[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6PCYXKT27EVJA3W4R5GHMFV":3,"skill-same:01M6PCYXKT27EVJA3W4R5GHMFV":75},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":22,"publishedAt":43,"linkOnly":44,"markdownContent":45,"markdownBody":46,"frontMatter":47,"refName":32,"commitSha":57,"skillDirectory":58,"forksCount":13,"repositoryHtmlUrl":59,"repositoryHomepageUrl":6,"ownerHtmlUrl":60,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":61,"install":62,"resources":74},"01M6PCYXKT27EVJA3W4R5GHMFV","run-deep-swe",null,"Run reproducible DeepSWE coding-agent benchmark evaluations through OpenRouter and mini-swe-agent.","duc-duy-1612\u002FOnline-Delivery-Systems-Web","duc-duy-1612","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F192231384?v=4","01M6NSDKQQDKVTHZ8DZMZ1VYY6","01M6NSDKW8DDVTQHBT1HBDDJPT",0,"MIT","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Frun-deep-swe\u002FSKILL.md",[17],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42],"run","SWE","run deep swe","deep","agent-evaluation","agent benchmark","true","deepswe","critical","main","community","github","Coding-Agent","openrouter","Reproducible","Evaluation","https","license","benchmark","codex","2026-11-10 10:12:30",false,"---\nname: run-deep-swe\ndescription: \"Run reproducible DeepSWE coding-agent benchmark evaluations through OpenRouter and mini-swe-agent.\"\ncategory: agent-evaluation\nrisk: critical\nsource: community\nsource_repo: davidondrej\u002Fskills\nsource_type: community\ndate_added: \"2026-07-07\"\nauthor: davidondrej\ntags: [benchmark, deepswe, openrouter, evaluation]\ntools: [claude, codex]\nlicense: \"MIT\"\nlicense_source: \"https:\u002F\u002Fgithub.com\u002Fdavidondrej\u002Fskills\u002Fblob\u002Fmain\u002FLICENSE\"\ndisable-model-invocation: true\n---\n\n# Run DeepSWE via OpenRouter\n\n## When to Use\n\n- Use when the user wants to benchmark a model on DeepSWE or mini-swe-agent tasks.\n- Use when you need a reproducible coding-agent evaluation plan and output artifacts.\n\nDeepSWE (deepswe.datacurve.ai) is a 113-task Harbor-compatible coding-agent benchmark. It runs via **Pier** (Harbor fork) driving **mini-swe-agent** (model-agnostic). Any model reachable through OpenRouter can be scored.\n\n## Prerequisites — state-check first\n\n```bash\nwhich uv git docker || echo \"MISSING: install uv, git, docker\"\ndocker info >\u002Fdev\u002Fnull 2>&1 || echo \"MISSING: Docker daemon not running (Pier's default sandbox)\"\necho \"OPENROUTER_API_KEY set? ${OPENROUTER_API_KEY:+YES}\"\n```\n\n**Docker must be running** — Pier sandboxes each task in Docker by default (`--env modal` for cloud instead).\n\n`OPENROUTER_API_KEY` must already be present in the environment. If it is unset,\nask the user to configure their preferred secret-management path; do not read\nshell startup files, print secrets, or invent a key.\n\n## Setup\n\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002Fdatacurve-ai\u002Fdeep-swe && cd deep-swe\nuv tool install datacurve-pier            # PyPI (preferred)\n# or: uv tool install git+https:\u002F\u002Fgithub.com\u002Fdatacurve-ai\u002Fpier\n# pier bundles mini-swe-agent as the --agent driver\n```\n\nRun all `pier` commands from inside `deep-swe\u002F`, using relative `-p tasks\u002F...`.\n\n## OpenRouter wiring (the part the docs don't spell out)\n\nmini-swe-agent has a native OpenRouter model class. Both routes below use `OPENROUTER_API_KEY` and the OpenRouter slug (`vendor\u002Fmodel`, e.g. `minimax\u002Fminimax-m3`):\n\n**Route A — native OpenRouter class (preferred, hits openrouter.ai\u002Fapi\u002Fv1 directly):**\n```bash\npier run -p deep-swe\u002Ftasks --agent mini-swe-agent \\\n  --model minimax\u002Fminimax-m3 --model-class openrouter\n```\n\n**Route B — LiteLLM provider prefix (fallback; same key):**\n```bash\npier run -p deep-swe\u002Ftasks --agent mini-swe-agent \\\n  --model openrouter\u002Fminimax\u002Fminimax-m3\n```\n\nNotes:\n- Slug = the exact OpenRouter slug. Verify it at openrouter.ai\u002Fmodels before running.\n- Free\u002Fzero-cost models: OpenRouter cost tracking can error. Set `export MSWEA_COST_TRACKING=ignore_errors`.\n- Flag spelling can vary by version — confirm with `pier run --help` and `mini --help`.