[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M792ZJ466V94NGPDZSW2B19G":3,"skill-same:01M792ZJ466V94NGPDZSW2B19G":56},{"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":26,"commitSha":27,"skillDirectory":28,"forksCount":29,"repositoryHtmlUrl":30,"repositoryHomepageUrl":6,"ownerHtmlUrl":31,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":32,"install":33,"resources":45},"01M792ZJ466V94NGPDZSW2B19G","analysis",null,"Guide Kalshi, Polymarket, and cross-venue analysis workflows for prediction-market-analysis.","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\u002Fprediction-market-analysis\u002Fsub-skills\u002Fanalysis\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: analysis\ndescription: \"Guide Kalshi, Polymarket, and cross-venue analysis workflows for\n  prediction-market-analysis.\"\nmetadata:\n  disco-role: operating\ndisable-model-invocation: true\nlicense: MIT\n---\n\n# analysis\n\nUse this sub-skill for anything that runs, interprets, or extends the repo's analysis classes.\nIt covers both the menu-driven CLI and the Python `Analysis` framework.\n\n## Use this route when\n\n- The user wants to run a named analysis or all analyses.\n- The user wants calibration, return, volume, category, or statistical-study guidance.\n- The user wants a new analysis class or a fix to an existing one.\n- The user wants help understanding `Analysis`, `AnalysisOutput`, or `ChartConfig`.\n\n## Scope\n\n### Included\n\n- Kalshi calibration and pricing analyses.\n- Kalshi maker\u002Ftaker, category, hour-of-day, and volume analyses.\n- Kalshi meta statistics and paper-style statistical tests.\n- Polymarket calibration, volume, and trade-time analyses.\n- The cross-venue animated calibration comparison.\n- `Analysis.save()` output formats and `ChartConfig` JSON export.\n\n### Excluded\n\n- Market\u002Ftrade\u002Fblock backfills and cursor recovery, which belong to `sub-skills\u002Findexing\u002F`.\n- Dataset download, archive creation, and host-tool installation, which belong to `sub-skills\u002Fdata-ops\u002F`.\n\n## Read first\n\n- `..\u002F..\u002Freferences\u002Fanalysis-catalog.md` for the full analysis list.\n- `..\u002F..\u002Freferences\u002Fapi-reference.md` for the `Analysis` and `ChartConfig` APIs.\n- `..\u002F..\u002Freferences\u002Fdata-layout.md` for the required Parquet inputs.\n- `..\u002F..\u002Freferences\u002Ftroubleshooting.md` for cross-cutting failures.\n\n## Core workflow\n\n1. Identify the analysis name from the catalog or from `scripts\u002Fcatalog.py`.\n2. Confirm the required input directories exist.\n3. Run the analysis with `uv run main.py analyze \u003Cname>` or the equivalent wrapper.\n4. Read the saved outputs under `output\u002F\u003Canalysis-name>.*`.\n5. If the analysis is missing, thin, or failing, inspect the relevant source module and the family-specific troubleshooting notes.\n\n## Analysis families\n\n### Kalshi calibration and pricing\n\nUse these when the task is about price calibration, mispricing, or expected value:\n\n- `win_rate_by_price`\n- `mispricing_by_price`\n- `win_rate_by_trade_size`\n- `ev_yes_vs_no`\n\nTypical inputs:\n`data\u002Fkalshi\u002Ftrades\u002F`, `data\u002Fkalshi\u002Fmarkets\u002F`.\n\n### Kalshi time and volume\n\nUse these when the task is about temporal trends or notional volume:\n\n- `returns_by_hour`\n- `vwap_by_hour`\n- `volume_over_time`\n- `longshot_volume_share_over_time`\n- `kalshi_calibration_deviation_over_time`\n- `maker_taker_gap_over_time`\n\nTypical inputs:\n`data\u002Fkalshi\u002Ftrades\u002F`, sometimes `data\u002Fkalshi\u002Fmarkets\u002F`.\n\n### Kalshi maker\u002Ftaker and category studies\n\nUse these when the task compares makers and takers, direction, or category grouping:\n\n- `trade_size_by_role`\n- `maker_returns_by_direction`\n- `maker_win_rate_by_direction`\n- `maker_vs_taker_returns`\n- `maker_taker_returns_by_category`\n- `market_types`\n- `yes_vs_no_by_price`\n- `meta_stats`\n- `statistical_tests`\n\nTypical inputs:\n`data\u002Fkalshi\u002Ftrades\u002F`, `data\u002Fkalshi\u002Fmarkets\u002F`, and `src.analysis.kalshi.util.categories`.\n\n### Polymarket analyses\n\nUse these when the task is about Polymarket calibration, volume, or block-level trade history:\n\n- `polymarket_win_rate_by_price`\n- `polymarket_calibration_by_bucket`\n- `polymarket_volume_over_time`\n- `polymarket_trades_over_time`\n\nTypical inputs:\n`data\u002Fpolymarket\u002Ftrades\u002F`, `data\u002Fpolymarket\u002Flegacy_trades\u002F`, `data\u002Fpolymarket\u002Fmarkets\u002F`, `data\u002Fpolymarket\u002Fblocks\u002F`, and `data\u002Fpolymarket\u002Ffpmm_collateral_lookup.json`.