[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DBG8D5EKKEA7EX4G2XNWSF":3,"skill-same:01M6DBG8D5EKKEA7EX4G2XNWSF":63},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":23,"publishedAt":38,"linkOnly":39,"markdownContent":40,"markdownBody":41,"frontMatter":42,"refName":43,"commitSha":44,"skillDirectory":45,"forksCount":14,"repositoryHtmlUrl":46,"repositoryHomepageUrl":6,"ownerHtmlUrl":47,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":48,"install":49,"resources":62},"01M6DBG8D5EKKEA7EX4G2XNWSF","institutional-literature-access",null,"Use when the user has lawful university or consortium access and needs a disciplined route through institutional library portals, ORCID identity, DOI\u002FOA fallback, and secret-safe configuration. Includes the working E-nformation (Anelis Plus) Muse Proxy recipe, canonical cookie-jar location, and refresh procedure.","Prekzursil\u002Fagent-skills-toolchain","Prekzursil","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F54636077?v=4","01M6DACZ1PCQHD99SCR1YXG28B","Andrei Mihai Visalon","01M6DACZ670WZF535V3WYYSS4Z",0,"MIT","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Finstitutional-literature-access\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000021","资料检索与研究","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37],"access","institutional literature access","safe","identity","proxy","library","refresh","user","use","fallback","configuration","location","muse","route","2026-11-10 10:12:30",false,"---\nname: institutional-literature-access\ndescription: Use when the user has lawful university or consortium access and needs a disciplined route through institutional library portals, ORCID identity, DOI\u002FOA fallback, and secret-safe configuration. Includes the working E-nformation (Anelis Plus) Muse Proxy recipe, canonical cookie-jar location, and refresh procedure.\n---\n\n# institutional-literature-access\n\nThis skill routes lawful institutional access for research literature. Treat the user-provided University of Bucharest and E-nformation entitlement list as data, not as blanket permission. Start with the legal access path, then fall back to DOI, OA, repository, and metadata-only routes.\n\n## When to use\n\n- The user has university, library, or consortium entitlements and needs the cleanest legal path to papers, books, or analytics platforms.\n- Access depends on an institutional portal, federated login, proxy\u002FVPN, ORCID sign-in, or registered researcher identity.\n- The workflow must remember configuration labels and the canonical secrets locations below; never scatter session material anywhere else.\n\n## E-nformation (Anelis Plus) proxy access — WORKING RECIPE\n\nThe owner (Miky) has an institutional account with e-nformation.ro (Anelis Plus consortium)\ncovering JSTOR, Cambridge Core, Oxford, Project MUSE, De Gruyter, Springer, T&F, Wiley, etc.\nThis access is owner-sanctioned for agent use. Verified facts (2026-08-20):\n\n- **Proxy**: MuseKnowledge Proxy at `https:\u002F\u002Fz.e-nformation.ro\u002F` (hostname-rewriting mode).\n- **Proxy URL pattern**: `{prefix}-y-https-{target-host-with-dashes}.z.e-nformation.ro`\n  e.g. `0511ar8cs-y-https-www-jstor-org.z.e-nformation.ro\u002Fstable\u002F...`\n  The `{prefix}` is minted per session; do not hardcode it. Cambridge Core would rewrite as\n  `...-y-https-www-cambridge-org.z.e-nformation.ro`.\n- **Proxy application ID**: `PlatformaUnivBucsiBCUBuc` (Univ. Bucharest + BCU Bucharest, groupID=1).\n  Entry point: `https:\u002F\u002Fz.e-nformation.ro\u002FPlatformaUnivBucsiBCUBuc`.\n- **Entering a target URL through the proxy** (once authenticated):\n  `https:\u002F\u002Fz.e-nformation.ro\u002FPlatformaUnivBucsiBCUBuc?groupID=1&action=source&sourceID={Source}&qurl={url-encoded target URL}`\n  (observed with `sourceID=Jstor`; the proxy then redirects to the rewritten `{prefix}-y-https-...` hostname).\n- **Auth flow**: the proxy 302-redirects unauthenticated requests to\n  `https:\u002F\u002Fwww.e-nformation.ro\u002Fprofil-acces?