Agent skill

Product Tech Influence Article

by digoal in digoal/blog

Write a concise, source-backed Chinese WeChat-ready Markdown article that helps raise a product's technical influence from a neutral third-party advisor perspective, but stop without writing when…

GPL-2.0Auto-check passedProductivity & Automation

Install Product Tech Influence Article

skills CLI
$ npx skills add digoal/blog --skill product-tech-influence-article -a claude-code

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

GitHub CLI
$ gh skill install digoal/blog product-tech-influence-article --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/product-tech-influence-article .claude/skills/product-tech-influence-article && 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
product-tech-influence-article
GitHub stars
8.6k
Token cost
~1.8k tokens
SKILL.md length
894 words
Files
2
Skills in repo
98
Repo updated
First seen
Licence
GPL-2.0

At a glance

Write a concise, source-backed Chinese WeChat-ready Markdown article that helps raise a product's technical influence from a neutral third-party advisor perspective, but stop without writing when…

  • Works in 6 steps: Clarify the target product. → Search current evidence. → Apply the evidence gate before writing. → …
  • The user provides a product name and asks for recent-news-based product influence writing
  • SKILL.md covers Goal, Workflow, Article Shape and Quality Bar
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Product Tech Influence Article is an agent skill from digoal/blog. Write a concise, source-backed Chinese WeChat-ready Markdown article that helps raise a product's technical influence from a neutral third-party advisor perspective, but stop without writing when recent evidence is insufficient. Use when the user provides a product name and asks for recent-news-based product influence writing, product technology commentary, product industry interpretation, brand-neutral technical positioning, or a short public-account article saved under the current project's markdown directory.

Its SKILL.md is about 1.8k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).

It sits in Productivity & Automation, covering Messaging and chat bots. It works with WeChat. 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

  • The user provides a product name and asks for recent-news-based product influence writing
  • Product technology commentary
  • Product industry interpretation
  • Brand-neutral technical positioning

Example prompts

  • “/product-tech-influence-article”

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. Clarify the target product.
  2. Search current evidence.
  3. Apply the evidence gate before writing.
  4. Judge before writing.
  5. Write the article.
  6. Save the output.

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 markdown).

    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

Product Tech Influence Article loads about 1.8k tokens when it runs. Until then it costs about 137 tokens; SKILL.md has 894 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~137
When it runs · the whole SKILL.md, loaded when a task matches
~1.8k

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). 894 words, ~1,805 tokens.

Download SKILL.mdSave it as .claude/skills/product-tech-influence-article/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
product-tech-influence-article
description
Write a concise, source-backed Chinese WeChat-ready Markdown article that helps raise a product's technical influence from a neutral third-party advisor perspective, but stop without writing when recent evidence is insufficient. Use when the user provides a product name and asks for recent-news-based product influence writing, product technology commentary, product industry interpretation, brand-neutral technical positioning, or a short public-account article saved under the current project's markdown directory.

Product Tech Influence Article

Goal

Create a short Chinese Markdown article for mobile WeChat reading based on enough recent evidence about a named product. Write as a knowledgeable neutral advisor who understands the product's industry, users, and future trend, with the purpose of improving the product's technical influence without obvious polishing or marketing tone. If enough recent evidence is not available, stop and report that no article was created.

Workflow

  1. Clarify the target product.

    • If the product name is ambiguous, identify the likely company, product category, region, and market segment from public sources.
    • If ambiguity could change the article materially, ask one concise clarification question.
  2. Search current evidence.

    • Search web news from the last 30 days for the product name, company, key competitors, product category, and relevant industry keywords.
    • Prefer primary sources and reputable third-party sources: official announcements, product docs, earnings/newsroom posts, regulator releases, established media, industry analysts, benchmark reports, user/community evidence, and credible technical blogs.
    • Add broader evidence when needed: market trend reports, competitor moves, technical standards, user adoption signals, security incidents, pricing changes, funding, ecosystem launches, or customer cases.
    • Also collect enough background to introduce the topic naturally before the news: what the product is, who uses it, what category it belongs to, what problem it addresses, or what industry shift makes the news relevant.
    • Record source URLs, publication dates, key facts, and whether each source is primary, third-party, or opinion.
  3. Apply the evidence gate before writing.

    • Continue only when there are enough timely, product-specific facts to support a public article.
    • Treat evidence as sufficient only when at least one of these is true:
      • there are 2 or more credible product-specific sources from the last 30 days;
      • there is 1 credible product-specific source from the last 30 days plus 2 or more recent supporting sources about the same product, company, industry, users, regulation, ecosystem, or competitors;
      • the user explicitly provides fresh internal or external material and asks to use it.
    • Treat evidence as insufficient when the last 30 days contain no credible product-specific update, only old news, only duplicated reposts of the same item, only thin sales pages, or only weak community chatter.
    • If evidence is insufficient, do not write or save an article. Return a concise note with:
      • 未生成文章:近 30 天缺少足够、可信、可写成文章的产品相关证据。
      • 1-3 bullets summarizing what was searched or what evidence was missing.
    • Do not turn lack of news into a publishable angle. Avoid openings like "过去一个月,我没有看到..." or arguments that reframe missing evidence as a meaningful industry signal.
  4. Judge before writing.

