cnki-researcher
Skill28 starsChanged 2 months agoMITView on GitHub
Coordinate a CNKI literature workflow from search and screening to evidence-based reading and citation export.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- vluckyzhang/cnki-skills-codextheir own version, first seen Jun 14, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- vluckyzhang/cnki-skills-codex★ 17same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository12 other files it gives its agents.
- cnki-advanced-searchSkill
- cnki-downloadSkill
- cnki-evidence-tableSkill
- cnki-exportSkill
- cnki-jevSkill
- cnki-journal-browseSkill
- cnki-navigate-pagesSkill
- cnki-paper-detailSkill
- cnki-parse-resultsSkill
- cnki-resumeSkill
- cnki-screeningSkill
- cnki-searchSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
17 rules. About 0 are common, 15 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈15
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 8
Use the sibling cnki-* skills when installed.
- Distinctive: line 9
If one is missing, report the missing module and perform only stages supported by the available tools.
- Distinctive: line 13
Default to Chinese journal articles.
- Distinctive: line 14
Use cnki-search or cnki-advanced-search, cnki-navigate-pages and cnki-parse-results.
- Distinctive: line 19
Use cnki-paper-detail. Full-text analysis requires retrieved readable full text.
- Very specific: line 21
When downloads are requested, use cnki-download with PDF as the default.
- Very specific: line 22
Create the local Downloads/CNKI/YYYY-MM-DD folder first (user's local date.
- Distinctive: line 27
Use cnki-export for the requested citation set.
- Distinctive: line 29
Before delivery compare all titles/identifiers against extracted records, ensure no duplicate filler entries, and verify exported counts …
- Distinctive: line 36
When the user requests screening tables, empirical comparisons, or resumable work, use cnki-resume from task start and save each verified …
- Distinctive: line 57
Use the user's available browser connector.
- Distinctive: line 66
Start at an already-open CNKI official/authorized institutional entry.
- Distinctive: line 73
Never start at an overseas mirror (oversea.cnki.net, global.cnki.net, data.oversea.cnki.net, scholar.cnki.net, ar.oversea.cnki.net or …
- Distinctive: line 82
Do not invent selectors, search API payloads, article URLs, download hashes or session tokens.
- Distinctive: line 83
Use read-only DOM extraction only if supported and grounded in observed markup.
- Distinctive: line 84
If an operation fails twice without progress, preserve completed records and report the blocker.
- Distinctive: line 102
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.
≈ “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.
Files
CNKI research workflow
Use the sibling cnki-* skills when installed; read each before its stage. If one is missing, report the missing module and perform only stages supported by the available tools. These are instructions, not automatic subagent spawning.
- State the database, query/fields, period, sort, requested count and citation scope. Default to Chinese journal articles. For “since 2023” use 2023-01-01 through today.
- Use cnki-search or cnki-advanced-search, cnki-navigate-pages and cnki-parse-results. Freeze a unique, source-linked result list before screening; retain site rank.
- Select the requested subset based on title/abstract relevance to the question. Explain selection and retain original list numbers. Do not substitute newer or better-known papers outside the list without clearly reporting the change.
- Use cnki-paper-detail. Full-text analysis requires retrieved readable full text; otherwise label abstract/preview analysis and identify missing evidence. When downloads are requested, use cnki-download with PDF as the default. Create the local Downloads/CNKI/YYYY-MM-DD folder first (user's local date; respect a supplied destination), then save and verify files there. Reuse the current session and follow cnki-download's bounded progress-based waiting. Preserve an explicit user format choice; otherwise do not substitute CAJ when PDF is unavailable. Continue accessible items and report the shortfall.
- Use cnki-export for the requested citation set. If “export the citations” is unspecified, export the listed set and a separate selected-subset file.
- Before delivery compare all titles/identifiers against extracted records, ensure no duplicate filler entries, and verify exported counts and file paths.
- Return the search manifest, result list, reading analysis, .bib artifact and any limitations. Never claim a blocked stage completed.
Durable screening, comparison and resume
When the user requests screening tables, empirical comparisons, or resumable work, use cnki-resume from task start and save each verified result immediately. Use cnki-screening for criterion-linked include/exclude/uncertain decisions, and cnki-evidence-table for per-field evidence with page/section locators. Follow their shared schema; use one task file through these stages. Existing local readable papers can be analyzed without downloading again. Missing sibling modules are reported, never implicitly installed.
On continuation, read the existing queue before any web action. Reuse completed records and verified files; inspect running transfers before retry. Preserve the original query/criteria and selection scope. Export the workbook even if access blocks some records, while explicitly reporting unfinished work and abstract-only analysis. Do not claim structural evidence validation proves scholarly accuracy.
Browser and access
Optional paid screening: use cnki-jev only when installed and explicitly enabled for this task with an authorized title/abstract upload scope and budget. Read its SKILL.md before use. Otherwise keep the baseline workflow. Jev proposals do not replace frozen criteria, source evidence, or the existing screening ledger.
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:
- 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).
- 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:
- 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.
- 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.
- 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.
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
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.