_rwpReturn=...&_rwpAppId=PlatformaUnivBucsiBCUBuc`.\n  Log in on the portal (WordPress-style) with the credentials below, then follow the\n  `_rwpReturn` redirect back to `z.e-nformation.ro` — this mints a fresh `MuseProxySessionID`\n  cookie on `.z.e-nformation.ro`. There is NO login form on the proxy itself (`\u002Flogon` is 404);\n  auth is fully delegated to the portal.\n- **Credentials**: environment variables `INSTITUTIONAL_EMAIL` and `INSTITUTIONAL_PASSWORD`\n  (set at both User and Machine scope). Names only here — never print the values.\n- **Canonical cookie jar**: `C:\\Users\\Prekzursil\\.agents\\secrets\\enformation-cookies.txt`\n  (Netscape format, used with `curl -b\u002F-c`). The `.agents\\secrets\\` directory is the ONLY\n  permitted location for session material; it is gitignored (`.agents\\.gitignore`) and must\n  never be committed or copied elsewhere.\n- **Cookie lifetimes**: `MuseProxySessionID` is a session cookie that expires server-side\n  within hours–a day; expect to refresh it. JSTOR `AccessPersist` cookies last ~1 month.\n- **One-line access test** (authenticated content vs login redirect):\n  `curl.exe -s -o NUL -b \"C:\\Users\\Prekzursil\\.agents\\secrets\\enformation-cookies.txt\" -w \"%{http_code} %{redirect_url}\" --max-time 30 \"https:\u002F\u002Fz.e-nformation.ro\u002FPlatformaUnivBucsiBCUBuc\"`\n  A redirect to `www.e-nformation.ro\u002Fprofil-acces` means the session is DEAD; an in-proxy\n  2xx\u002Fredirect to a rewritten host means it is alive.\n- **Refresh procedure** (one careful attempt; never loop failed logins):\n  1. GET `https:\u002F\u002Fz.e-nformation.ro\u002FPlatformaUnivBucsiBCUBuc` with a fresh jar (`-c`), capture the 302 `_rwpReturn` URL.\n  2. GET the portal login page `https:\u002F\u002Fwww.e-nformation.ro\u002Fprofil-acces` (same jar), inspect the form fields.\n  3. POST the login form with `INSTITUTIONAL_EMAIL` \u002F `INSTITUTIONAL_PASSWORD` (values via env, never inline).\n  4. Follow the `_rwpReturn` redirect back to the proxy to mint `MuseProxySessionID`.\n  5. Verify with the one-line test, then save the jar atomically to the canonical path.\n- **Known outage**: on 2026-08-20 `www.e-nformation.ro` was TCP-unreachable (443 and 80,\n  confirmed from two networks) while `z.e-nformation.ro` stayed up. When the portal is down,\n  no refresh is possible — record `portal down, refresh blocked` and retry later instead of\n  hammering.\n- **Verified subscription map (2026-08-20, logged-in session)**: the app exposes ONE group\n  (\"Group 1, 35 subscribed\") whose working sourceIDs are: `Scopus_AnelisPlus`,\n  `ScienceDirect_AnelisPlus`, `WileyJournals_AnelisPlus`, `SpringerLink_AnelisPlus`,\n  `PQCentral_AnelisPlus`, `SAGEKnowledgeEbooks_AnelisPlus`, `ClarivateWoS_AnelisPlus`,\n  `iGLibraryALA_AnelisPlus`, `CabiDL_AnelisPlus`, `DeGruytereBooks_AnelisPlus`, plus unlisted\n  `Jstor`. Invalid sourceIDs return **502**. Cambridge Core, Project MUSE, Oxford Scholarship\n  and Taylor & Francis are NOT available: every name variant 502s, and a rewritten-host request\n  to `www-cambridge-org` gets bounced OUT of the proxy to the unproxied abstract page.\n- **Per-source limits verified with curl**:\n  - `SpringerLink_AnelisPlus` WORKS end-to-end; predictable PDFs at\n    `https:\u002F\u002Flink.springer.com\u002Fcontent\u002Fpdf\u002F{doi}.pdf` via `qurl` download cleanly.\n  - `DeGruytereBooks_AnelisPlus` covers only de Gruyter's own imprint — UC Press (10.1525) and\n    Rutgers (10.36019) titles return `\u002FunauthorizedDownload` (HTTP 202, 0 bytes).