[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6QGFGDH3EK9MVRGQCC9842Y":3,"skill-same:01M6QGFGDH3EK9MVRGQCC9842Y":82},{"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":26,"publishedAt":47,"linkOnly":48,"markdownContent":49,"markdownBody":50,"frontMatter":51,"refName":59,"commitSha":60,"skillDirectory":61,"forksCount":14,"repositoryHtmlUrl":62,"repositoryHomepageUrl":63,"ownerHtmlUrl":64,"ownerBlogUrl":65,"ownerDescription":66,"updatedAt":67,"install":68,"resources":81},"01M6QGFGDH3EK9MVRGQCC9842Y","bgpt-paper-search",null,"Searches BGPT scientific papers by topic or DOI and retrieves claim-level evidence extracted from full text, including experiments, reported statistics, scope, limitations, and provenance. Use for literature reviews, evidence synthesis, and finding experimental details beyond abstracts.","Tashima-Tarsh\u002FDisha6.6","Tashima-Tarsh","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F269906498?v=4","01M6PBH98X03XERH0HFT4PFB1P","NITISH KUMAR","01M6PBH9DA0M6KM3Z12P848F0K",0,"MIT","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkd-bgpt-paper-search\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000021","资料检索与研究","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46],"paper","paper search","bgpt paper search","search","scope","papers","reviews","internet","remote","scientific","doi","literature","access","MCP","api","statistics","claim","evidence synthesis","bridge","text","2026-11-10 10:12:30",false,"---\nname: bgpt-paper-search\ndescription: Searches BGPT scientific papers by topic or DOI and retrieves claim-level evidence extracted from full text, including experiments, reported statistics, scope, limitations, and provenance. Use for literature reviews, evidence synthesis, and finding experimental details beyond abstracts.\nlicense: MIT\ncompatibility: Requires a configured remote BGPT MCP connection and internet access to bgpt.pro. A stdio bridge additionally needs Node.js\u002Fnpm. Paid access requires a BGPT API key configured as an Authorization header.\nmetadata:\n  version: \"1.3\"\n  skill-author: BGPT\n  website: https:\u002F\u002Fbgpt.pro\u002Fmcp\u002F\n  last-reviewed: \"2026-09-30\"\ncategory: \"scientific-computing\"\n---\n\n# BGPT Paper Search\n\n## When to use\n\nUse BGPT to find full-text-derived evidence for a research question or a known\nDOI. It returns extracted claims and their supporting experiments, rather than\nonly bibliographic metadata. Use these records to build a traceable evidence\ntable; they are not a complete systematic-review search or a validated\nrisk-of-bias assessment.\n\n## Connect\n\nConfigure BGPT in the host before use; installing this skill does not register\nan MCP server. The provider supports both transports:\n\n| Transport | Endpoint |\n| --- | --- |\n| Streamable HTTP | `https:\u002F\u002Fbgpt.pro\u002Fmcp\u002Fstream` |\n| SSE | `https:\u002F\u002Fbgpt.pro\u002Fmcp\u002Fsse` |\n\nUse the host's native remote-MCP configuration when supported. For a host that\nuses `mcpServers` JSON and requires a local stdio bridge, this configuration uses\n`mcp-remote` (adapt it to the host's actual settings format):\n\n```json\n{\n  \"mcpServers\": {\n    \"bgpt\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"mcp-remote\", \"https:\u002F\u002Fbgpt.pro\u002Fmcp\u002Fstream\", \"--transport\", \"http-only\"]\n    }\n  }\n}\n```\n\nThe published `bgpt-mcp` 1.1.0 npm package is a thin SSE wrapper around\n`mcp-remote`, not a local paper database. Its bundled README predates the current\ntool contract and pricing. Prefer the native connection or configurable bridge\nabove. The linked BGPT GitHub repository was unavailable at review time; use\n[the current provider documentation](https:\u002F\u002Fbgpt.pro\u002Fmcp\u002F) and live tool schema.\n\nFree access needs no key. For paid usage, configure `Authorization: Bearer \u003Ckey>`\nin the host's remote-server headers, using its credential storage. For the bridge,\n[`mcp-remote` supports `--header-file`](https:\u002F\u002Fgithub.com\u002Fpunkpeye\u002Fmcp-remote#custom-headers)\nwith a local credential file. Do not put `api_key` in an MCP tool call: neither\ncurrent tool declares that argument. Authenticate through the connection.