    • Separate facts from interpretation.
    • Identify what is genuinely positive, what is uncertain, and what is negative or risky.
    • Do not force a favorable conclusion. If the product has weak news momentum, reputational risk, technical debt, or unclear value, say it tactfully.
    • Use first-principles reasoning: user pain -> product capability -> technical barrier -> industry timing -> adoption constraint.
  5. Write the article.

    • Language: Chinese by default unless the user asks otherwise.
    • Voice: first person, modest, independent, and human; phrases like "我个人认为" and "仅代表个人观点" are acceptable when useful.
    • Do not reveal an author identity, role label, prompt, workflow, or AI involvement.
    • Keep it suitable for public-account publishing and phone reading: short paragraphs, strong opening, clear subheadings, no long academic blocks.
    • Before introducing the recent news, write a brief transition background: introduce the product, its user scenario, category, existing market tension, or the specific industry context that makes the news understandable.
    • Keep the background short and purposeful. It should help readers understand the news, not become a generic product encyclopedia.
    • Keep the body under 4 phone screens, roughly 900-1500 Chinese characters unless the user specifies another length.
    • Include source links in a compact "参考资料" section at the end, or inline if that reads better.
    • Add Mermaid, SVG, or ASCII only when it improves comprehension; keep visuals simple and mobile-friendly.
  6. Save the output.

    • Save as Markdown under the current project's markdown directory; create it if missing.
    • Use a readable filename such as 产品名-技术影响力短文-YYYYMMDD.md.
    • Include the article title, body, optional diagram, and references in the saved file.
    • Save only after the evidence gate passes. Never create a placeholder article for insufficient evidence.
Show full SKILL.md (212 more words)Show less

Article Shape

Do not reuse fixed second-level headings across articles. Generate headings from the actual evidence, product category, user pain, and judgment angle. Keep 3-5 short second-level headings, and make each heading carry a concrete point rather than a generic section label.

Use this flexible shape as a planning aid, not as literal headings:

markdown
# [一句有判断力的标题]

[短开场:先用一小段产品、用户场景或行业背景搭桥,再引出最新可信事实和判断]

## [围绕最新事实提炼的判断型标题]

[用事实解释产品变化、用户痛点、行业约束]

## [围绕关键技术、生态位置或用户价值生成的标题]

[分析产品的真实技术影响力来自哪里]

## [围绕风险、约束或未验证问题生成的标题]

[指出风险、短板、竞争压力或验证不足]

## [围绕下一步观察指标生成的标题]

[给出 2-3 个判断指标,不写空泛口号]

参考资料:
- [来源名:标题](URL)

Quality Bar

  • Every concrete claim about recent events, dates, launches, metrics, partnerships, regulation, security, pricing, or funding must be backed by a source.
  • Do not write an article when timely product-specific evidence is insufficient; returning no article is the correct result.
  • The article should feel like a careful person wrote it after reading evidence, not like a press release.
  • Do not start by abruptly listing news. First provide a compact transition background that explains why the news matters to the product's users, category, or industry.
  • Avoid template fatigue: do not use the same second-level headings by default, such as "不是简单的...", "我更看重...", "但问题也不能回避", or "接下来值得观察什么".
  • Prefer "this may matter because..." over exaggerated words like "颠覆", "革命", "遥遥领先", unless directly supported and quoted.
  • Keep praise specific: name the technical capability, user value, ecosystem leverage, or adoption signal.
  • Keep criticism fair: distinguish product weakness, industry constraint, execution risk, and insufficient evidence.
  • Do not fabricate news, metrics, quotes, customers, charts, or citations.

© 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 in skills/product-tech-influence-article of digoal/blog.

  • SKILL.md
  • agents/openai.yaml

Open the folder on GitHubat commit ad6fcb7

Compare with similar skills

Product Tech Influence Article 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.