\n  - `Jstor` session authenticates, but JSTOR serves its JavaScript \"Client Challenge\" even\n    through the proxy — curl cannot download. **Working recipe (verified 2026-08-20):**\n    Playwright Chromium, HEADFUL (headless never clears the challenge), with\n    `--disable-blink-features=AutomationControlled` + `navigator.webdriver` masked, jar cookies\n    loaded via addCookies, enter via the `action=source&sourceID=Jstor` link, then download\n    PDFs with in-page `fetch` (same fingerprint). Scripts live in `Cowork\\scripts\\pw\\`\n    (`jstor-grab.js` and successors). ALWAYS verify the first PDF page (pdf-parse) against the\n    expected title — JSTOR search first-hits are often the WRONG article. JSTOR search hides\n    unlicensed content, so a title that never appears likely means \"not in UB's collections\".\n  - **UB JSTOR license limits (measured)**: journal archives incl. World Politics, BJHS,\n    J. History of Biology are licensed; **JSTOR ebooks are NOT** (chapters show\n    `preview_access`), and **BJPS + The Historical Journal are not in UB's collections**.\n  - `PQCentral_AnelisPlus` authenticates via a two-step handshake (openurl →\n    `intermediateredirectforezproxy` interstitial exposing `part1+part2` continuation +\n    `deleteCookiesEventUrl`; fire delete-cookies, then the continuation immediately — tokens\n    are single-use), but lands on a JS-only search UI; curl cannot reach docview\u002FPDF.\n  - `qurl` is clamped to the source's own domains; foreign URLs are silently replaced by the\n    source home page.\n- **Bot walls**: direct (unproxied) `www.jstor.org` serves a JavaScript client challenge to\n  curl even with valid cookies — and (verified) the challenge also fires through the proxy.\n- **Free-copy fallbacks that worked**: Early Modern Texts for public-domain classics\n  (Gutenberg's `files\u002F{id}\u002F{id}-pdf.pdf` often 404s); Unpaywall API\n  (`api.unpaywall.org\u002Fv2\u002F{doi}?email=...`) and Semantic Scholar\n  (`api.semanticscholar.org\u002Fgraph\u002Fv1\u002Fpaper\u002FDOI:{doi}?fields=openAccessPdf`) for OA sweeps;\n  ResearchGate hosts author copies but Cloudflare-403s curl.\n- Throttle 3–5 s between downloads; verify every \"PDF\" starts with `%PDF`; stop a platform\n  after repeated 403s.\n\n## Workflow\n\n1. Identify the exact resource and the entitlement lane: publisher site, aggregator, index, analytics platform, or repository.\n2. For E-nformation platforms, use the proxy recipe above with the canonical cookie jar; refresh the session if the test shows a login redirect.\n3. Route in order: institutional proxy\u002Fportal or federated access, publisher landing page, DOI resolver, OA discovery, repository copy, metadata-only fallback.\n4. Record access state precisely: `full text reachable`, `abstract only`, `citation only`, `analytics only`, or `not lawfully accessible`.\n5. Preserve provenance for every retrieved item: portal used, DOI, platform, date, and whether access depended on institutional entitlement.\n\n## Configuration and access\n\n- Store passwords ONLY as environment variables (`INSTITUTIONAL_EMAIL`, `INSTITUTIONAL_PASSWORD`); store session cookies ONLY in `C:\\Users\\Prekzursil\\.agents\\secrets\\`. Never print secret values, never commit them, never copy them into project folders or chat output.\n- Save stable references such as portal URLs, identity-provider names, ORCID iD, and environment-variable names.\n- The entitlement lane may include ACS, APS, CABI, CEEOL, Elsevier\u002FScienceDirect, Emerald, IEEE, IOP, JSTOR, MathSciNet, Nature, ProQuest, Reaxys, SAGE, SciVal, Scopus, Springer, Taylor and Francis, Web of Science, InCites, JCR, Derwent, Wiley, de Gruyter, Cambridge Core, Oxford, Project MUSE, and related E-nformation resources. Treat that list as a candidate access map to verify platform by platform.\n\n## Output standard\n\n- Lead with the best lawful access route.\n- State whether the result came from institutional access, open access, or metadata-only fallback.\n- If the item is not reachable, end with the next lawful path rather than vague encouragement.\n\n## Guardrails\n\n- Do not suggest Sci-Hub or pirated mirrors.\n- Session material lives ONLY in the canonical secrets location above (owner-sanctioned); treat any copy elsewhere as a leak to clean up.