\n\n## Smoke test FIRST (1 task — do this before any full run)\n\nAlways validate end-to-end wiring on a single task before spending tokens on the corpus:\n\n```bash\npier run -p deep-swe\u002Ftasks\u002F\u003Ctask-id> --agent mini-swe-agent \\\n  --model minimax\u002Fminimax-m3 --model-class openrouter\n# list available task ids:\nls deep-swe\u002Ftasks\n```\n\nPass criteria: run completes, model returns actions (not auth\u002Fformat errors), a score\u002Ftrajectory is emitted. If it 401s → key wrong. If \"provider not provided\"\u002F\"model not mapped\" → fix slug or switch route.\n\n## Subset run (deterministic sample)\n\n```bash\npier run -p deep-swe\u002Ftasks --agent mini-swe-agent \\\n  --model minimax\u002Fminimax-m3 --model-class openrouter \\\n  --n-tasks 10 --sample-seed 0\n```\n\n## Full 113-task corpus (costs tokens + time — confirm with user first)\n\n```bash\npier run -p deep-swe\u002Ftasks --agent mini-swe-agent \\\n  --model minimax\u002Fminimax-m3 --model-class openrouter\n# add `--env modal` to run in parallel Modal sandboxes (needs Modal configured)\n```\n\n## Output & leaderboard\n\n- Trials land in `jobs\u002F\u003Crun>\u002F\u003Ctrial_id>\u002F`. Inspect with `pier view jobs\u002F\u003Crun>`, `pier analyze jobs\u002F\u003Crun>`, or `pier critique run jobs\u002F\u003Crun>`.\n- Report: the exact command used, pass\u002Ffail, score, and any blockers.\n- Submit results for the official leaderboard to: **\u003Cemail-address>**\n\n## Failure modes\n\n| Symptom | Cause | Fix |\n|---|---|---|\n| HTTP 401 | bad\u002Fmissing key | re-export `OPENROUTER_API_KEY` |\n| \"LLM Provider NOT provided\" | missing slug prefix | use Route B `openrouter\u002F...` or Route A with `--model-class openrouter` |\n| \"model isn't mapped\"\u002Fcost error | unknown cost for model | `export MSWEA_COST_TRACKING=ignore_errors` |\n| unknown flag | version drift | check `pier run --help` |\n\n## Limitations\n\n- Adapted from `davidondrej\u002Fskills`; verify local paths, tools, credentials, and agent features before acting.\n- For commands, remote access, scheduling, browser automation, or file-changing workflows, get explicit user approval and confirm the target environment first.\n","# Run DeepSWE via OpenRouter\n\n## When to Use\n\n- Use when the user wants to benchmark a model on DeepSWE or mini-swe-agent tasks.\n- Use when you need a reproducible coding-agent evaluation plan and output artifacts.\n\nDeepSWE (deepswe.datacurve.ai) is a 113-task Harbor-compatible coding-agent benchmark. It runs via **Pier** (Harbor fork) driving **mini-swe-agent** (model-agnostic). Any model reachable through OpenRouter can be scored.\n\n## Prerequisites — state-check first\n\n```bash\nwhich uv git docker || echo \"MISSING: install uv, git, docker\"\ndocker info >\u002Fdev\u002Fnull 2>&1 || echo \"MISSING: Docker daemon not running (Pier's default sandbox)\"\necho \"OPENROUTER_API_KEY set? ${OPENROUTER_API_KEY:+YES}\"\n```\n\n**Docker must be running** — Pier sandboxes each task in Docker by default (`--env modal` for cloud instead).\n\n`OPENROUTER_API_KEY` must already be present in the environment. If it is unset,\nask the user to configure their preferred secret-management path; do not read\nshell startup files, print secrets, or invent a key.\n\n## Setup\n\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002Fdatacurve-ai\u002Fdeep-swe && cd deep-swe\nuv tool install datacurve-pier            # PyPI (preferred)\n# or: uv tool install git+https:\u002F\u002Fgithub.com\u002Fdatacurve-ai\u002Fpier\n# pier bundles mini-swe-agent as the --agent driver\n```\n\nRun all `pier` commands from inside `deep-swe\u002F`, using relative `-p tasks\u002F...`.\n\n## OpenRouter wiring (the part the docs don't spell out)\n\nmini-swe-agent has a native OpenRouter model class. Both routes below use `OPENROUTER_API_KEY` and the OpenRouter slug (`vendor\u002Fmodel`, e.g. `minimax\u002Fminimax-m3`):\n\n**Route A — native OpenRouter class (preferred, hits openrouter.ai\u002Fapi\u002Fv1 directly):**\n```bash\npier run -p deep-swe\u002Ftasks --agent mini-swe-agent \\\n  --model minimax\u002Fminimax-m3 --model-class openrouter\n```\n\n**Route B — LiteLLM provider prefix (fallback; same key):**\n```bash\npier run -p deep-swe\u002Ftasks --agent mini-swe-agent \\\n  --model openrouter\u002Fminimax\u002Fminimax-m3\n```\n\nNotes:\n- Slug = the exact OpenRouter slug. Verify it at openrouter.ai\u002Fmodels before running.