[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7FDMN0VRXW0G92593BJ5DTS":3,"skill-same:01M7FDMN0VRXW0G92593BJ5DTS":55},{"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":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":24,"commitSha":25,"skillDirectory":26,"forksCount":14,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":6,"ownerDescription":29,"updatedAt":30,"install":31,"resources":44},"01M7FDMN0VRXW0G92593BJ5DTS","vista",null,"This skill should be used when the user asks about research directions, open problems, future work, or follow-up research from the academic literature. Trigger phrases include \"open problems in X\", \"what's next for Y\", \"future work for paper Z\", \"research directions on T\", \"salient follow-up research\", \"what should I work on next in\", \"find me follow-up research unrelated to my prior work\", \"broad survey of W\", \"neglected directions in V\". Routes the request to the right Vista MCP tool, reads back the structured paper sections, and synthesizes research directions in the conversation.","Abdulqudduz\u002Fclaude-anvil","Abdulqudduz","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F111210054?v=4","01M7FDCB600A6D0CXP9AZ75K5G","MAQGEEK","01M7FDCB6K7XH3DSTYWD1B4GVB",0,"MIT","https:\u002F\u002Fgithub.com\u002FAbdulqudduz\u002Fclaude-anvil\u002Fblob\u002Fmain\u002Fvista\u002Fskills\u002Fvista\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: vista\ndescription: This skill should be used when the user asks about research directions, open problems, future work, or follow-up research from the academic literature. Trigger phrases include \"open problems in X\", \"what's next for Y\", \"future work for paper Z\", \"research directions on T\", \"salient follow-up research\", \"what should I work on next in\", \"find me follow-up research unrelated to my prior work\", \"broad survey of W\", \"neglected directions in V\". Routes the request to the right Vista MCP tool, reads back the structured paper sections, and synthesizes research directions in the conversation.\n---\n\n# Vista\n\nVista surfaces *salient research directions* by reading the **Future Work**,\n**Limitations**, **Discussion**, and **Conclusion** sections of highly-cited\npapers. The MCP server does the mechanical work (OpenAlex search, PDF fetch,\nsection extraction, caching). This skill tells you when to call which MCP tool\nand how to synthesize the structured payload it returns.\n\n## Core principle\n\nThe MCP tools are **mechanical**. They return raw section text plus metadata.\nYou (Claude in this conversation) read the sections and produce the synthesis:\nranking, pattern detection, novelty assessment, cross-paper themes. Do not\nexpect the MCP to \"give you the answer\"; it gives you the inputs.\n\n## When to invoke which tool\n\nRead the user's question carefully and route:\n\n| User intent | Tool | Notes |\n|-------------|------|-------|\n| \"Open problems \u002F future work \u002F research directions in **a topic**\" | `topic_followups(topic, max_papers=8, year_min=2020, min_citations=30)` | Most common. Recent, highly-cited, arXiv-available. |\n| \"What does paper \u002F arXiv:1234.5678 \u002F DOI X say about future work?\" | `paper_followups(identifier)` | Single-paper deep-dive. Identifier can be DOI, arXiv id, OpenAlex id, or title. |\n| \"Older \u002F classical \u002F under-explored \u002F neglected directions in X\" | `find_seminal(topic, year_max=2019, min_citations=1000)` | Legacy track. The \"papers everyone cites but nobody followed up on.\" |\n| \"Broad \u002F cross-field \u002F serendipitous search; find directions outside my prior work\" | `broad_followups(query, fields=None, max_papers=12)` | Exploratory; looser thresholds; spans fields. |\n| \"Search the local catalog of distilled directions\" | `search_directions(query, ...)` | Use after a build run. Searches what the user has already mined. |\n| \"List interesting \u002F open \u002F started directions\" | `list_directions(...)