\n- One careful login attempt per refresh; if it fails twice, stop and report rather than risking an account lockout.\n- Distinguish user-provided entitlement assumptions from verified platform behavior.\n- If a platform exposes only analytics and not full text, say so explicitly.\n","# institutional-literature-access\n\nThis skill routes lawful institutional access for research literature. Treat the user-provided University of Bucharest and E-nformation entitlement list as data, not as blanket permission. Start with the legal access path, then fall back to DOI, OA, repository, and metadata-only routes.\n\n## When to use\n\n- The user has university, library, or consortium entitlements and needs the cleanest legal path to papers, books, or analytics platforms.\n- Access depends on an institutional portal, federated login, proxy\u002FVPN, ORCID sign-in, or registered researcher identity.\n- The workflow must remember configuration labels and the canonical secrets locations below; never scatter session material anywhere else.\n\n## E-nformation (Anelis Plus) proxy access — WORKING RECIPE\n\nThe owner (Miky) has an institutional account with e-nformation.ro (Anelis Plus consortium)\ncovering JSTOR, Cambridge Core, Oxford, Project MUSE, De Gruyter, Springer, T&F, Wiley, etc.\nThis access is owner-sanctioned for agent use. Verified facts (2026-08-20):\n\n- **Proxy**: MuseKnowledge Proxy at `https:\u002F\u002Fz.e-nformation.ro\u002F` (hostname-rewriting mode).\n- **Proxy URL pattern**: `{prefix}-y-https-{target-host-with-dashes}.z.e-nformation.ro`\n  e.g. `0511ar8cs-y-https-www-jstor-org.z.e-nformation.ro\u002Fstable\u002F...`\n  The `{prefix}` is minted per session; do not hardcode it. Cambridge Core would rewrite as\n  `...-y-https-www-cambridge-org.z.e-nformation.ro`.\n- **Proxy application ID**: `PlatformaUnivBucsiBCUBuc` (Univ. Bucharest + BCU Bucharest, groupID=1).\n  Entry point: `https:\u002F\u002Fz.e-nformation.ro\u002FPlatformaUnivBucsiBCUBuc`.\n- **Entering a target URL through the proxy** (once authenticated):\n  `https:\u002F\u002Fz.e-nformation.ro\u002FPlatformaUnivBucsiBCUBuc?groupID=1&action=source&sourceID={Source}&qurl={url-encoded target URL}`\n  (observed with `sourceID=Jstor`; the proxy then redirects to the rewritten `{prefix}-y-https-...` hostname).\n- **Auth flow**: the proxy 302-redirects unauthenticated requests to\n  `https:\u002F\u002Fwww.e-nformation.ro\u002Fprofil-acces?_rwpReturn=...&_rwpAppId=PlatformaUnivBucsiBCUBuc`.\n  Log in on the portal (WordPress-style) with the credentials below, then follow the\n  `_rwpReturn` redirect back to `z.e-nformation.ro` — this mints a fresh `MuseProxySessionID`\n  cookie on `.z.e-nformation.ro`. There is NO login form on the proxy itself (`\u002Flogon` is 404);\n  auth is fully delegated to the portal.\n- **Credentials**: environment variables `INSTITUTIONAL_EMAIL` and `INSTITUTIONAL_PASSWORD`\n  (set at both User and Machine scope). Names only here — never print the values.\n- **Canonical cookie jar**: `C:\\Users\\Prekzursil\\.agents\\secrets\\enformation-cookies.txt`\n  (Netscape format, used with `curl -b\u002F-c`). The `.agents\\secrets\\` directory is the ONLY\n  permitted location for session material; it is gitignored (`.agents\\.gitignore`) and must\n  never be committed or copied elsewhere.\n- **Cookie lifetimes**: `MuseProxySessionID` is a session cookie that expires server-side\n  within hours–a day; expect to refresh it. JSTOR `AccessPersist` cookies last ~1 month.\n- **One-line access test** (authenticated content vs login redirect):\n  `curl.exe -s -o NUL -b \"C:\\Users\\Prekzursil\\.agents\\secrets\\enformation-cookies.txt\" -w \"%{http_code} %{redirect_url}\" --max-time 30 \"https:\u002F\u002Fz.e-nformation.ro\u002FPlatformaUnivBucsiBCUBuc\"`\n  A redirect to `www.e-nformation.ro\u002Fprofil-acces` means the session is DEAD; an in-proxy\n  2xx\u002Fredirect to a rewritten host means it is alive.