\n\n## Search and DOI lookup\n\nDiscover the connected server's tools before calling them. The live BGPT 2.14.7\nschema reviewed on 2026-09-30 exposes:\n\n| Tool \u002F argument | Contract |\n| --- | --- |\n| `search_papers.query` | Required string. Use short English search terms. |\n| `num_results` | Integer, 1–100; default 16. Set it explicitly to control result use. |\n| `days_back` | Optional integer; papers published within the last N days. Omit for all dates. |\n| `min_citations` | Optional integer; minimum number of **references cited by the paper**, not citations received. |\n| `study_type` | Optional string: `primary study`, `systematic review`, `meta-analysis`, `narrative review`, `protocol`, `dataset`, `commentary`, or `other`. |\n| `output_format` | `evidence` (default), `full`, or `legacy`. |\n| `lookup_paper.doi` | Required DOI string; also accepts `output_format`. A found paper counts as one result. |\n\nUse the filter arguments instead of putting years or filters into the query.\nNo Boolean-query grammar, offset, page, or cursor is documented by this schema.\nA result limit is not pagination: do not invent continuation arguments or claim\nthe search enumerates every matching paper. For broader coverage, run explicit\nquestion variants and deduplicate by DOI while retaining the query history.\n\nSearch example verified with one public result (invoke through the connected\ntool interface):\n\n```json\n{\"query\": \"CRISPR human cells\", \"num_results\": 1, \"output_format\": \"full\"}\n```\n\nIllustrative filtered search (filters were schema-checked, not executed):\n\n```json\n{\"query\": \"CRISPR delivery neurons\", \"num_results\": 5, \"days_back\": 90, \"study_type\": \"primary study\", \"output_format\": \"evidence\"}\n```\n\nFor a paper already identified, call `lookup_paper` with its bare DOI rather\nthan hoping a title search returns that exact paper:\n\n```json\n{\"doi\": \"10.1016\u002Fj.ymeth.2015.10.014\", \"output_format\": \"evidence\"}\n```\n\nDo not interpret a connection, quota, or tool error as an empty evidence set.\nThe provider publishes a result allowance, but no numeric request-rate limit\non the reviewed page; avoid assuming unlimited request throughput.\n\n## Read the result contract\n\nSearch returns an envelope with a `results` list and `count`; record the returned\n`query` too, since the service may rewrite search terms. DOI lookup returns `found`\nand a single `result`; handle not-found before reading it. Inspect the MCP\nresult for tool errors before interpreting the envelope.\n\n- `evidence` gives compact evidence records; empty optional fields may be absent.\n- `full` adds legacy paper metadata to the evidence record.\n- `legacy` requests the older paper metadata representation. Do not assume every\n  paper has all previously advertised fields or a quality score.\n\nThe provider says evidence\u002Ffull formats omit papers without extracted evidence.\nHowever, the live smoke test returned a record with `schema_version: \"legacy\"`,\n`extraction_status: \"legacy\"`, and an empty `evidence_units` list in both formats.\nA returned record therefore does not guarantee claim-level provenance. An empty\nsearch or unfound DOI also does not establish that the paper does not exist.\nRetain `doi`, `title`, `publication_date`, and `publication_name` when available,\nthen inspect `central_claim` and `evidence.evidence_units`. Each unit links its\nclaim to an experiment, reported statistics, demonstrated scope, and provenance.\nKeep the schema version: older records can have a different shape. Legacy full\nmetadata can contain nulls, numeric strings, and serialized text instead of\nnative lists; preserve the raw values and never execute them as code.\n\nThe provider documents V4 limits of five evidence units per record, two provenance\npassages per unit, and 320 characters per passage. These are bounded extractions,\nnot the complete article. Check `extraction_status`, `normalization_warnings`,\nand `evidence.record_provenance`, including truncation information, before synthesis.