agentsclimarketplace

Article read

Skill zhijunio/skills/article-read

个人 Agent Skills:健康、阅读、写作、日记、Keep 等脚本与说明

Install
npx -y skills add zhijunio/skills --skill article-read

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Fetch URL or PDF as clean Markdown for reading, citation, or archive (读). Modes convert (default), summarize, save, preview. Routes CN platforms, GitHub, PDF, proxy cascade, MCP fallback. Use for 读链接, 抓取正文, 提取文章; not article drafts, topic learning workspace, or codebase audit.

SKILL.md

3.1 KB, as published. Nobody here has run it

Article Read

Role: 读 — URL / PDF → Markdown for reading, citation, or archive. Scripts under scripts/; policy under references/.

Hard rules

  1. Quote URLs in shell.
  2. Repo text (non-PDF) → editor Read tool.
  3. Never invent body on fetch failure.
  4. Paywall/login wall → reject; see references/cascade.md.
  5. One mode per run unless user sequences (e.g. convert then summarize).

Modes

ModeUser signalsRead
convert (default)读一下, 抓取, fetch URLreferences/workflow.md
summarize摘要, 总结 + URLreferences/summarize.md
save保存, save to filereferences/output.md § save
preview预览, 太长references/output.md § length

Workflow (convert)

  1. Intakereferences/workflow.md (classify input).
  2. Routereferences/router.md → domain refs if needed.
  3. Fetch:
READ_ROOT="<path-to>/article-read"
bash "${READ_ROOT}/scripts/read.sh" "https://…"
  1. Deliver — wrapper in references/output.md.
  2. On failurereferences/vet.md + references/mcp-fallback.md.

Script surface

ScriptPurpose
scripts/read.shMain fetch
scripts/save.shstdin → ~/Downloads/{slug}.md
scripts/pdf-extract.shLocal PDF text
scripts/feishu-fetch.pyFeishu Open API (needs creds)
scripts/github-blob-to-raw.pyGitHub blob → raw URL
scripts/lib/common.shShared (sourced by read.sh)

Deps: scripts/requirements.txt (requests for Feishu).

Validation

After editing scripts:

bash -n article-read/scripts/read.sh
bash -n article-read/scripts/save.sh
bash -n article-read/scripts/pdf-extract.sh
bash -n article-read/scripts/lib/common.sh

Smoke: bash article-read/scripts/read.sh "https://example.com" (expect fetch attempt or documented fallback).

Boundaries

UseUse instead
Single URL/PDF → MDMulti-query writing research → article-write gather
Citation / topic-learn sources/Systematic topic mastery workspace → topic-learn
Optional summarize after fetchArticle drafting → article-write; codebase audit → codebase-audit
Repo text (non-PDF) → editor Read toolMulti-platform排版导出

References

  • references/workflow.md — intake, modes, commands
  • references/router.md — decision tree
  • references/cascade.md — proxy tiers, paywalls
  • references/domain-cn.md — 微信、飞书
  • references/domain-stealth.md — JS / 反爬域名
  • references/domain-github-pdf.md — GitHub、PDF
  • references/mcp-fallback.md
  • references/output.md
  • references/summarize.md
  • references/vet.md
  • references/topic-sources.md

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.