\n\n### Cross-venue comparison\n\nUse `win_rate_by_price_animated` when the user wants a single workflow that compares Kalshi and Polymarket in one animated calibration plot.\n\nTypical inputs:\nBoth platforms' data directories plus `data\u002Fpolymarket\u002Fblocks\u002F` and the collateral lookup file.\n\n## Adding or fixing an analysis\n\n- Subclass `Analysis`.\n- Set a stable `name` and a human-readable `description` in `__init__`.\n- Keep data selection, transformations, figure creation, and chart serialization inside `run()` or helper methods.\n- Return `AnalysisOutput`.\n- Use `self.progress()` for longer SQL or dataframe steps.\n- Prefer `ChartConfig` helpers when the analysis should also emit JSON chart output.\n- Use the category helpers from `src.analysis.kalshi.util.categories` when grouping Kalshi markets.\n\n## Common failure patterns\n\n- Missing or empty `data\u002F` subtrees.\n- No finalized or resolved markets, leading to empty dataframes.\n- Missing Polymarket helper files, especially the collateral lookup or block timestamps.\n- `Analysis.load()` returning no classes because the command was run from the wrong directory.\n- Matplotlib backend issues on headless hosts.\n\n## Helpful helper\n\n- `..\u002F..\u002Fscripts\u002Fcatalog.py` lists the analysis names without opening the interactive menu when run through the repo environment.\n","# analysis\n\nUse this sub-skill for anything that runs, interprets, or extends the repo's analysis classes.\nIt covers both the menu-driven CLI and the Python `Analysis` framework.\n\n## Use this route when\n\n- The user wants to run a named analysis or all analyses.\n- The user wants calibration, return, volume, category, or statistical-study guidance.\n- The user wants a new analysis class or a fix to an existing one.\n- The user wants help understanding `Analysis`, `AnalysisOutput`, or `ChartConfig`.\n\n## Scope\n\n### Included\n\n- Kalshi calibration and pricing analyses.\n- Kalshi maker\u002Ftaker, category, hour-of-day, and volume analyses.\n- Kalshi meta statistics and paper-style statistical tests.\n- Polymarket calibration, volume, and trade-time analyses.\n- The cross-venue animated calibration comparison.\n- `Analysis.save()` output formats and `ChartConfig` JSON export.\n\n### Excluded\n\n- Market\u002Ftrade\u002Fblock backfills and cursor recovery, which belong to `sub-skills\u002Findexing\u002F`.\n- Dataset download, archive creation, and host-tool installation, which belong to `sub-skills\u002Fdata-ops\u002F`.\n\n## Read first\n\n- `..\u002F..\u002Freferences\u002Fanalysis-catalog.md` for the full analysis list.\n- `..\u002F..\u002Freferences\u002Fapi-reference.md` for the `Analysis` and `ChartConfig` APIs.\n- `..\u002F..\u002Freferences\u002Fdata-layout.md` for the required Parquet inputs.\n- `..\u002F..\u002Freferences\u002Ftroubleshooting.md` for cross-cutting failures.\n\n## Core workflow\n\n1. Identify the analysis name from the catalog or from `scripts\u002Fcatalog.py`.\n2. Confirm the required input directories exist.\n3. Run the analysis with `uv run main.py analyze \u003Cname>` or the equivalent wrapper.\n4. Read the saved outputs under `output\u002F\u003Canalysis-name>.*`.\n5. If the analysis is missing, thin, or failing, inspect the relevant source module and the family-specific troubleshooting notes.\n\n## Analysis families\n\n### Kalshi calibration and pricing\n\nUse these when the task is about price calibration, mispricing, or expected value:\n\n- `win_rate_by_price`\n- `mispricing_by_price`\n- `win_rate_by_trade_size`\n- `ev_yes_vs_no`\n\nTypical inputs:\n`data\u002Fkalshi\u002Ftrades\u002F`, `data\u002Fkalshi\u002Fmarkets\u002F`.\n\n### Kalshi time and volume\n\nUse these when the task is about temporal trends or notional volume:\n\n- `returns_by_hour`\n- `vwap_by_hour`\n- `volume_over_time`\n- `longshot_volume_share_over_time`\n- `kalshi_calibration_deviation_over_time`\n- `maker_taker_gap_over_time`\n\nTypical inputs:\n`data\u002Fkalshi\u002Ftrades\u002F`, sometimes `data\u002Fkalshi\u002Fmarkets\u002F`.