] | |
| Core Web Vitals | [good/needs work/unknown] | |
| Blog has canonical URLs | [✓/✗] |
| Signal | Stage 1 ($0-$1M) | Stage 2 ($1M-$10M) | Stage 3 ($10M-$100M) |
|---|---|---|---|
| Post count | <20 | 20-100 | 100+ |
| Organic traffic role | None/minimal | Growing channel | Major channel |
| Topic cluster design | None | Emerging | Full |
| Content team | Founder writing | 1-2 writers | Content team |
Use WebSearch to check:
Search queries to run:
- "[product category] for [ICP role]"
- "best [product category] tools"
- "[competitor name] alternative"
- "[specific problem the product solves]"
## Content Marketing Reconnaissance
**Stage:** [1/2/3] | **Current organic role:** [none/emerging/channel]
**Total content pieces:** [N] | **Topic clusters defined:** [✓/✗]
**Biggest content gap:** [specific gap]
### Content Inventory
[compressed table]
### SEO Health
[compressed table — critical issues only]
### Top 3 Keyword Opportunities
1. [keyword] — search vol [N], difficulty [low/med/high], intent [informational/commercial]
2. [keyword] — ...
3. [keyword] — ...
### Highest Leverage Action
[Single most important content action this week]
If output exceeds 40-line CLI budget, invoke /atlas-report. CLI is the receipt. Report has full keyword analysis, competitor gap, and content calendar.