\n- **Refresh procedure** (one careful attempt; never loop failed logins):\n  1. GET `https:\u002F\u002Fz.e-nformation.ro\u002FPlatformaUnivBucsiBCUBuc` with a fresh jar (`-c`), capture the 302 `_rwpReturn` URL.\n  2. GET the portal login page `https:\u002F\u002Fwww.e-nformation.ro\u002Fprofil-acces` (same jar), inspect the form fields.\n  3. POST the login form with `INSTITUTIONAL_EMAIL` \u002F `INSTITUTIONAL_PASSWORD` (values via env, never inline).\n  4. Follow the `_rwpReturn` redirect back to the proxy to mint `MuseProxySessionID`.\n  5. Verify with the one-line test, then save the jar atomically to the canonical path.\n- **Known outage**: on 2026-08-20 `www.e-nformation.ro` was TCP-unreachable (443 and 80,\n  confirmed from two networks) while `z.e-nformation.ro` stayed up. When the portal is down,\n  no refresh is possible — record `portal down, refresh blocked` and retry later instead of\n  hammering.\n- **Verified subscription map (2026-08-20, logged-in session)**: the app exposes ONE group\n  (\"Group 1, 35 subscribed\") whose working sourceIDs are: `Scopus_AnelisPlus`,\n  `ScienceDirect_AnelisPlus`, `WileyJournals_AnelisPlus`, `SpringerLink_AnelisPlus`,\n  `PQCentral_AnelisPlus`, `SAGEKnowledgeEbooks_AnelisPlus`, `ClarivateWoS_AnelisPlus`,\n  `iGLibraryALA_AnelisPlus`, `CabiDL_AnelisPlus`, `DeGruytereBooks_AnelisPlus`, plus unlisted\n  `Jstor`. Invalid sourceIDs return **502**. Cambridge Core, Project MUSE, Oxford Scholarship\n  and Taylor & Francis are NOT available: every name variant 502s, and a rewritten-host request\n  to `www-cambridge-org` gets bounced OUT of the proxy to the unproxied abstract page.\n- **Per-source limits verified with curl**:\n  - `SpringerLink_AnelisPlus` WORKS end-to-end; predictable PDFs at\n    `https:\u002F\u002Flink.springer.com\u002Fcontent\u002Fpdf\u002F{doi}.pdf` via `qurl` download cleanly.\n  - `DeGruytereBooks_AnelisPlus` covers only de Gruyter's own imprint — UC Press (10.1525) and\n    Rutgers (10.36019) titles return `\u002FunauthorizedDownload` (HTTP 202, 0 bytes).\n  - `Jstor` session authenticates, but JSTOR serves its JavaScript \"Client Challenge\" even\n    through the proxy — curl cannot download. **Working recipe (verified 2026-08-20):**\n    Playwright Chromium, HEADFUL (headless never clears the challenge), with\n    `--disable-blink-features=AutomationControlled` + `navigator.webdriver` masked, jar cookies\n    loaded via addCookies, enter via the `action=source&sourceID=Jstor` link, then download\n    PDFs with in-page `fetch` (same fingerprint). Scripts live in `Cowork\\scripts\\pw\\`\n    (`jstor-grab.js` and successors). ALWAYS verify the first PDF page (pdf-parse) against the\n    expected title — JSTOR search first-hits are often the WRONG article. JSTOR search hides\n    unlicensed content, so a title that never appears likely means \"not in UB's collections\".\n  - **UB JSTOR license limits (measured)**: journal archives incl. World Politics, BJHS,\n    J. History of Biology are licensed; **JSTOR ebooks are NOT** (chapters show\n    `preview_access`), and **BJPS + The Historical Journal are not in UB's collections**.\n  - `PQCentral_AnelisPlus` authenticates via a two-step handshake (openurl →\n    `intermediateredirectforezproxy` interstitial exposing `part1+part2` continuation +\n    `deleteCookiesEventUrl`; fire delete-cookies, then the continuation immediately — tokens\n    are single-use), but lands on a JS-only search UI; curl cannot reach docview\u002FPDF.\n  - `qurl` is clamped to the source's own domains; foreign URLs are silently replaced by the\n    source home page.\n- **Bot walls**: direct (unproxied) `www.jstor.org` serves a JavaScript client challenge to\n  curl even with valid cookies — and (verified) the challenge also fires through the proxy.\n- **Free-copy fallbacks that worked**: Early Modern Texts for public-domain classics\n  (Gutenberg's `files\u002F{id}\u002F{id}-pdf.pdf` often 404s); Unpaywall API\n  (`api.unpaywall.org\u002Fv2\u002F{doi}?email=...