` | Curation\u002Freview. |\n| \"Mark this direction as interesting\" | `mark_direction(direction_id, status, notes)` | User curation. |\n| \"Save these directions for paper X\" | `submit_directions(paper_id, directions)` | After you've synthesized directions, persist them so future runs can search them. Appends by default; curation is never lost. |\n| \"What papers \u002F directions \u002F fields are in the store?\" | `status()` or `run_sql(...)` | Inspection. |\n\nIf unsure: prefer `topic_followups` for topic questions and `paper_followups`\nfor paper questions. If the user wants breadth or surprise, use\n`broad_followups`. If the request mentions classical, neglected, or\n\"never-followed-up\", use `find_seminal`.\n\n## Synthesis pattern after a tool call\n\nEach on-demand tool returns `{..., \"papers\": [Paper, ...], \"paper_count\": N}`,\nwhere each Paper carries metadata, links, and a `sections` list of\n`{type, heading, method, content, char_count}` (`type` is one of\n`future_work`, `limitations`, `discussion`, `conclusion`). The full shapes\nare in `references\u002Foutput-shape.md`.\n\nFor each paper:\n\n1. Read the `future_work` section if present, else `limitations`, else\n   `discussion`\u002F`conclusion` (the latter often contain future-work prose\n   without a separate heading).\n2. Pull out **concrete, actionable** directions. Reject vague aspirations\n   (\"more experiments\", \"scale up\").\n3. For each, capture: a one-sentence direction, a one-line rationale grounded\n   in the section text, a short verbatim quote (substring of the section), and\n   tags (`[\"topic-keyword\", \"method-keyword\"]`).\n4. Estimate `feasibility` and `novelty` (low\u002Fmedium\u002Fhigh) based on the paper's\n   stated limits.\n\nThen synthesize across papers:\n\n- **Consensus directions**: themes that appear across 2 or more papers.\n- **Frontier directions**: novel, mentioned by one paper, well-supported.\n- **Conspicuous absences**: areas the user might expect to be flagged but\n  aren't (use sparingly; it's interpretive).\n- **Contradictions**: papers disagreeing on what to do next.\n\nPresent the synthesis with explicit citations to paper title and year, and\ninclude the arXiv or DOI URL so the user can drill in.\n\nIf the user wants the synthesized directions persisted, call\n`submit_directions(paper_id, directions)` per paper. The default\n`mode=\"append\"` adds new directions and updates ones with the same text in\nplace (keeping the user's status and notes, merging tags); pass\n`mode=\"replace\"` only to drop the paper's other uncurated directions.\nOtherwise leave the catalog alone, since the conversation answer is enough.\n\n`paper_followups` with a title accepts only an exact (normalized) title. If it\nreturns `\"error\": \"not found\"` with `candidates`, show them to the user or\nretry with the chosen candidate's `paper_id` (an OpenAlex id resolves free).\n\n## Defaults to nudge\n\n- For ML\u002FAI topics, `topic_followups` defaults are usually fine.\n- For statistics, drop `min_citations` to ~20 and set `require_arxiv=False`\n  (many top stats papers are not on arXiv).\n- For ransomware \u002F security, set `require_arxiv=False` and lean on\n  `min_citations=15`. USENIX\u002FNDSS papers are often OA but not arXiv.\n\n## When OpenAlex refuses\n\nIf a tool fails with `OpenAlexBudgetExhausted` (a 429 on a spent daily budget),\ndo not retry: it cannot succeed until the budget resets. Tell the user that\nkeyless OpenAlex access shares one small budget per IP, that a free key from\nhttps:\u002F\u002Fopenalex.org\u002Fsettings\u002Fapi raises it 10x, and that they need to\n`export OPENALEX_API_KEY=...` and restart Claude Code so the MCP server picks\nit up. Transient throttling (per-second 429s, 5xx) is retried automatically.\n\n## Output style\n\nDefault to a concise structured response: synthesis first, then a \"directions\ntable\" with paper, year, citation count, direction one-liner, and a link.\nOffer to drill into any direction. Do not paste raw section text back at the\nuser unless they ask for it.