Agent skill

State Trend Advisor

by digoal in digoal/blog

顺势而为,跟着国家走——抓取并分析国家五年规划、政策文件及重大新闻,结合询问者背景(擅长领域、特长、爱好),围绕"投资、创业方向、商业思路、产品思路、就业择业、学习规划"六大维度,生成逻辑严密、图文并茂、有数据支撑的战略分析报告,输出到项目 markdown/ 目录。

GPL-2.0Auto-check passedDocuments & Office

Install State Trend Advisor

skills CLI
$ npx skills add digoal/blog --skill state-trend-advisor -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install digoal/blog state-trend-advisor --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/digoal/blog.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/skills_for_claude_web/state-trend-advisor .claude/skills/state-trend-advisor && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
state-trend-advisor
GitHub stars
8.6k
Token cost
~1k tokens
SKILL.md length
168 words
Files
2 (incl. references)
Skills in repo
98
Repo updated
First seen
Licence
GPL-2.0

At a glance

顺势而为,跟着国家走——抓取并分析国家五年规划、政策文件及重大新闻,结合询问者背景(擅长领域、特长、爱好),围绕"投资、创业方向、商业思路、产品思路、就业择业、学习规划"六大维度,生成逻辑严密、图文并茂、有数据支撑的战略分析报告,输出到项目 markdown/ 目录。

  • Works in 8 steps: :解析询问者背景 → :抓取政策与趋势数据 → :识别核心趋势与风口 → …
  • Tasks that involve Markdown
  • SKILL.md covers 核心理念, 执行流程总览, Step 1:解析询问者背景 and Step 2:抓取政策与趋势数据, plus 8 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

State Trend Advisor is an agent skill from digoal/blog. 顺势而为,跟着国家走——抓取并分析国家五年规划、政策文件及重大新闻,结合询问者背景(擅长领域、特长、爱好),围绕"投资、创业方向、商业思路、产品思路、就业择业、学习规划"六大维度,生成逻辑严密、图文并茂、有数据支撑的战略分析报告,输出到项目 markdown/ 目录。 触发条件:用户提到"顺势而为"、"跟着国家走"、"国家政策方向"、"五年规划"、"赚政策的钱"、"走在趋势上"、"政策红利"、"国家扶持"、"政策风口"、"应该往哪个方向走"、"未来哪些行业有前途"、"政策支持什么方向"、"国家在推什么",或者用户描述自己的背景/特长并询问未来发展方向时,必须使用本 skill。 即使用户只说"我擅长XX,应该往哪里走"或"现在创业方向怎么选",也应使用本 skill。

Its SKILL.md is about 1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/persona_mapping.md`).

It sits in Documents & Office, covering Markdown. It works with Mermaid. The repository describes itself as: AI,Opensource,Database,Business,Finance,Minds. git clone --depth 1 https://github.com/digoal/blog. The licence is GPL-2.0.

When your agent uses it

  • Tasks that involve Markdown

Example prompts

  • “投资、创业方向、商业思路、产品思路、就业择业、学习规划”
  • “国家政策方向”
  • “应该往哪个方向走”
  • “/state-trend-advisor”

Workflow steps

8 steps, taken from the step headings in SKILL.md.

  1. :解析询问者背景
  2. :抓取政策与趋势数据
  3. :识别核心趋势与风口
  4. :映射个人禀赋 → 趋势机会
  5. :生成六维分析报告
  6. :图表要求与规范
  7. :报告写作规范
  8. :文件输出

What it can do on your machine

Read from SKILL.md and the folder at commit ad6fcb7. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are mermaid and bash).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

State Trend Advisor loads about 1k tokens when it runs, and up to ~2.6k if it reads all its reference files. Until then it costs about 90 tokens; SKILL.md has 168 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~90
When it runs · the whole SKILL.md, loaded when a task matches
~1k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~2.6k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from digoal/blog at commit ad6fcb7, republished under its GPL-2.0 licence (© digoal). 168 words, ~1,041 tokens.