\n\n### Kalshi maker\u002Ftaker and category studies\n\nUse these when the task compares makers and takers, direction, or category grouping:\n\n- `trade_size_by_role`\n- `maker_returns_by_direction`\n- `maker_win_rate_by_direction`\n- `maker_vs_taker_returns`\n- `maker_taker_returns_by_category`\n- `market_types`\n- `yes_vs_no_by_price`\n- `meta_stats`\n- `statistical_tests`\n\nTypical inputs:\n`data\u002Fkalshi\u002Ftrades\u002F`, `data\u002Fkalshi\u002Fmarkets\u002F`, and `src.analysis.kalshi.util.categories`.\n\n### Polymarket analyses\n\nUse these when the task is about Polymarket calibration, volume, or block-level trade history:\n\n- `polymarket_win_rate_by_price`\n- `polymarket_calibration_by_bucket`\n- `polymarket_volume_over_time`\n- `polymarket_trades_over_time`\n\nTypical inputs:\n`data\u002Fpolymarket\u002Ftrades\u002F`, `data\u002Fpolymarket\u002Flegacy_trades\u002F`, `data\u002Fpolymarket\u002Fmarkets\u002F`, `data\u002Fpolymarket\u002Fblocks\u002F`, and `data\u002Fpolymarket\u002Ffpmm_collateral_lookup.json`.\n\n### Cross-venue comparison\n\nUse `win_rate_by_price_animated` when the user wants a single workflow that compares Kalshi and Polymarket in one animated calibration plot.\n\nTypical inputs:\nBoth platforms' data directories plus `data\u002Fpolymarket\u002Fblocks\u002F` and the collateral lookup file.\n\n## Adding or fixing an analysis\n\n- Subclass `Analysis`.\n- Set a stable `name` and a human-readable `description` in `__init__`.\n- Keep data selection, transformations, figure creation, and chart serialization inside `run()` or helper methods.\n- Return `AnalysisOutput`.\n- Use `self.progress()` for longer SQL or dataframe steps.\n- Prefer `ChartConfig` helpers when the analysis should also emit JSON chart output.\n- Use the category helpers from `src.analysis.kalshi.util.categories` when grouping Kalshi markets.\n\n## Common failure patterns\n\n- Missing or empty `data\u002F` subtrees.\n- No finalized or resolved markets, leading to empty dataframes.\n- Missing Polymarket helper files, especially the collateral lookup or block timestamps.\n- `Analysis.load()` returning no classes because the command was run from the wrong directory.\n- Matplotlib backend issues on headless hosts.\n\n## Helpful helper\n\n- `..\u002F..\u002Fscripts\u002Fcatalog.py` lists the analysis names without opening the interactive menu when run through the repo environment.\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fprediction-market-analysis\u002Fsub-skills\u002Fanalysis",27,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab","2026-09-03 10:25:21",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":25},[35,38,41],{"tool":36,"command":37},"npx","npx skills add VectorSpaceLab\u002FAREX-Skill --skill analysis",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill analysis",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill analysis","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fprediction-market-analysis\u002Fsub-skills\u002Fanalysis\u002FSKILL.md",[46,52],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Ftroubleshooting.md","REFERENCE","参考文档",1677,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fprediction-market-analysis\u002Fsub-skills\u002Fanalysis\u002Freferences\u002Ftroubleshooting.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Fworkflows.md",1588,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fprediction-market-analysis\u002Fsub-skills\u002Fanalysis\u002Freferences\u002Fworkflows.md",[57,65,72,79,86,93],{"skillNo":58,"name":59,"nameZh":6,"description":60,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":61,"licenseFileUrl":6,"sourceHtmlUrl":62,"categories":63,"keywords":64,"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":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":61,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"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":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":61,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"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":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":61,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"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":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":61,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"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":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":61,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"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",[],[]]