\n\n## Bulk \u002F pipeline workflows\n\nIf the user asks to **build a corpus** rather than ask an in-conversation\nquestion (e.g., \"set up a recurring sweep across all four fields\"), use the\nbulk tools (`discover`, `extract_pending`, `render_markdown`) or hand them\nback to the CLI: `vista pipeline --fields ml,ai,stats,ransomware --per-field 25`.\n\n## Additional resources\n\n- `references\u002Ftool-routing.md`: extended decision examples for picking the\n  right MCP tool from ambiguous user phrasings.\n- `references\u002Foutput-shape.md`: full JSON schema for each tool's response.\n","# Vista\n\nVista surfaces *salient research directions* by reading the **Future Work**,\n**Limitations**, **Discussion**, and **Conclusion** sections of highly-cited\npapers. The MCP server does the mechanical work (OpenAlex search, PDF fetch,\nsection extraction, caching). This skill tells you when to call which MCP tool\nand how to synthesize the structured payload it returns.\n\n## Core principle\n\nThe MCP tools are **mechanical**. They return raw section text plus metadata.\nYou (Claude in this conversation) read the sections and produce the synthesis:\nranking, pattern detection, novelty assessment, cross-paper themes. Do not\nexpect the MCP to \"give you the answer\"; it gives you the inputs.\n\n## When to invoke which tool\n\nRead the user's question carefully and route:\n\n| User intent | Tool | Notes |\n|-------------|------|-------|\n| \"Open problems \u002F future work \u002F research directions in **a topic**\" | `topic_followups(topic, max_papers=8, year_min=2020, min_citations=30)` | Most common. Recent, highly-cited, arXiv-available. |\n| \"What does paper \u002F arXiv:1234.5678 \u002F DOI X say about future work?\" | `paper_followups(identifier)` | Single-paper deep-dive. Identifier can be DOI, arXiv id, OpenAlex id, or title. |\n| \"Older \u002F classical \u002F under-explored \u002F neglected directions in X\" | `find_seminal(topic, year_max=2019, min_citations=1000)` | Legacy track. The \"papers everyone cites but nobody followed up on.\" |\n| \"Broad \u002F cross-field \u002F serendipitous search; find directions outside my prior work\" | `broad_followups(query, fields=None, max_papers=12)` | Exploratory; looser thresholds; spans fields. |\n| \"Search the local catalog of distilled directions\" | `search_directions(query, ...)` | Use after a build run. Searches what the user has already mined. |\n| \"List interesting \u002F open \u002F started directions\" | `list_directions(...)` | Curation\u002Freview. |\n| \"Mark this direction as interesting\" | `mark_direction(direction_id, status, notes)` | User curation. |\n| \"Save these directions for paper X\" | `submit_directions(paper_id, directions)` | After you've synthesized directions, persist them so future runs can search them. Appends by default; curation is never lost. |\n| \"What papers \u002F directions \u002F fields are in the store?\" | `status()` or `run_sql(...)` | Inspection. |\n\nIf unsure: prefer `topic_followups` for topic questions and `paper_followups`\nfor paper questions. If the user wants breadth or surprise, use\n`broad_followups`. If the request mentions classical, neglected, or\n\"never-followed-up\", use `find_seminal`.\n\n## Synthesis pattern after a tool call\n\nEach on-demand tool returns `{..., \"papers\": [Paper, ...], \"paper_count\": N}`,\nwhere each Paper carries metadata, links, and a `sections` list of\n`{type, heading, method, content, char_count}` (`type` is one of\n`future_work`, `limitations`, `discussion`, `conclusion`). The full shapes\nare in `references\u002Foutput-shape.md`.\n\nFor each paper:\n\n1. Read the `future_work` section if present, else `limitations`, else\n   `discussion`\u002F`conclusion` (the latter often contain future-work prose\n   without a separate heading).\n2. Pull out **concrete, actionable** directions. Reject vague aspirations\n   (\"more experiments\", \"scale up\").