Download SKILL.mdSave it as .claude/skills/state-trend-advisor/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
state-trend-advisor
description
顺势而为,跟着国家走——抓取并分析国家五年规划、政策文件及重大新闻,结合询问者背景(擅长领域、特长、爱好),围绕"投资、创业方向、商业思路、产品思路、就业择业、学习规划"六大维度,生成逻辑严密、图文并茂、有数据支撑的战略分析报告,输出到项目 markdown/ 目录。 触发条件:用户提到"顺势而为"、"跟着国家走"、"国家政策方向"、"五年规划"、"赚政策的钱"、"走在趋势上"、"政策红利"、"国家扶持"、"政策风口"、"应该往哪个方向走"、"未来哪些行业有前途"、"政策支持什么方向"、"国家在推什么",或者用户描述自己的背景/特长并询问未来发展方向时,必须使用本 skill。 即使用户只说"我擅长XX,应该往哪里走"或"现在创业方向怎么选",也应使用本 skill。

State Trend Advisor — 顺势而为战略分析

核心理念

"风来了,猪都能飞。" 本 skill 的核心是:识别国家战略趋势,将个人禀赋映射到政策风口,帮助询问者在势头最强的方向上发力。


执行流程总览

1. 解析询问者背景
2. 抓取国家政策与趋势数据(五年规划 + 近期重大政策)
3. 识别核心趋势与风口
4. 映射个人禀赋 → 趋势机会
5. 生成六维分析报告(投资/创业/商业/产品/就业/学习)
6. 输出 Markdown 报告到 markdown/ 目录

Step 1:解析询问者背景

从用户输入中提取以下信息:

维度内容若未提供
擅长领域专业、工作经验、技术栈等视为"普通人,无特定专长"
特长软技能、硬技能、资源等视为"通用技能"
爱好兴趣爱好、关注领域视为"广泛兴趣"
目标导向六维中用户最关心的方向全维度输出
地域用户所在地区默认全国视角

若用户未提供背景信息,以"普通中国公民,无特定专业背景"作为基准画像,给出通用建议。


Step 2:抓取政策与趋势数据

使用 web_search 工具并行搜索以下数据源,每类至少搜索 2 次以交叉验证:

2.1 核心政策文件
搜索词(依次执行):
- "十四五规划 全文 重点方向 site:gov.cn"
- "十五五规划 2026 国家重点方向"
- "2025年 国务院 重大政策 发布"
- "2025年 中央经济工作会议 部署"
- "国家战略性新兴产业 最新政策 2025"
2.2 产业政策与补贴
- "新质生产力 重点方向 2025"
- "国家扶持产业 补贴政策 2025"
- "战略性新兴产业 七大方向 最新"
- "未来产业 政策支持 2025 2026"
2.3 投资与就业信号
- "国家重点投资领域 2025 基建"
- "紧缺人才 国家需求 2025"
- "高薪就业 政策支持行业 2025"
2.4 验证与补充

对搜索结果中出现的重要政策文件,使用 web_fetch 获取原文关键章节,确保数据准确。

数据校验原则:

  • 优先使用 gov.cn、新华社、人民日报等权威来源
  • 标注数据来源和发布时间
  • 对相互矛盾的信息,优先采信最新、最权威来源

Step 3:识别核心趋势与风口

基于抓取数据,提炼3-5 个最强政策风口,按照以下框架分析每个风口:

风口名称:[名称]
政策支撑强度:★★★★★(1-5星)
市场规模预测:[数字 + 来源]
政策进入阶段:[萌芽期/成长期/爆发期/成熟期]
典型历史参照:[类比案例,如"类似2012年移动互联网"]
主要受益群体:[技术人员/普通创业者/资本/就业者]

Step 4:映射个人禀赋 → 趋势机会

构建禀赋-趋势匹配矩阵:

  • 纵轴:询问者的核心禀赋(3-5项)
  • 横轴:识别出的政策风口(3-5个)
  • 评分:1-5分,综合考虑"切入难度"、"竞争烈度"、"个人匹配度"

优先推荐匹配分 ≥ 3 且风口强度 ≥ 3星的组合。


Step 5:生成六维分析报告

报告结构(ALWAYS 使用此结构)
# 《顺势而为:[询问者画像] 的战略方向报告》
生成时间:[日期]

## 一、国家战略趋势总览
## 二、核心风口识别(Top 3-5)
## 三、六维行动建议
   ### 3.1 投资方向
   ### 3.2 创业方向
   ### 3.3 商业思路
   ### 3.4 产品思路
   ### 3.5 就业择业
   ### 3.6 学习规划
## 四、禀赋-趋势匹配矩阵
## 五、风险与注意事项
## 六、行动优先级清单
## 七、数据来源

Step 6:图表要求与规范

SVG 图表(外挂式,必须保存为独立 .svg 文件)

每份报告至少包含以下 3 类图表,全部以外挂方式引用:

图表 1:政策风口热力图(SVG)

  • 文件名:trend_heatmap.svg
  • 内容:各风口的"政策强度 × 市场空间 × 时间窗口"气泡图
  • 在 Markdown 中引用:![政策风口热力图](trend_heatmap.svg)

图表 2:禀赋-趋势匹配矩阵(SVG 或 Mermaid)

  • 文件名:match_matrix.svg(若用 Mermaid 则内嵌)
  • 内容:个人禀赋与政策趋势的交叉评分热力表

图表 3:行动路径时间轴(SVG 或 ASCII)

  • 文件名:action_timeline.svg(若用 ASCII 则内嵌)
  • 内容:从"现在"到"3年后"的关键行动节点
SVG 设计规范
- 画布:viewBox="0 0 800 500"
- 背景:#0f172a(深色) 或 #f8fafc(浅色)
- 主色系:蓝色 #3b82f6、金色 #f59e0b、红色 #ef4444、绿色 #22c55e
- 字体:font-family="Arial, 'PingFang SC', sans-serif"
- 标题字号:18px,正文:13px,注释:11px
- 所有 SVG 文件保存在 markdown/ 目录下,与 .md 文件同级
Mermaid 图(内嵌于 Markdown)

用于流程图、关系图、时间轴(当 SVG 过于复杂时使用):

mermaid
graph TD
    A[国家政策] --> B[五年规划]
    A --> C[产业政策]
    B --> D[风口识别]
    C --> D
    D --> E[个人匹配]

Step 7:报告写作规范

语言风格
  • 面向决策者:每个建议都要有"做什么"+ "为什么"+ "怎么开始"
  • 通俗易懂:避免官方文件体,用商业语言转化政策语言
  • 有温度:理解询问者的处境,给出有人情味的建议
  • 不模糊:避免"可以考虑"等废话,给出明确方向
数据引用格式
> 据[来源],[时间],[具体数据/政策内容]。
> 来源:[URL 或文件名]
历史案例引用(增加说服力)

每个风口建议需配 1 个历史参照案例:

  • 格式:📌 历史参照:[时间] [事件] → [结果],说明[类比逻辑]
  • 示例:📌 历史参照:2012年 4G牌照发放 → 催生移动互联网十年红利,说明基础设施政策往往提前3-5年布局

Step 8:文件输出

bash
# 确保输出目录存在
mkdir -p markdown/

# 输出文件列表
markdown/
├── state_trend_report_[日期].md      # 主报告
├── trend_heatmap.svg                  # 政策风口热力图
├── match_matrix.svg                   # 禀赋匹配矩阵(可选,也可内嵌)
└── action_timeline.svg                # 行动时间轴(可选,也可内嵌)

命名规范:

  • 日期格式:YYYYMMDD,如 state_trend_report_20250611.md
  • 若询问者有明确身份,可加后缀:state_trend_report_20250611_developer.md

