agentleFS
longkou1988longkou1988/cnki-skills/skills/cnki-advanced-search/SKILL.md

cnki-advanced-search

Skill28 starsChanged 2 months agoMITView on GitHub

Search CNKI with subject, title, author, institution, journal and date filters using the current advanced-search UI.

4 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

9 rules. About 0 are common, 9 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈9

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use the page's date controls.

    line 11
  2. Distinctive:

    If fewer results than requested, report the actual number.

    line 15
  3. Distinctive:

    Use the user's available browser connector.

    line 18
  4. Distinctive:

    Start at an already-open CNKI official/authorized institutional entry.

    line 27
  5. Distinctive:

    Never start at an overseas mirror (oversea.cnki.net, global.cnki.net, data.oversea.cnki.net, scholar.cnki.net, ar.oversea.cnki.net or …

    line 34
  6. Distinctive:

    Do not invent selectors, search API payloads, article URLs, download hashes or session tokens.

    line 43
  7. Distinctive:

    Use read-only DOM extraction only if supported and grounded in observed markup.

    line 44
  8. Distinctive:

    If an operation fails twice without progress, preserve completed records and report the blocker.

    line 45
  9. Distinctive:

    Do not treat a plain redirect to oversea.cnki.net as "the domestic site is down" by itself — navigate to the kns.cnki.net entry first.

    line 63

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

CNKI advanced-search

  1. Open the visible 高级检索 link from the authorized entry. Inspect all available field and Boolean controls.
  2. Translate intent into rows: topic → 主题, title → 篇名, author → 作者, institution → 作者单位, journal → 文献来源, only when those labels actually exist. If a field is unavailable, disclose that limitation instead of silently changing its meaning.
  3. Connect separate concepts with AND. For the acceptance example use 主题=生成式人工智能 AND 主题=企业创新, journals only, publication date from 2023-01-01 through today's date. Preserve the user's own alternative query if provided.
  4. Use the page's date controls; record whether they filter publication, online-first or year only. A year-only filter may include forthcoming issues: disclose this and inspect online dates when a strict cutoff matters.
  5. Inspect any enabled synonym/Chinese-English expansion option; record the state and do not describe expanded search as exact matching.
  6. Submit, then verify active criteria and result count. For newest first choose the visible date/发表时间 sort and verify descending selection. Do not pass ScienceDirect parameters such as qs, tak or sortBy.
  7. Extract the requested results using cnki-parse-results if installed, or read each row's exact title, URL, date, source and displayed authors. Count unique records, preserve site order, and report missing/shortened fields.
  8. If fewer results than requested, report the actual number. Broaden only within the user's scope and label the new search separately.

Browser and access

Use the user's available browser connector. Claude Code: Chrome DevTools MCP (list pages → select page → take snapshot → interact). Codex: use its available browser skill/tool and documented API. WorkBuddy: the browser-skill CLI (bsk) — bsk session start → bsk navigate <url> --session <id> → bsk snapshot → interact → bsk session stop <id> (mandatory, even on error paths). Read that tool's instructions first; do not assume Chrome DevTools names exist in the other runtimes. If no connector is available, report the missing dependency, without installing it implicitly.

Start at an already-open CNKI official/authorized institutional entry. Otherwise default to the domestic CNKI site, in this order:

  1. https://kns.cnki.net/kns8s/defaultresult/index — domestic 检索 entry (verified working: renders 主题 + 学术期刊 controls and the result table, and honours an institutional login).
  2. https://www.cnki.net/ — domestic homepage, only if the entry above is unreachable.

Never start at an overseas mirror (oversea.cnki.net, global.cnki.net, data.oversea.cnki.net, scholar.cnki.net, ar.oversea.cnki.net or similar). Detection: if the page title is "CNKI Overseas" or the host contains oversea, you are on the international platform — www.cnki.net may silently redirect there depending on the network exit point. Navigate straight to the kns.cnki.net entry above instead of staying on the mirror. Preserve the current institution route and observed links; do not reconstruct proxy URLs or trust a hostname solely because it contains "cnki". Inspect current visible controls before acting; refresh observations after navigation. Do not invent selectors, search API payloads, article URLs, download hashes or session tokens. Use read-only DOM extraction only if supported and grounded in observed markup. If an operation fails twice without progress, preserve completed records and report the blocker. Login and CAPTCHA require user intervention under the runtime policy; do not evade detection or bypass access controls. Do not export cookies or credentials. Close owned temporary tabs when finished, retaining only a page needed for user handoff.

Overseas fallback (last resort only)

Fall back to an overseas mirror only when the domestic site is genuinely unreachable or blocked for the user — for example kns.cnki.net times out, returns a network/ISP block page, or shows an access blocker with no institutional route available. When that happens:

  1. Tell the user explicitly that the domestic site failed, state the observed reason (timeout, block page, missing institution entitlement), and say you are switching to the international platform.
  2. Record which platform produced every result: the overseas edition indexes a different corpus, so counts, full text and export formats are not comparable with domestic CNKI results.
  3. Re-check whether an authorized domestic route exists before continuing; if the user has one, ask before settling for the overseas edition. Do not treat a plain redirect to oversea.cnki.net as "the domestic site is down" by itself — navigate to the kns.cnki.net entry first.

Evidence

This release is a UI-guided workflow, not a tested site scraper. In development, www.cnki.net redirected to oversea.cnki.net; Chinese language selection reached /chn/, exposing 主题, 搜索, 高级检索 and 出版物检索. Clicking 高级检索 on the overseas platform triggered a puzzle CAPTCHA before query submission. A later run opened https://kns.cnki.net/kns8s/defaultresult/index directly: the domestic 检索 page rendered 主题/学术期刊 controls and a result table, an institutional login was recognised, and a 主题 keyword search returned 总库 / 学术期刊 / 学位论文 counts without a CAPTCHA. The domestic entry is therefore the verified default; the overseas platform is fallback only (see above). Domestic full-text download and export controls remain unverified. Treat domestic and international platforms separately. Never report an attempted click as a successful search/export/download. Keep publication date, online-first date and indexing date distinct. Missing fields stay missing.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.