`) and Semantic Scholar\n  (`api.semanticscholar.org\u002Fgraph\u002Fv1\u002Fpaper\u002FDOI:{doi}?fields=openAccessPdf`) for OA sweeps;\n  ResearchGate hosts author copies but Cloudflare-403s curl.\n- Throttle 3–5 s between downloads; verify every \"PDF\" starts with `%PDF`; stop a platform\n  after repeated 403s.\n\n## Workflow\n\n1. Identify the exact resource and the entitlement lane: publisher site, aggregator, index, analytics platform, or repository.\n2. For E-nformation platforms, use the proxy recipe above with the canonical cookie jar; refresh the session if the test shows a login redirect.\n3. Route in order: institutional proxy\u002Fportal or federated access, publisher landing page, DOI resolver, OA discovery, repository copy, metadata-only fallback.\n4. Record access state precisely: `full text reachable`, `abstract only`, `citation only`, `analytics only`, or `not lawfully accessible`.\n5. Preserve provenance for every retrieved item: portal used, DOI, platform, date, and whether access depended on institutional entitlement.\n\n## Configuration and access\n\n- Store passwords ONLY as environment variables (`INSTITUTIONAL_EMAIL`, `INSTITUTIONAL_PASSWORD`); store session cookies ONLY in `C:\\Users\\Prekzursil\\.agents\\secrets\\`. Never print secret values, never commit them, never copy them into project folders or chat output.\n- Save stable references such as portal URLs, identity-provider names, ORCID iD, and environment-variable names.\n- The entitlement lane may include ACS, APS, CABI, CEEOL, Elsevier\u002FScienceDirect, Emerald, IEEE, IOP, JSTOR, MathSciNet, Nature, ProQuest, Reaxys, SAGE, SciVal, Scopus, Springer, Taylor and Francis, Web of Science, InCites, JCR, Derwent, Wiley, de Gruyter, Cambridge Core, Oxford, Project MUSE, and related E-nformation resources. Treat that list as a candidate access map to verify platform by platform.\n\n## Output standard\n\n- Lead with the best lawful access route.\n- State whether the result came from institutional access, open access, or metadata-only fallback.\n- If the item is not reachable, end with the next lawful path rather than vague encouragement.\n\n## Guardrails\n\n- Do not suggest Sci-Hub or pirated mirrors.\n- Session material lives ONLY in the canonical secrets location above (owner-sanctioned); treat any copy elsewhere as a leak to clean up.\n- One careful login attempt per refresh; if it fails twice, stop and report rather than risking an account lockout.\n- Distinguish user-provided entitlement assumptions from verified platform behavior.\n- If a platform exposes only analytics and not full text, say so explicitly.\n",{"name":5,"description":7},"main","a298c929b6cbd662e1fce54302ce520d5ceea1a5",".agents\u002Fskills\u002Finstitutional-literature-access","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain","https:\u002F\u002Fgithub.com\u002FPrekzursil","2026-11-02 14:30:57",{"source":8,"skillName":5,"commands":50,"prompt":60,"zipAvailable":61},[51,54,57],{"tool":52,"command":53},"npx","npx skills add Prekzursil\u002Fagent-skills-toolchain --skill institutional-literature-access",{"tool":55,"command":56},"bunx","bunx skills add Prekzursil\u002Fagent-skills-toolchain --skill institutional-literature-access",{"tool":58,"command":59},"pnpm","pnpm dlx skills add Prekzursil\u002Fagent-skills-toolchain --skill institutional-literature-access","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Finstitutional-literature-access\u002FSKILL.md",true,[],[64,85,114,141,155,170],{"skillNo":65,"name":66,"nameZh":6,"description":67,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":68,"categories":69,"keywords":70,"publishedAt":38},"01M6DF7D7478R55P46REYH4QAC","clarify-requirements","Resolve genuine pre-execution ambiguity by scanning repo context, generating 1-6 grounded options, and asking 1-3 focused questions via AskUserQuestion. NOT for mid-task use (injection risk); NOT when the goal is already