常见禀赋-趋势映射速查

参见 references/persona_mapping.md 获取常见职业/背景到趋势的快速映射参考。


质量自检清单

完成报告后,逐一确认:

  • 政策数据来自权威来源(gov.cn / 新华社等),且有明确时间标注
  • 每个风口都有至少一个历史案例支撑
  • 六维建议(投资/创业/商业/产品/就业/学习)全部覆盖
  • 至少 3 张图表(热力图 + 矩阵 + 时间轴)
  • SVG 文件为外挂式,在 Markdown 中正确引用
  • 报告有明确的"行动优先级清单"(可执行,非口号)
  • 风险章节提醒了政策执行落差、时间窗口等注意事项
  • 文件已保存到 markdown/ 目录

© digoal, GPL-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file (references) in skills/skills_for_claude_web/state-trend-advisor of digoal/blog.

  • SKILL.md
  • references/persona_mapping.md

Open the folder on GitHubat commit ad6fcb7

Compare with similar skills

State Trend Advisor next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

State Trend Advisor compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
State Trend Advisor this skilldigoal/blog8.6k—~1kAutomated safety check: PassGPL-2.0
Markdown to Word Convertercat-xierluo/SuitAgent205—~559Automated safety check: PassMIT
Chinese Quotes Fixranxi2001/zero2Agent703—~735Automated safety check: PassMIT
Bangunai Blog ManagerLeoYeAI/openclaw-master-skills2.2k—~5.7kAutomated safety check: PassMIT
X Article Publisherwshuyi/x-article-publisher-skill8712 repos~3.6kAutomated safety check: PassMIT
Markdown PRD to HTML Rendererowainlewis/blueprint412—~1.3kAutomated safety check: PassMIT

Similar skills

  • Markdown to Word Converter

    cat-xierluo/SuitAgent

    Converts Markdown files into Word documents formatted to Chinese typesetting conventions, with presets for academic, legal, report and book layouts.

    205 GitHub stars~559 tokensUpdated 1 mo ago
    Documents & OfficeAuto-check passed
  • Chinese Quotes Fix

    ranxi2001/zero2Agent

    Check and fix Chinese quote pairing in Markdown files generated by ClaudeCode or other agents, while preserving Markdown syntax and protected blocks.

    703 GitHub stars~735 tokensUpdated today
    Documents & OfficeAuto-check passed
  • Bangunai Blog Manager

    LeoYeAI/openclaw-master-skills

    A skill your agent uses when managing BangunAI Blog content, automating blog workflows, and writing MDX articles with BangunAI conventions.

    2.2k GitHub stars~5.7k tokensUpdated 2 mo ago
    Documents & OfficeAuto-check passed
  • X Article Publisher

    wshuyi/x-article-publisher-skill

    Publish Markdown articles to X (Twitter) Articles editor with proper formatting.

    871 GitHub starsUsed in 2 repos~3.6k tokens
    Documents & OfficeAuto-check passed
  • Markdown PRD to HTML Renderer

    owainlewis/blueprint

    Converts a complete Markdown PRD or technical design into one verified, static HTML reading page without changing what it says.

    412 GitHub stars~1.3k tokensUpdated 3 days ago
    Documents & OfficeAuto-check passed
  • Markstream Migration

    Simon-He95/markstream-vue

    Audit and migrate existing Markdown rendering to Markstream, or upgrade a markstream-vue 1.x integration to 2.x.