\n- Free\u002Fzero-cost models: OpenRouter cost tracking can error. Set `export MSWEA_COST_TRACKING=ignore_errors`.\n- Flag spelling can vary by version — confirm with `pier run --help` and `mini --help`.\n\n## Smoke test FIRST (1 task — do this before any full run)\n\nAlways validate end-to-end wiring on a single task before spending tokens on the corpus:\n\n```bash\npier run -p deep-swe\u002Ftasks\u002F\u003Ctask-id> --agent mini-swe-agent \\\n  --model minimax\u002Fminimax-m3 --model-class openrouter\n# list available task ids:\nls deep-swe\u002Ftasks\n```\n\nPass criteria: run completes, model returns actions (not auth\u002Fformat errors), a score\u002Ftrajectory is emitted. If it 401s → key wrong. If \"provider not provided\"\u002F\"model not mapped\" → fix slug or switch route.\n\n## Subset run (deterministic sample)\n\n```bash\npier run -p deep-swe\u002Ftasks --agent mini-swe-agent \\\n  --model minimax\u002Fminimax-m3 --model-class openrouter \\\n  --n-tasks 10 --sample-seed 0\n```\n\n## Full 113-task corpus (costs tokens + time — confirm with user first)\n\n```bash\npier run -p deep-swe\u002Ftasks --agent mini-swe-agent \\\n  --model minimax\u002Fminimax-m3 --model-class openrouter\n# add `--env modal` to run in parallel Modal sandboxes (needs Modal configured)\n```\n\n## Output & leaderboard\n\n- Trials land in `jobs\u002F\u003Crun>\u002F\u003Ctrial_id>\u002F`. Inspect with `pier view jobs\u002F\u003Crun>`, `pier analyze jobs\u002F\u003Crun>`, or `pier critique run jobs\u002F\u003Crun>`.\n- Report: the exact command used, pass\u002Ffail, score, and any blockers.\n- Submit results for the official leaderboard to: **\u003Cemail-address>**\n\n## Failure modes\n\n| Symptom | Cause | Fix |\n|---|---|---|\n| HTTP 401 | bad\u002Fmissing key | re-export `OPENROUTER_API_KEY` |\n| \"LLM Provider NOT provided\" | missing slug prefix | use Route B `openrouter\u002F...` or Route A with `--model-class openrouter` |\n| \"model isn't mapped\"\u002Fcost error | unknown cost for model | `export MSWEA_COST_TRACKING=ignore_errors` |\n| unknown flag | version drift | check `pier run --help` |\n\n## Limitations\n\n- Adapted from `davidondrej\u002Fskills`; verify local paths, tools, credentials, and agent features before acting.\n- For commands, remote access, scheduling, browser automation, or file-changing workflows, get explicit user approval and confirm the target environment first.\n",{"name":5,"risk":31,"tags":48,"tools":50,"author":52,"source":33,"license":14,"category":27,"date_added":53,"description":7,"source_repo":54,"source_type":33,"license_source":55,"disable-model-invocation":56},[41,30,36,49],"evaluation",[51,42],"claude","davidondrej","2026-07-07","davidondrej\u002Fskills","https:\u002F\u002Fgithub.com\u002Fdavidondrej\u002Fskills\u002Fblob\u002Fmain\u002FLICENSE",true,"f3312ba749561b6159f477dbfc9313c875d40a56",".agents\u002Fskills_archive\u002Frun-deep-swe","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612","2026-10-25 23:50:58",{"source":8,"skillName":5,"commands":63,"prompt":73,"zipAvailable":56},[64,67,70],{"tool":65,"command":66},"npx","npx skills add duc-duy-1612\u002FOnline-Delivery-Systems-Web --skill run-deep-swe",{"tool":68,"command":69},"bunx","bunx skills add duc-duy-1612\u002FOnline-Delivery-Systems-Web --skill run-deep-swe",{"tool":71,"command":72},"pnpm","pnpm dlx skills add duc-duy-1612\u002FOnline-Delivery-Systems-Web --skill run-deep-swe","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Frun-deep-swe\u002FSKILL.md",[],[76,102,125,146,174,198],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":85,"publishedAt":43},"01M6Q0FA5FZ410Z33Z3TFQ4DBA","zero-trust","Implement zero-trust network architecture. Configure identity-based access, micro-segmentation, and continuous verification. Use when implementing modern security