\n\n## Evidence checks\n\nFor each extracted result, retain the DOI and source section, table, or figure.\nVerify sample sizes, units, experimental arms, reported statistics, and uncertainty\nagainst the paper before using them in a synthesis. Distinguish author-reported\nlimitations from extraction-generated interpretations. Preserve contradictory\nor mixed evidence and demonstrated scope. If legacy quality scores are present,\nuse them only as screening aids, not as a study-specific risk-of-bias assessment.\n\n## Allowance and review scope\n\nAt the review date the provider advertises 50 free **results** per network,\nthen $0.02 per returned result. A successful DOI lookup counts as one result;\nunfound lookups cost none. Recheck the allowance and pricing before a large\nbatch. Do not repeatedly retry a quota-exhausted request.\n\nSources: [provider setup, record formats, and billing](https:\u002F\u002Fbgpt.pro\u002Fmcp\u002F),\n[live MCP endpoint](https:\u002F\u002Fbgpt.pro\u002Fmcp\u002Fstream),\n[published BGPT wrapper metadata](https:\u002F\u002Fregistry.npmjs.org\u002Fbgpt-mcp\u002Flatest),\nand [bridge documentation](https:\u002F\u002Fgithub.com\u002Fpunkpeye\u002Fmcp-remote).\nThe tool schemas, one-result full search, matching evidence-format DOI lookup,\nand SSE handshake were checked with unauthenticated requests. The public\nsearch\u002Flookup returned a legacy-schema record, not a V4 fixture. Paid\nauthentication, filtered search behavior, and host-specific configuration were\nnot tested.\n","# BGPT Paper Search\n\n## When to use\n\nUse BGPT to find full-text-derived evidence for a research question or a known\nDOI. It returns extracted claims and their supporting experiments, rather than\nonly bibliographic metadata. Use these records to build a traceable evidence\ntable; they are not a complete systematic-review search or a validated\nrisk-of-bias assessment.\n\n## Connect\n\nConfigure BGPT in the host before use; installing this skill does not register\nan MCP server. The provider supports both transports:\n\n| Transport | Endpoint |\n| --- | --- |\n| Streamable HTTP | `https:\u002F\u002Fbgpt.pro\u002Fmcp\u002Fstream` |\n| SSE | `https:\u002F\u002Fbgpt.pro\u002Fmcp\u002Fsse` |\n\nUse the host's native remote-MCP configuration when supported. For a host that\nuses `mcpServers` JSON and requires a local stdio bridge, this configuration uses\n`mcp-remote` (adapt it to the host's actual settings format):\n\n```json\n{\n  \"mcpServers\": {\n    \"bgpt\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"mcp-remote\", \"https:\u002F\u002Fbgpt.pro\u002Fmcp\u002Fstream\", \"--transport\", \"http-only\"]\n    }\n  }\n}\n```\n\nThe published `bgpt-mcp` 1.1.0 npm package is a thin SSE wrapper around\n`mcp-remote`, not a local paper database. Its bundled README predates the current\ntool contract and pricing. Prefer the native connection or configurable bridge\nabove. The linked BGPT GitHub repository was unavailable at review time; use\n[the current provider documentation](https:\u002F\u002Fbgpt.pro\u002Fmcp\u002F) and live tool schema.\n\nFree access needs no key. For paid usage, configure `Authorization: Bearer \u003Ckey>`\nin the host's remote-server headers, using its credential storage. For the bridge,\n[`mcp-remote` supports `--header-file`](https:\u002F\u002Fgithub.com\u002Fpunkpeye\u002Fmcp-remote#custom-headers)\nwith a local credential file. Do not put `api_key` in an MCP tool call: neither\ncurrent tool declares that argument. Authenticate through the connection.\n\n## Search and DOI lookup\n\nDiscover the connected server's tools before calling them. The live BGPT 2.14.7\nschema reviewed on 2026-09-30 exposes:\n\n| Tool \u002F argument | Contract |\n| --- | --- |\n| `search_papers.query` | Required string. Use short English search terms. |\n| `num_results` | Integer, 1–100; default 16. Set it explicitly to control result use. |\n| `days_back` | Optional integer; papers published within the last N days. Omit for all dates. |\n| `min_citations` | Optional integer; minimum number of **references cited by the paper**, not citations received. |\n| `study_type` | Optional string: `primary study`, `systematic review`, `meta-analysis`, `narrative review`, `protocol`, `dataset`, `commentary`, or `other`. |\n| `output_format` | `evidence` (default), `full`, or `legacy`. |\n| `lookup_paper.doi` | Required DOI string; also accepts `output_format`. A found paper counts as one result. |\n\nUse the filter arguments instead of putting years or filters into the query.