    3k GitHub stars~2k tokensUpdated 4 days ago
    Documents & OfficeAuto-check passed

More from digoal/blog

All 98 skills in this repo
  • 三层审查模型,逐段逐句验证文章真伪、证据链与逻辑结构。Use when the user asks to fact-check, verify, audit, or evaluate the credibility of an article, essay, report, opinion piece, social-media post, or any written claim —…

    8.6k GitHub stars~939 tokensUpdated today
    Auto-check passed
  • Find latent bugs in a local PostgreSQL source tree (RELxxSTABLE branch or HEAD) the way a core hacker does: build a heavily-poisoned debug instance (cassert + cache-discard + -O0/-ggdb3 + core…

    8.6k GitHub stars~4k tokensUpdated today
    Auto-check passed
  • Digoal

    digoal/blog

    Portable digital employee distilled from digoal's personal blog for PostgreSQL, PolarDB, DuckDB, AI+database, vector/RAG, database operations, source-code reading, technical content creation…

    8.6k GitHub stars~2.2k tokensUpdated today
    Auto-check passed
  • 从论文 PDF 文件或论文 PDF URL 生成通俗易懂、图文并茂、带批判性评估的中文 Markdown 解读,并保存到当前项目的 markdown 目录。Use when the user asks to interpret,精读,解读,summarize,explain,analyze, or write an article from an academic paper PDF…

    8.6k GitHub stars~1.5k tokensUpdated today
    Auto-check passed
  • Analyze a product from documentation, websites, PDFs, articles, release notes, pricing pages, app listings, reviews, filings, or related links; save separate intermediate analyses from seven roles…

    8.6k GitHub stars~1.8k tokensUpdated today
    Auto-check passed
  • Turn a blog post, article, notes, or any source material into a set of vertical poster images — one cover plus several coherent content slides that explain the core points.

    8.6k GitHub stars~1.4k tokensUpdated today
    Auto-check passed

Works with

Questions about State Trend Advisor

What does State Trend Advisor do?

顺势而为,跟着国家走——抓取并分析国家五年规划、政策文件及重大新闻,结合询问者背景(擅长领域、特长、爱好),围绕"投资、创业方向、商业思路、产品思路、就业择业、学习规划"六大维度,生成逻辑严密、图文并茂、有数据支撑的战略分析报告,输出到项目 markdown/ 目录。. State Trend Advisor is an agent skill from digoal/blog.

When should I use State Trend Advisor?

State Trend Advisor fits situations like: tasks that involve Markdown.

How do I install State Trend Advisor in Claude Code?

Run `npx skills add digoal/blog --skill state-trend-advisor -a claude-code`. Or copy the skill folder (skills/skills_for_claude_web/state-trend-advisor in digoal/blog) into .claude/skills/state-trend-advisor in your project. Claude Code loads it when a task matches its description.

How do I install State Trend Advisor in Codex?

Run `npx skills add digoal/blog --skill state-trend-advisor -a codex`. Or copy the skill folder (skills/skills_for_claude_web/state-trend-advisor in digoal/blog) into .agents/skills/state-trend-advisor in your project. Codex loads it when a task matches its description.

Can I use State Trend Advisor in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add digoal/blog --skill state-trend-advisor -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/state-trend-advisor, .gemini/skills/state-trend-advisor, .github/skills/state-trend-advisor and .opencode/skills/state-trend-advisor in your project.

What does State Trend Advisor need to run?

SKILL.md names no scripts, command-line tools or credentials: State Trend Advisor is instructions for the agent only.

Does State Trend Advisor access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is State Trend Advisor safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does State Trend Advisor use?

State Trend Advisor is published under the GPL-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does State Trend Advisor use?

About 1k tokens (SKILL.md is roughly 4.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.6k tokens, read only when the agent opens those files.

What are the alternatives to State Trend Advisor?

Skills that share tags, products or a category with State Trend Advisor: Markdown to Word Converter (cat-xierluo/SuitAgent, 205 stars), Chinese Quotes Fix (ranxi2001/zero2Agent, 703 stars), Bangunai Blog Manager (LeoYeAI/openclaw-master-skills, 2.2k stars) and X Article Publisher (wshuyi/x-article-publisher-skill, 871 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains State Trend Advisor?

digoal (a GitHub user) maintains it in digoal/blog, which has 8,586 GitHub stars. The repository holds 98 skills in this directory. The repository was last updated on October 9, 2026.

Source: digoal/blog on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.