[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7FDM4XB6CP8VTNVYWKG93KF":3,"skill-same:01M7FDM4XB6CP8VTNVYWKG93KF":46},{"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":25,"commitSha":26,"skillDirectory":27,"forksCount":14,"repositoryHtmlUrl":28,"repositoryHomepageUrl":6,"ownerHtmlUrl":29,"ownerBlogUrl":6,"ownerDescription":30,"updatedAt":31,"install":32,"resources":45},"01M7FDM4XB6CP8VTNVYWKG93KF","research",null,"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.","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\u002Fresearch-agent\u002Fskills\u002Fresearch\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: research\ndescription: >-\n  Launch an autonomous research agent that iterates toward a goal through\n  proofs, code, simulations, tests, and counterexample search.\n  Fire-and-forget: the agent runs on its own and writes all results to\n  .research\u002F in the target project.\nargument-hint: \"\u003Cgoal> [eval script at \u003Cpath>] [budget: N cycles, H hours]\"\n---\n\n# Autonomous Research Agent\n\nLaunch the researcher on: $ARGUMENTS\n\n## Step 1: Parse the Request\n\nExtract from the arguments (or the user's message):\n\n1. **Goal** (required): the natural-language research objective, the main content of the request.\n2. **Eval script** (optional): a path to an executable script (\"eval script at ...\", \"use ... as eval\", or a path ending in `.sh`, `.py`, or similar).\n3. **Budget** (optional): a cycle cap and\u002For a wall-clock cap (\"at most 30 cycles\", \"stop after 4 hours\"). Omitted means unbounded; the agent still concludes on its own stall rule.\n\nIf the goal is unclear, ask the user to clarify before proceeding. If no eval script is mentioned, the agent self-evaluates.\n\n## Step 2: Verify Eval Script (if provided)\n\nVerify the path exists (Read tool). If it does not, tell the user and ask whether to proceed with self-evaluation instead.\n\n## Step 3: Check for an Existing Run\n\nIf `.research\u002F` exists in this directory (Glob tool), do not launch fresh:\n\n- Read `.research\u002Frun.json` if present. The run is **live** when `status` is `running` or `stopping` and `heartbeat` is less than `stale_after_minutes` old (compare against `date -u +%Y-%m-%dT%H:%M:%SZ`). If live, refuse: another researcher is working here. Point at `\u002Fresearch-agent:status` and `\u002Fresearch-agent:synthesize`. Never archive a live run.\n- Otherwise offer `\u002Fresearch-agent:resume` to continue it, or archiving it before starting fresh. Archive only on the user's explicit confirmation, with Bash: `mkdir -p .research-archive && mv .research .research-archive\u002F\u003CUTC-timestamp>`.\n\nThe agent itself refuses to start a fresh run on top of an existing `.research\u002F`.\n\n## Step 4: Launch the Agent\n\nSpawn the researcher (Agent tool, `subagent_type: research-agent:researcher`) with:\n\n    \u003Cgoal>\n    {the user's research goal, verbatim}\n    \u003C\u002Fgoal>\n\n    \u003Ceval>\n    {path to eval script, or \"none - use self-evaluation\"}\n    \u003C\u002Feval>\n\n    \u003Cbudget max_cycles=\"{N}\" max_hours=\"{H}\"\u002F>   (omit the tag, or either attribute, when not given)\n\n    \u003Cworking_directory>\n    {absolute path to current working directory}\n    \u003C\u002Fworking_directory>\n\n    Begin your research per your fresh-mode initialization.\n\nThen inform the user:\n\n> Research agent launched. It works autonomously in this directory, writing progress to `.research\u002F`. When it finishes, the synthesis will be at `.research\u002Fsynthesis.md`.\n>\n> While it runs:\n> - `\u002Fresearch-agent:status` shows cycle progress, current focus, budget, and eval trend (read-only)\n> - `\u002Fresearch-agent:synthesize` asks it to wrap up and write the synthesis now\n> - `\u002Fresearch-agent:resume` continues the run after an interruption or session restart\n> - `\u002Fresearch-agent:branch \u003Cname> [focus]` forks a competing strategy\n","# Autonomous Research Agent\n\nLaunch the researcher on: $ARGUMENTS\n\n## Step 1: Parse the Request\n\nExtract from the arguments (or the user's message):\n\n1. **Goal** (required): the natural-language research objective, the main content of the request.\n2. **Eval script** (optional): a path to an executable script (\"eval script at ...\", \"use ... as eval\", or a path ending in `.sh`, `.py`, or similar).