\nNo Boolean-query grammar, offset, page, or cursor is documented by this schema.\nA result limit is not pagination: do not invent continuation arguments or claim\nthe search enumerates every matching paper. For broader coverage, run explicit\nquestion variants and deduplicate by DOI while retaining the query history.\n\nSearch example verified with one public result (invoke through the connected\ntool interface):\n\n```json\n{\"query\": \"CRISPR human cells\", \"num_results\": 1, \"output_format\": \"full\"}\n```\n\nIllustrative filtered search (filters were schema-checked, not executed):\n\n```json\n{\"query\": \"CRISPR delivery neurons\", \"num_results\": 5, \"days_back\": 90, \"study_type\": \"primary study\", \"output_format\": \"evidence\"}\n```\n\nFor a paper already identified, call `lookup_paper` with its bare DOI rather\nthan hoping a title search returns that exact paper:\n\n```json\n{\"doi\": \"10.1016\u002Fj.ymeth.2015.10.014\", \"output_format\": \"evidence\"}\n```\n\nDo not interpret a connection, quota, or tool error as an empty evidence set.\nThe provider publishes a result allowance, but no numeric request-rate limit\non the reviewed page; avoid assuming unlimited request throughput.\n\n## Read the result contract\n\nSearch returns an envelope with a `results` list and `count`; record the returned\n`query` too, since the service may rewrite search terms. DOI lookup returns `found`\nand a single `result`; handle not-found before reading it. Inspect the MCP\nresult for tool errors before interpreting the envelope.\n\n- `evidence` gives compact evidence records; empty optional fields may be absent.\n- `full` adds legacy paper metadata to the evidence record.\n- `legacy` requests the older paper metadata representation. Do not assume every\n  paper has all previously advertised fields or a quality score.\n\nThe provider says evidence\u002Ffull formats omit papers without extracted evidence.\nHowever, the live smoke test returned a record with `schema_version: \"legacy\"`,\n`extraction_status: \"legacy\"`, and an empty `evidence_units` list in both formats.\nA returned record therefore does not guarantee claim-level provenance. An empty\nsearch or unfound DOI also does not establish that the paper does not exist.\nRetain `doi`, `title`, `publication_date`, and `publication_name` when available,\nthen inspect `central_claim` and `evidence.evidence_units`. Each unit links its\nclaim to an experiment, reported statistics, demonstrated scope, and provenance.\nKeep the schema version: older records can have a different shape. Legacy full\nmetadata can contain nulls, numeric strings, and serialized text instead of\nnative lists; preserve the raw values and never execute them as code.\n\nThe provider documents V4 limits of five evidence units per record, two provenance\npassages per unit, and 320 characters per passage. These are bounded extractions,\nnot the complete article. Check `extraction_status`, `normalization_warnings`,\nand `evidence.record_provenance`, including truncation information, before synthesis.\n\n## Evidence checks\n\nFor each extracted result, retain the DOI and source section, table, or figure.\nVerify sample sizes, units, experimental arms, reported statistics, and uncertainty\nagainst the paper before using them in a synthesis. Distinguish author-reported\nlimitations from extraction-generated interpretations. Preserve contradictory\nor mixed evidence and demonstrated scope. If legacy quality scores are present,\nuse them only as screening aids, not as a study-specific risk-of-bias assessment.