unambiguous; use to disambiguate vague prompts before any file edits.","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Fworkspace-hooks\u002Fskills\u002Fclarify-requirements\u002FSKILL.md",[],[71,72,73,74,75,76,77,78,79,32,80,81,82,83,84],"clarify requirements","clarify","requirements","risk","options","task","prompts","goal","scanning","context","repo","injection","execution","file",{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":94,"publishedAt":38},"01M6DF79CA4BHJS66J8EZDBPWJ","openmm-md","Run FREE, open-source, Windows-native GPU molecular dynamics via the openmm-md MCP (OpenMM + CUDA on the local NVIDIA GPU). Use for protein \u002F protein-ligand MD when you want a free stack or are on Windows without a Schrodinger license. Covers the full workflow (prepare, solvate, minimize, equilibrate, production, analyze, mmgbsa) AND an honest decision guide vs Schrodinger Desmond, including how to run Desmond legitimately on Linux or a cloud GPU with a real license. This is a deliberately LESSER free alternative and does NOT replace the schrodinger MCP tools. Do NOT use it to pick a free tool when a validated FEP+, WaterMap, IFD-MD, or Prime MM-GBSA result is actually required.","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Fmcp\u002Fopenmm-md-mcp\u002Fskill\u002Fopenmm-md\u002FSKILL.md",[91],{"categoryNo":92,"categoryName":93,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[95,96,97,98,99,100,101,102,103,104,105,106,107,108,32,109,110,111,112,113],"openmm md","how","decision","pick","linux","analyze","tool","stack","open","NVIDIA","gpu","license","workflow","windows","free","molecular dynamics","local","do","MCP",{"skillNo":115,"name":116,"nameZh":6,"description":117,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":118,"categories":119,"keywords":126,"publishedAt":38},"01M6DF76C1MG85VEWP8VZCBNMN","visual-review","Take screenshots of web pages and UI using Playwright for visual review and iteration","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fvisual-review\u002FSKILL.md",[120,123],{"categoryNo":121,"categoryName":122,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000003","演示文稿",{"categoryNo":124,"categoryName":125,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量",[127,128,129,130,131,132,133,134,135,136,96,137,138,139,140],"review","visual","visual review","pages","web","false","iteration","take","check","slides","ui","screenshot","playwright","screenshots",{"skillNo":142,"name":143,"nameZh":6,"description":144,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":145,"categories":146,"keywords":147,"publishedAt":38},"01M6DF73AQVCBZKEN0YXEX9FXP","status","Diagnostic status report — shows metaswarm installation state, project setup, and potential issues","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fstatus\u002FSKILL.md",[],[143,148,149,150,151,152,153,154],"setup","report","project","installation","project setup","issues","state",{"skillNo":156,"name":157,"nameZh":6,"description":158,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":159,"categories":160,"keywords":162,"publishedAt":38},"01M6DF6X6C2XB0P6GX76P7TTYV","start","Use when starting work on any task, when the user mentions metaswarm, or when the user wants to begin tracked development work","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fstart\u002FSKILL.md",[161],{"categoryNo":92,"categoryName":93,"taxonomyType":21,"taxonomyTypeDesc":22},[157,163,76,164,165,166,32,31,167,168,169],"start issue","issue","ready","work on issue","work","work on","development",{"skillNo":171,"name":148,"nameZh":6,"description":172,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":173,"categories":174,"keywords":175,"publishedAt":38},"01M6DF6QMJ9AJKFKHHKRT005PQ","Interactive project setup — detects your project, configures metaswarm, writes project-local files","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fsetup\u002FSKILL.md",[],[148,150,111,176,152,177],"files","interactive"]