Product Tech Influence Article compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Product Tech Influence Article this skilldigoal/blog8.6k—~1.8kAutomated safety check: PassGPL-2.0
Dbs Wechat HTMLdontbesilent2025/dbskill11k—~1.9kAutomated safety check: PassCustom licence
Wechat Article Aggregatorwwwzhouhui/skills_collection283—~1.5kAutomated safety check: PassNone
Wechat Article Fetcherwwwzhouhui/skills_collection283—~759Automated safety check: PassNone
Wechat Md PublisherLeoYeAI/openclaw-master-skills2.2k—~3kAutomated safety check: PassMIT
She Love Me863401402/she-love-me9251 repos~1.3kAutomated safety check: PassMIT

Similar skills

  • Dbs Wechat HTML

    dontbesilent2025/dbskill

    把 Markdown 转成可粘贴到微信公众号后台的 HTML,并提供 15 种内置风格。用户要求生成公众号 HTML、制作微信版本或排版公众号文章时使用。

    11k GitHub stars~1.9k tokensUpdated yesterday
    Productivity & AutomationAuto-check passed
  • Wechat Article Aggregator

    wwwzhouhui/skills_collection

    微信公众号文章聚合器。通过 mptext.top API 批量获取指定公众号博主的最新文章列表,下载文章内容并解析为 Markdown/HTML/纯文本格式。支持按公众号名称或 fakeid 获取,预置 8 个热门 AI 技术公众号。适用场景:获取指定公众号最新文章、批量抓取多个博主内容、公众号文章聚合阅读、技术资讯采集。关键词:公众号文章获取、微信文章抓取、公众号聚合、文章采集、mptext…

    283 GitHub stars~1.5k tokensUpdated 3 days ago
    Productivity & AutomationAuto-check passed
  • Wechat Article Fetcher

    wwwzhouhui/skills_collection

    获取并解析微信公众号文章。从微信文章链接中提取标题、作者、公众号名称、正文内容、图片和元数据。当用户提供微信文章链接(mp.weixin.qq.com/s/...)并希望阅读、提取、下载或转换文章内容时使用。适用场景包括获取/下载微信文章、提取微信文章文字或元数据、将微信文章转换为Markdown、将微信文章连同图片保存到本地。关键词:微信公众号、文章获取、文章抓取、文章下载。

    283 GitHub stars~759 tokensUpdated 3 days ago
    Productivity & AutomationAuto-check passed
  • Wechat Md Publisher

    LeoYeAI/openclaw-master-skills

    发布 Markdown 文章到微信公众号,支持草稿管理、多主题、智能图片处理、自动封面图。推荐与 news-to-markdown-skill 配合使用实现一键转载。

    2.2k GitHub stars~3k tokensUpdated 2 mo ago
    Productivity & AutomationAuto-check passed
  • She Love Me

    863401402/she-love-me

    Acquire, import, and analyze WeChat or QQ chat histories, including installing supported exporters, guiding required login or contact selection, converting exports, assessing relationship dynamics…

    925 GitHub starsUsed in 1 repo~1.3k tokens
    Productivity & AutomationAuto-check passed
  • Wechat Article Extractor

    freestylefly/wechat-article-extractor-skill

    Extract metadata and content from WeChat Official Account articles.

    136 GitHub starsUsed in 1 repo~1k tokens
    Productivity & AutomationAuto-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 Product Tech Influence Article

What does Product Tech Influence Article do?

Write a concise, source-backed Chinese WeChat-ready Markdown article that helps raise a product's technical influence from a neutral third-party advisor perspective, but stop without writing when…. Product Tech Influence Article is an agent skill from digoal/blog. Write a concise, source-backed Chinese WeChat-ready Markdown article that helps raise a product's technical influence from a neutral third-party advisor perspective, but stop without writing when recent evidence is insufficient.

When should I use Product Tech Influence Article?

Product Tech Influence Article fits situations like: the user provides a product name and asks for recent-news-based product influence writing; product technology commentary; product industry interpretation; brand-neutral technical positioning.

How do I install Product Tech Influence Article in Claude Code?

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

How do I install Product Tech Influence Article in Codex?

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

Can I use Product Tech Influence Article 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 product-tech-influence-article -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/product-tech-influence-article, .gemini/skills/product-tech-influence-article, .github/skills/product-tech-influence-article and .opencode/skills/product-tech-influence-article in your project.

What does Product Tech Influence Article need to run?

SKILL.md names no scripts, command-line tools or credentials: Product Tech Influence Article is instructions for the agent only.

Does Product Tech Influence Article 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 Product Tech Influence Article 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 Product Tech Influence Article use?

Product Tech Influence Article 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 Product Tech Influence Article use?

About 1.8k tokens (SKILL.md is roughly 7.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Product Tech Influence Article?

Skills that share tags, products or a category with Product Tech Influence Article: Dbs Wechat HTML (dontbesilent2025/dbskill, 11k stars), Wechat Article Aggregator (wwwzhouhui/skills_collection, 283 stars), Wechat Article Fetcher (wwwzhouhui/skills_collection, 283 stars) and Wechat Md Publisher (LeoYeAI/openclaw-master-skills, 2.2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Product Tech Influence Article?

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.