[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7944NY88ZNFBWF671GTYJK6":3,"skill-same:01M7944NY88ZNFBWF671GTYJK6":59},{"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":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":27,"commitSha":28,"skillDirectory":29,"forksCount":30,"repositoryHtmlUrl":31,"repositoryHomepageUrl":6,"ownerHtmlUrl":32,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":33,"install":34,"resources":46},"01M7944NY88ZNFBWF671GTYJK6","quant-finance",null,"Run and troubleshoot RD-Agent quantitative-finance factor and model workflows backed by Qlib, including factor-report and co-optimization loops.","VectorSpaceLab\u002FAREX-Skill","VectorSpaceLab","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F180637102?v=4","01M7538C5WPSJGWF7KHR4EFZ9F","01M7538C6R2GFP53NPXTCZNBRT",351,"MIT","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Frd-agent\u002Fsub-skills\u002Fquant-finance\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: quant-finance\ndescription: \"Run and troubleshoot RD-Agent quantitative-finance factor and\n  model workflows backed by Qlib, including factor-report and co-optimization\n  loops.\"\nmetadata:\n  disco-role: operating\n  parent-skill: rd-agent\nlicense: MIT\ndisable-model-invocation: true\n---\n\n# RD-Agent quantitative finance\n\nUse this sub-skill for RD-Agent(Q), factor generation, factor reports, Qlib model research, finance data-agent\u002Fmodel-agent loops, and backtest interpretation.\n\n## Choose the workflow\n\n- `rdagent fin_quant` is the finance quant agent entry point for factor\u002Fmodel co-optimization.\n- `rdagent fin_factor_report` is the inspected CLI entry point for factor-report-driven workflows. Run `--help` in the active version before using it; older documentation may call the flow `fin_factor`.\n- Read the Qlib experiment templates and the active scenario config before changing dates, provider paths, model, or evaluator settings.\n\nA typical safe sequence is:\n\n```bash\nrdagent fin_quant --help\nrdagent fin_factor_report --help\n# inspect the resolved configuration and data path\n# run a tiny\u002Fdebug iteration before a full loop\n```\n\n## Data and split contract\n\nThe documented defaults use local Qlib data (commonly `~\u002F.qlib\u002Fqlib_data\u002Fcn_data`), the CSI300 universe, and `SH000300` as benchmark. The reference templates use chronological splits around 2008–2014 for training, 2015–2016 for validation, and 2017–2020 for test\u002Fbacktest. Treat those values as template evidence, not universal defaults: record the actual provider URI, market, benchmark, dates, and timezone used by the run.\n\nFactor-agent loop:\n\n1. formulate a financially motivated hypothesis;\n2. implement a factor with a name, description, formula, and variables;\n3. evaluate it on the configured data;\n4. combine new factors with the baseline feature set and run the model\u002Fbacktest;\n5. inspect signal and portfolio records;\n6. use feedback to refine the next hypothesis.\n\nModel-agent loop follows the same evidence discipline but may read a report\u002Fpaper and generate model code. Do not compare runs if the universe, date split, transaction costs, or evaluator changed.\n\n## Backtest hygiene\n\n- Check chronological ordering and fit\u002Fvalidation\u002Ftest boundaries before evaluating.\n- Record the feature source, missing-value\u002Fnormalization pipeline, model seed, `n_jobs`, device, and transaction-cost assumptions.\n- Treat `SignalRecord`, signal analysis, and portfolio analysis as separate artifacts.\n- Investigate leakage, survivorship bias, look-ahead features, and accidental test-set use before celebrating a metric.\n- A generated factor that imports successfully is not a validated factor; require evaluator output and a reproducible artifact.\n\nRead [qlib-contract.md](references\u002Fqlib-contract.md) for the template\u002Fdata\u002Fevaluation contract. Use [the parent troubleshooting guide](..\u002F..\u002Freferences\u002Ftroubleshooting.md) for provider, generated-code, and evaluator failures.\n","# RD-Agent quantitative finance\n\nUse this sub-skill for RD-Agent(Q), factor generation, factor reports, Qlib model research, finance data-agent\u002Fmodel-agent loops, and backtest interpretation.\n\n## Choose the workflow\n\n- `rdagent fin_quant` is the finance quant agent entry point for factor\u002Fmodel co-optimization.\n- `rdagent fin_factor_report` is the inspected CLI entry point for factor-report-driven workflows. Run `--help` in the active version before using it; older documentation may call the flow `fin_factor`.\n- Read the Qlib experiment templates and the active scenario config before changing dates, provider paths, model, or evaluator settings.\n\nA typical safe sequence is:\n\n```bash\nrdagent fin_quant --help\nrdagent fin_factor_report --help\n# inspect the resolved configuration and data path\n# run a tiny\u002Fdebug iteration before a full loop\n```\n\n## Data and split contract\n\nThe documented defaults use local Qlib data (commonly `~\u002F.qlib\u002Fqlib_data\u002Fcn_data`), the CSI300 universe, and `SH000300` as benchmark. The reference templates use chronological splits around 2008–2014 for training, 2015–2016 for validation, and 2017–2020 for test\u002Fbacktest. Treat those values as template evidence, not universal defaults: record the actual provider URI, market, benchmark, dates, and timezone used by the run.\n\nFactor-agent loop:\n\n1. formulate a financially motivated hypothesis;\n2. implement a factor with a name, description, formula, and variables;\n3. evaluate it on the configured data;\n4. combine new factors with the baseline feature set and run the model\u002Fbacktest;\n5. inspect signal and portfolio records;\n6. use feedback to refine the next hypothesis.\n\nModel-agent loop follows the same evidence discipline but may read a report\u002Fpaper and generate model code. Do not compare runs if the universe, date split, transaction costs, or evaluator changed.