\n\n## Allowance and review scope\n\nAt the review date the provider advertises 50 free **results** per network,\nthen $0.02 per returned result. A successful DOI lookup counts as one result;\nunfound lookups cost none. Recheck the allowance and pricing before a large\nbatch. Do not repeatedly retry a quota-exhausted request.\n\nSources: [provider setup, record formats, and billing](https:\u002F\u002Fbgpt.pro\u002Fmcp\u002F),\n[live MCP endpoint](https:\u002F\u002Fbgpt.pro\u002Fmcp\u002Fstream),\n[published BGPT wrapper metadata](https:\u002F\u002Fregistry.npmjs.org\u002Fbgpt-mcp\u002Flatest),\nand [bridge documentation](https:\u002F\u002Fgithub.com\u002Fpunkpeye\u002Fmcp-remote).\nThe tool schemas, one-result full search, matching evidence-format DOI lookup,\nand SSE handshake were checked with unauthenticated requests. The public\nsearch\u002Flookup returned a legacy-schema record, not a V4 fixture. Paid\nauthentication, filtered search behavior, and host-specific configuration were\nnot tested.\n",{"name":5,"license":15,"category":52,"metadata":53,"description":7,"compatibility":58},"scientific-computing",{"version":54,"website":55,"skill-author":56,"last-reviewed":57},"1.3","https:\u002F\u002Fbgpt.pro\u002Fmcp\u002F","BGPT","2026-09-30","Requires a configured remote BGPT MCP connection and internet access to bgpt.pro. A stdio bridge additionally needs Node.js\u002Fnpm. Paid access requires a BGPT API key configured as an Authorization header.","main","0da4485785ee599388900be50db1635489d53056",".agents\u002Fskills\u002Fkd-bgpt-paper-search","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6","https:\u002F\u002Fdisha6.6.thenitishkr.in\u002F","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh","www.thenitishkr","thenitishkr | AI • Cyber-security • Research\r\n","2026-11-08 03:33:25",{"source":8,"skillName":5,"commands":69,"prompt":79,"zipAvailable":80},[70,73,76],{"tool":71,"command":72},"npx","npx skills add Tashima-Tarsh\u002FDisha6.6 --skill bgpt-paper-search",{"tool":74,"command":75},"bunx","bunx skills add Tashima-Tarsh\u002FDisha6.6 --skill bgpt-paper-search",{"tool":77,"command":78},"pnpm","pnpm dlx skills add Tashima-Tarsh\u002FDisha6.6 --skill bgpt-paper-search","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fkd-bgpt-paper-search\u002FSKILL.md",true,[],[83,112,137,162,187,211],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":92,"publishedAt":47},"01M6QRD07D4TGNDK6VJ4EHF8BV","youtube-full","Use when the user needs YouTube transcripts, video search, channel browsing, playlist extraction, or content monitoring. Trigger phrases: 'get the transcript for', 'search YouTube for', 'what are the latest videos on', 'list this playlist', 'monitor this channel', or any request involving a YouTube URL, video ID, or @handle. Do NOT use for downloading video or audio files, YouTube engagement data (likes, comments), or private\u002Fage-restricted videos.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fyoutube-full\u002FSKILL.md",[89],{"categoryNo":90,"categoryName":91,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000016","图像与多媒体",[93,94,95,96,30,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111],"youtube full","youtube","full","transcript","monitoring","data","Video","Audio","list","files","do","get","age","trigger","URL","for","browsing","request","youtube transcripts",{"skillNo":113,"name":114,"nameZh":6,"description":115,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":116,"categories":117,"keywords":118,"publishedAt":47},"01M6QRCJ3112VYPA97YG7KGMC2","x-twitter-growth","X\u002FTwitter growth engine for building audience, crafting viral content, and analyzing engagement. Use when the user wants to grow on X\u002FTwitter, write tweets or threads, analyze their X profile, research competitors on X, plan a posting strategy, or optimize engagement. Complements social-content (generic multi-platform) with X-specific depth: algorithm mechanics, thread engineering, reply strategy, profile optimization, and competitive intelligence via web search.