\n3. **Budget** (optional): a cycle cap and\u002For a wall-clock cap (\"at most 30 cycles\", \"stop after 4 hours\"). Omitted means unbounded; the agent still concludes on its own stall rule.\n\nIf the goal is unclear, ask the user to clarify before proceeding. If no eval script is mentioned, the agent self-evaluates.\n\n## Step 2: Verify Eval Script (if provided)\n\nVerify the path exists (Read tool). If it does not, tell the user and ask whether to proceed with self-evaluation instead.\n\n## Step 3: Check for an Existing Run\n\nIf `.research\u002F` exists in this directory (Glob tool), do not launch fresh:\n\n- Read `.research\u002Frun.json` if present. The run is **live** when `status` is `running` or `stopping` and `heartbeat` is less than `stale_after_minutes` old (compare against `date -u +%Y-%m-%dT%H:%M:%SZ`). If live, refuse: another researcher is working here. Point at `\u002Fresearch-agent:status` and `\u002Fresearch-agent:synthesize`. Never archive a live run.\n- Otherwise offer `\u002Fresearch-agent:resume` to continue it, or archiving it before starting fresh. Archive only on the user's explicit confirmation, with Bash: `mkdir -p .research-archive && mv .research .research-archive\u002F\u003CUTC-timestamp>`.\n\nThe agent itself refuses to start a fresh run on top of an existing `.research\u002F`.\n\n## Step 4: Launch the Agent\n\nSpawn the researcher (Agent tool, `subagent_type: research-agent:researcher`) with:\n\n    \u003Cgoal>\n    {the user's research goal, verbatim}\n    \u003C\u002Fgoal>\n\n    \u003Ceval>\n    {path to eval script, or \"none - use self-evaluation\"}\n    \u003C\u002Feval>\n\n    \u003Cbudget max_cycles=\"{N}\" max_hours=\"{H}\"\u002F>   (omit the tag, or either attribute, when not given)\n\n    \u003Cworking_directory>\n    {absolute path to current working directory}\n    \u003C\u002Fworking_directory>\n\n    Begin your research per your fresh-mode initialization.\n\nThen inform the user:\n\n> Research agent launched. It works autonomously in this directory, writing progress to `.research\u002F`. When it finishes, the synthesis will be at `.research\u002Fsynthesis.md`.\n>\n> While it runs:\n> - `\u002Fresearch-agent:status` shows cycle progress, current focus, budget, and eval trend (read-only)\n> - `\u002Fresearch-agent:synthesize` asks it to wrap up and write the synthesis now\n> - `\u002Fresearch-agent:resume` continues the run after an interruption or session restart\n> - `\u002Fresearch-agent:branch \u003Cname> [focus]` forks a competing strategy\n",{"name":5,"description":7,"argument-hint":24},"\u003Cgoal> [eval script at \u003Cpath>] [budget: N cycles, H hours]","main","f6f3133da90d79585262853f985437619b96f30d","research-agent\u002Fskills\u002Fresearch","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":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add Abdulqudduz\u002Fclaude-anvil --skill research",{"tool":38,"command":39},"bunx","bunx skills add Abdulqudduz\u002Fclaude-anvil --skill research",{"tool":41,"command":42},"pnpm","pnpm dlx skills add Abdulqudduz\u002Fclaude-anvil --skill research","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FAbdulqudduz\u002Fclaude-anvil\u002Fblob\u002Fmain\u002Fresearch-agent\u002Fskills\u002Fresearch\u002FSKILL.md",true,[],[47,54,61,68,75,82],{"skillNo":48,"name":49,"nameZh":6,"description":50,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":51,"categories":52,"keywords":53,"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":55,"name":56,"nameZh":6,"description":57,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":58,"categories":59,"keywords":60,"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":62,"name":63,"nameZh":6,"description":64,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":65,"categories":66,"keywords":67,"publishedAt":19},"01M7FDMN0VRXW0G92593BJ5DTS","vista","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.","https:\u002F\u002Fgithub.com\u002FAbdulqudduz\u002Fclaude-anvil\u002Fblob\u002Fmain\u002Fvista\u002Fskills\u002Fvista\u002FSKILL.md",[],[],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"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":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"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":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"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",[],[]]