\n3. For each, capture: a one-sentence direction, a one-line rationale grounded\n   in the section text, a short verbatim quote (substring of the section), and\n   tags (`[\"topic-keyword\", \"method-keyword\"]`).\n4. Estimate `feasibility` and `novelty` (low\u002Fmedium\u002Fhigh) based on the paper's\n   stated limits.\n\nThen synthesize across papers:\n\n- **Consensus directions**: themes that appear across 2 or more papers.\n- **Frontier directions**: novel, mentioned by one paper, well-supported.\n- **Conspicuous absences**: areas the user might expect to be flagged but\n  aren't (use sparingly; it's interpretive).\n- **Contradictions**: papers disagreeing on what to do next.\n\nPresent the synthesis with explicit citations to paper title and year, and\ninclude the arXiv or DOI URL so the user can drill in.\n\nIf the user wants the synthesized directions persisted, call\n`submit_directions(paper_id, directions)` per paper. The default\n`mode=\"append\"` adds new directions and updates ones with the same text in\nplace (keeping the user's status and notes, merging tags); pass\n`mode=\"replace\"` only to drop the paper's other uncurated directions.\nOtherwise leave the catalog alone, since the conversation answer is enough.\n\n`paper_followups` with a title accepts only an exact (normalized) title. If it\nreturns `\"error\": \"not found\"` with `candidates`, show them to the user or\nretry with the chosen candidate's `paper_id` (an OpenAlex id resolves free).\n\n## Defaults to nudge\n\n- For ML\u002FAI topics, `topic_followups` defaults are usually fine.\n- For statistics, drop `min_citations` to ~20 and set `require_arxiv=False`\n  (many top stats papers are not on arXiv).\n- For ransomware \u002F security, set `require_arxiv=False` and lean on\n  `min_citations=15`. USENIX\u002FNDSS papers are often OA but not arXiv.\n\n## When OpenAlex refuses\n\nIf a tool fails with `OpenAlexBudgetExhausted` (a 429 on a spent daily budget),\ndo not retry: it cannot succeed until the budget resets. Tell the user that\nkeyless OpenAlex access shares one small budget per IP, that a free key from\nhttps:\u002F\u002Fopenalex.org\u002Fsettings\u002Fapi raises it 10x, and that they need to\n`export OPENALEX_API_KEY=...` and restart Claude Code so the MCP server picks\nit up. Transient throttling (per-second 429s, 5xx) is retried automatically.\n\n## Output style\n\nDefault to a concise structured response: synthesis first, then a \"directions\ntable\" with paper, year, citation count, direction one-liner, and a link.\nOffer to drill into any direction. Do not paste raw section text back at the\nuser unless they ask for it.\n\n## Bulk \u002F pipeline workflows\n\nIf the user asks to **build a corpus** rather than ask an in-conversation\nquestion (e.g., \"set up a recurring sweep across all four fields\"), use the\nbulk tools (`discover`, `extract_pending`, `render_markdown`) or hand them\nback to the CLI: `vista pipeline --fields ml,ai,stats,ransomware --per-field 25`.\n\n## Additional resources\n\n- `references\u002Ftool-routing.md`: extended decision examples for picking the\n  right MCP tool from ambiguous user phrasings.\n- `references\u002Foutput-shape.md`: full JSON schema for each tool's response.\n",{"name":5,"description":7},"main","f6f3133da90d79585262853f985437619b96f30d","vista\u002Fskills\u002Fvista","https:\u002F\u002Fgithub.com\u002FAbdulqudduz\u002Fclaude-anvil","https:\u002F\u002Fgithub.com\u002FAbdulqudduz","Hi there! 