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fx-twitter-growth\u002FSKILL.md",[],[119,120,121,122,30,123,124,125,126,127,128,129,130,131,132,133,134,135,136,108],"twitter","x twitter growth","growth","research","content","engineering","plan","web search","competitors","analyze","engine","write","strategy","use","platform","grow","posting","competitive",{"skillNo":138,"name":139,"nameZh":6,"description":140,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":141,"categories":142,"keywords":144,"publishedAt":47},"01M6QRBN3EHQNJY42RERP7A149","write-a-skill","Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, build, or author a new skill.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fwrite-a-skill\u002FSKILL.md",[143],{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[145,130,146,147,148,149,150,151,132,152,153,59,154,155,156,157,158,159,160,161],"write a skill","github","create","https","productivity","matt pocock","direct","example","build","new skill","structure","new agent","resources","with","tree","progressive disclosure","author",{"skillNo":163,"name":164,"nameZh":6,"description":165,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":166,"categories":167,"keywords":168,"publishedAt":47},"01M6QRB6G8P33PNGAF9Y69EJ9T","wrap-up","Close out a launched Claude Managed Agent — recap every primitive the founder now owns, regenerate the single-file overview page, and suggest the next 1-2 upgrades. Use when the user says \"wrap up\", \"close this out\", \"what do I own now\", \"give me the summary\", \"recap the agent\", or when the orchestrator routes phase=wrap-up. primitives_inventory.py tables everything owned (agent, environment, session, memory, outcome, deployment); overview_page.py regenerates a self-contained .\u002Fmy-agent\u002Fagent-overview.html; upgrade_suggester.py ranks the next moves from recorded deferrals plus standing hardening steps. Companion to run-without-you; the last stop before phase=done.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fwrap-up\u002FSKILL.md",[],[169,170,171,172,173,174,175,176,177,132,178,103,179,180,181,182,183,184,185,186],"wrap up","up","wrap","gemini","deployment","run","file","hardening","closeout","stop","upgrade","founder","close","companion","you","tables","directions","phase",{"skillNo":188,"name":189,"nameZh":6,"description":190,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":191,"categories":192,"keywords":194,"publishedAt":47},"01M6QRA5AYC1RBFZ39GTWGS3N8","workflow-builder","Design and write deterministic multi-agent workflow scripts (.js files in .claude\u002Fworkflows\u002F) for Claude Code's Workflow tool. Use when a user wants to build, create, author, scaffold, or run a custom Claude Code workflow, orchestrate sub-agents (fan-out, pipeline, loop, judge-panel), or automate a repeatable multi-step task across fresh-context agents.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fworkflow-builder\u002FSKILL.md",[193],{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},[195,196,197,198,199,147,174,200,201,202,203,204,130,205,102,206,207,208,209,210],"workflow","workflow builder","builder","design","workflows","code","orchestrate","pipeline","loop","multi-agent","context","across","fresh","scripts","judge","claude code workflow",{"skillNo":212,"name":213,"nameZh":6,"description":214,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":215,"categories":216,"keywords":217,"publishedAt":47},"01M6QR7QMCZESKQA0ERW1E657M","weekly-review","Use when someone wants to run a weekly review, close open loops, audit stalled projects and commitments, get their system back to trusted, restart a lapsed review habit, or says \"\u002Fcs:weekly-review\". Walks David Allen's three-phase loop — GET CLEAR, GET CURRENT, GET CREATIVE — with deterministic scripts that inventory open loops, gate the checklist with named gaps, and score commitment health 0-100.","https:\u002F\u002Fgithub.com\u002FTashima-Tarsh\u002FDisha6.6\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fweekly-review\u002FSKILL.md",[],[218,219,220,221,222,223,224,225,226,203,227,228,229,230,231,232,104,233,234,186],"review","weekly review","weekly","deterministic scripts","reflect","feeds","inventory","open","team","projects","project-management","scanner","conversation","back","project","sprint","cadence"]