\n\n## Backtest hygiene\n\n- Check chronological ordering and fit\u002Fvalidation\u002Ftest boundaries before evaluating.\n- Record the feature source, missing-value\u002Fnormalization pipeline, model seed, `n_jobs`, device, and transaction-cost assumptions.\n- Treat `SignalRecord`, signal analysis, and portfolio analysis as separate artifacts.\n- Investigate leakage, survivorship bias, look-ahead features, and accidental test-set use before celebrating a metric.\n- A generated factor that imports successfully is not a validated factor; require evaluator output and a reproducible artifact.\n\nRead [qlib-contract.md](references\u002Fqlib-contract.md) for the template\u002Fdata\u002Fevaluation contract. Use [the parent troubleshooting guide](..\u002F..\u002Freferences\u002Ftroubleshooting.md) for provider, generated-code, and evaluator failures.\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":26},{"disco-role":24,"parent-skill":25},"operating","rd-agent",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Frd-agent\u002Fsub-skills\u002Fquant-finance",27,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab","2026-09-03 10:25:21",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":26},[36,39,42],{"tool":37,"command":38},"npx","npx skills add VectorSpaceLab\u002FAREX-Skill --skill quant-finance",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill quant-finance",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill quant-finance","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Frd-agent\u002Fsub-skills\u002Fquant-finance\u002FSKILL.md",[47,53],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fqlib-contract.md","REFERENCE","参考文档",1302,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Frd-agent\u002Fsub-skills\u002Fquant-finance\u002Freferences\u002Fqlib-contract.md",{"path":54,"resourceType":55,"resourceTypeDesc":56,"sizeBytes":57,"sourceHtmlUrl":58},"scripts\u002Fcheck_qlib_data.py","SCRIPT","脚本",803,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Frd-agent\u002Fsub-skills\u002Fquant-finance\u002Fscripts\u002Fcheck_qlib_data.py",[60,68,75,82,89,96],{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":64,"licenseFileUrl":6,"sourceHtmlUrl":65,"categories":66,"keywords":67,"publishedAt":18},"01M799NYSH1R3RVAHSM2D88Y84","passnet-triton-opt","Make a single PassNet Triton kernel fast AND numerically faithful: performance model (when a replacement can win at all), block\u002Fgrid\u002Fwarp tuning, autotune policy, launch overhead, and per-op numeric recipes to pass the dtype baseline tolerances. Use when a pass matches and is correct but speedup below expected, or when correctness fails by small numeric margins.","Apache-2.0","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-triton-opt\u002FSKILL.md",[],[],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":64,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":18},"01M799NS5APEC0N1FZ7XZVW6BN","passnet-solve","END-TO-END playbook for solving one PassNet sample: analyze the computation graphs, decide the optimization strategy (what to fuse, what to replace, what to leave alone), drive the iteration loop, and maximize the sample score. This is the ENTRY skill — invoke it first for any PassNet optimization task; it tells you when to use passnet-pattern-fusion, passnet-triton-opt and passnet-feedback.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-solve\u002FSKILL.md",[],[],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":64,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":18},"01M799NNY9BKSM21V5R7QVTBJX","passnet-skill","PassNet GPU kernel optimization via compiler passes. Design and implement Triton-based optimization passes, create pass files under .\u002Fpass_dir\u002F, self-evaluate with pass_evaluator, and iterate to maximize GPU speedup.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-skill\u002FSKILL.md",[],[],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":64,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":18},"01M799NHH6NP7Z1RK77KGXAN6S","passnet-pattern-fusion","Author PassNet pass files: write patterns that actually MATCH the FX graph, pick fusion regions (which ops to absorb into one Triton kernel), and structure multi-pass submissions with the mandatory shared-dispatch architecture. Use when creating or fixing pattern()\u002Freplacement_args()\u002Freplacement_func() files, when a pass \"failed to match\", or when deciding how to fuse multiple kernels\u002Fops.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-pattern-fusion\u002FSKILL.md",[],[],{"skillNo":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":64,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"publishedAt":18},"01M799ND2J4WNC2PGAZ0A06NDF","passnet-orchestrate","Round\u002Fbatch planning and decision support for PassNet graph optimization. Use for multi-sample triage, worker allocation, eval-budget policy, and post-eval keep\u002Frevert decisions. For solving one concrete sample end to end, use passnet-solve as the entry skill; consult this skill only when you need broader planning or a specific decision gate.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-orchestrate\u002FSKILL.md",[],[],{"skillNo":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":64,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":102,"publishedAt":18},"01M799N8SBTMY02ZDG2AZF5ZWE","passnet-feedback","Fast, deterministic feedback for PassNet work: pre-flight pattern\u002Fmatch verification WITHOUT burning a GPU evaluation, per-node bottleneck analysis of a sample's graphs, and eval-log parsing into per-variant status + estimated score + failure classification. Use BEFORE every GPU evaluation (check_pattern), at the START of a sample (analyze_graph), and AFTER every evaluation (parse_eval_log).","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-feedback\u002FSKILL.md",[],[]]