architectures.","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Fzero-trust\u002FSKILL.md",[82],{"categoryNo":83,"categoryName":84,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000011","运维与部署",[86,87,88,89,90,91,78,92,93,94,95,96,33,32,97,31,98,99,100,101],"ZeRO","trust","zero trust","architecture","assessment","verification","segmentation","devops-security","access","configure","only","active","scope","scripts","relevant","implementing",{"skillNo":103,"name":104,"nameZh":6,"description":105,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":106,"categories":107,"keywords":108,"publishedAt":43},"01M6Q0F1YZJW3KX5FBKEVZ8CV4","zcode-delegate","Delegate coding tasks to the Z.AI ZCode CLI only when the user explicitly requests it, while the orchestrator retains review and landing responsibility.","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Fzcode-delegate\u002FSKILL.md",[],[109,110,111,112,113,114,115,23,116,117,118,119,120,96,121,33,122,123,31,124],"delegate","zcode","zcode delegate","review","cli","orchestration","tasks","Bash","model","node","read","orchestrator","files","desktop app","app","agent-orchestration",{"skillNo":126,"name":127,"nameZh":6,"description":128,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":129,"categories":130,"keywords":131,"publishedAt":43},"01M6Q0ETK41VGNMYEXW0T00AJN","youtube-transcript","Fetch YouTube transcripts through DeepAPI or local fallback tooling and save clean text output.","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Fyoutube-transcript\u002FSKILL.md",[],[132,133,134,135,34,42,136,40,39,137,138,139,140,33,32,141,142,143,144,145],"transcript","youtube transcript","youtube","safe","research","text","fetch","tooling","clean","local","output","deepapi","youtube transcripts","blob",{"skillNo":147,"name":148,"nameZh":6,"description":149,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":150,"categories":151,"keywords":163,"publishedAt":43},"01M6Q0EPPH2PVMDW40017F8WX0","youtube-transcript-skills","Fetch YouTube video transcripts, search videos\u002Fchannels, browse channels, and extract playlists via the getyoutubetranscript.com API - free tier, no card required.","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Fyoutube-transcript-skills\u002FSKILL.md",[152,155,158],{"categoryNo":153,"categoryName":154,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000010","后端与接口",{"categoryNo":156,"categoryName":157,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000016","图像与多媒体",{"categoryNo":159,"categoryName":160,"taxonomyType":161,"taxonomyTypeDesc":162},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[132,133,134,164,135,165,34,42,40,166,167,168,169,138,170,33,32,171,172,173],"youtube transcript skills","gemini","search","api","Video","browse","api-integration","free","card","channels",{"skillNo":175,"name":176,"nameZh":6,"description":177,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":178,"categories":179,"keywords":184,"publishedAt":43},"01M6Q0EAB96PX83W5PTE8A0R8D","youtube-notetaker","Turn YouTube talks into local study notes with slides, transcripts, editable annotations, and a markdown-backed viewer.","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Fyoutube-notetaker\u002FSKILL.md",[180,183],{"categoryNo":181,"categoryName":182,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000003","演示文稿",{"categoryNo":156,"categoryName":157,"taxonomyType":20,"taxonomyTypeDesc":21},[134,185,186,113,135,187,188,189,190,40,168,191,192,193,194,32,195,141,196,197],"youtube notetaker","notetaker","workflow","official","notes","code","markdown","slides","annotations","README","study","dair-academy","viewer",{"skillNo":199,"name":200,"nameZh":6,"description":201,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":202,"categories":203,"keywords":205,"publishedAt":43},"01M6Q0E55F0GW5MX48V8HXS8B5","youtube-full","Fetch YouTube transcripts, search videos, browse channels, and extract playlists via TranscriptAPI — no yt-dlp, no Google API key, works from any cloud server.","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Fyoutube-full\u002FSKILL.md",[204],{"categoryNo":153,"categoryName":154,"taxonomyType":20,"taxonomyTypeDesc":21},[206,134,207,208,135,165,166,209,210,167,168,169,138,211,170,33,32,171,212,144],"youtube full","full","google","server","dlp","credits","automatic"]