👋\r\nI'm Muhammed Abdulquddus, a software developer passionate about Flutter and Python, based in Abuja, Nigeria.","2026-10-23 13:31:03",{"source":8,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add Abdulqudduz\u002Fclaude-anvil --skill vista",{"tool":37,"command":38},"bunx","bunx skills add Abdulqudduz\u002Fclaude-anvil --skill vista",{"tool":40,"command":41},"pnpm","pnpm dlx skills add Abdulqudduz\u002Fclaude-anvil --skill vista","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FAbdulqudduz\u002Fclaude-anvil\u002Fblob\u002Fmain\u002Fvista\u002Fskills\u002Fvista\u002FSKILL.md",true,[45,51],{"path":46,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":49,"sourceHtmlUrl":50},"references\u002Foutput-shape.md","REFERENCE","参考文档",4858,"https:\u002F\u002Fgithub.com\u002FAbdulqudduz\u002Fclaude-anvil\u002Fblob\u002Fmain\u002Fvista\u002Fskills\u002Fvista\u002Freferences\u002Foutput-shape.md",{"path":52,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":53,"sourceHtmlUrl":54},"references\u002Ftool-routing.md",3038,"https:\u002F\u002Fgithub.com\u002FAbdulqudduz\u002Fclaude-anvil\u002Fblob\u002Fmain\u002Fvista\u002Fskills\u002Fvista\u002Freferences\u002Ftool-routing.md",[56,63,70,77,84,91],{"skillNo":57,"name":58,"nameZh":6,"description":59,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":60,"categories":61,"keywords":62,"publishedAt":19},"01M7FDMZAFJXWE6EQJRZE0RQCA","worldsmith-methodology","Use when working in a project with a worldbuilding documentation ecosystem (docs\u002F or lore\u002F directory). Provides the documentation-first methodology: canonical hierarchy, doc roles (timeline, lore, characters, systems), propagation discipline, and the dual canonical and exploratory workflow.","https:\u002F\u002Fgithub.com\u002FAbdulqudduz\u002Fclaude-anvil\u002Fblob\u002Fmain\u002Fworldsmith\u002Fskills\u002Fworldsmith-methodology\u002FSKILL.md",[],[],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":69,"publishedAt":19},"01M7FDMTEXZNE8RXCTCJVXFE4P","prose-craft","Use when writing fiction, editing fiction prose, reviewing chapters, or drafting scenes. Covers prose craft, dialogue mechanics, scene structure, and common failure modes in AI-assisted fiction. Trigger phrases: \"write fiction\", \"edit chapter\", \"prose review\", \"scene draft\", \"dialogue check\", \"fiction craft\", \"edit this scene\", \"review my prose\".","https:\u002F\u002Fgithub.com\u002FAbdulqudduz\u002Fclaude-anvil\u002Fblob\u002Fmain\u002Fworldsmith\u002Fskills\u002Fprose-craft\u002FSKILL.md",[],[],{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":19},"01M7FDMHKJX5F49JEGRPZXWQH9","synthesize","Make a research-agent run conclude and write synthesis.md (outcome, key findings, failed approaches, open questions, recommendations). Signals a live researcher to wrap up, or launches one in synthesis mode when none is running. Use when results are good enough or the agent is stalling.","https:\u002F\u002Fgithub.com\u002FAbdulqudduz\u002Fclaude-anvil\u002Fblob\u002Fmain\u002Fresearch-agent\u002Fskills\u002Fsynthesize\u002FSKILL.md",[],[],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":19},"01M7FDMDJT58GYN0YHMWPH3RH5","status","Show the current state of a research-agent run from .research\u002F: liveness, cycles and budget, sub-problem and hypothesis statuses, eval trend, current focus, and branches. Read-only.","https:\u002F\u002Fgithub.com\u002FAbdulqudduz\u002Fclaude-anvil\u002Fblob\u002Fmain\u002Fresearch-agent\u002Fskills\u002Fstatus\u002FSKILL.md",[],[],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":19},"01M7FDM90XM3H52XNDNKBB5SAP","resume","Resume an interrupted research-agent run from .research\u002F. Re-launches the researcher to reload its structured state and continue from the current focus, optionally on a named branch or with a new budget. Use after a session restart, crash, or explicit pause.","https:\u002F\u002Fgithub.com\u002FAbdulqudduz\u002Fclaude-anvil\u002Fblob\u002Fmain\u002Fresearch-agent\u002Fskills\u002Fresume\u002FSKILL.md",[],[],{"skillNo":92,"name":93,"nameZh":6,"description":94,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":95,"categories":96,"keywords":97,"publishedAt":19},"01M7FDM4XB6CP8VTNVYWKG93KF","research","Launch an autonomous research agent that iterates toward a goal through proofs, code, simulations, tests, and counterexample search. Fire-and-forget: the agent runs on its own and writes all results to .research\u002F in the target project.","https:\u002F\u002Fgithub.com\u002FAbdulqudduz\u002Fclaude-anvil\u002Fblob\u002Fmain\u002Fresearch-agent\u002Fskills\u002Fresearch\u002FSKILL.md",[],[]]