[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M746FPCP0GBRK19HRKTY0X7G":3,"skill-same:01M746FPCP0GBRK19HRKTY0X7G":64},{"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":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":29,"ownerHtmlUrl":30,"ownerBlogUrl":31,"ownerDescription":32,"updatedAt":33,"install":34,"resources":47},"01M746FPCP0GBRK19HRKTY0X7G","risk-attribution",null,"Estimate an asset covariance matrix from a supplied return history (sample, EWMA or Ledoit-Wolf), split portfolio VaR and Expected Shortfall into per-position Euler contributions (parametric normal, and historical-simulation ES), give incremental VaR per position, and regress asset returns on supplied factor returns to split portfolio variance into systematic and idiosyncratic parts. Use when the user asks which positions drive the risk, what a position adds to VaR or ES, what the covariance or correlation of a history is, or how much risk is factor risk. For a portfolio VaR or ES total from P&L alone use risk-tail; for gross and net exposure use risk-portfolio; for scenario shocks use risk-stress.","hashgraph-online\u002Fawesome-codex-plugins","hashgraph-online","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F160371962?v=4","01M6CNB6NRJVNNGN14TR01Q6D3","HOL (Hashgraph Online)","01M6JT1HSKKG9V68KQAQGBA7XP",1575,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FIman\u002Fagent-driven-risk-desk-and-skills\u002Fskills\u002Frisk-attribution\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: risk-attribution\ndescription: Estimate an asset covariance matrix from a supplied return history (sample, EWMA or Ledoit-Wolf), split portfolio VaR and Expected Shortfall into per-position Euler contributions (parametric normal, and historical-simulation ES), give incremental VaR per position, and regress asset returns on supplied factor returns to split portfolio variance into systematic and idiosyncratic parts. Use when the user asks which positions drive the risk, what a position adds to VaR or ES, what the covariance or correlation of a history is, or how much risk is factor risk. For a portfolio VaR or ES total from P&L alone use risk-tail; for gross and net exposure use risk-portfolio; for scenario shocks use risk-stress.\n---\n\n# Risk Attribution\n\nFour calculations, each a pure function over supplied data. None fetches\nmarket data. Contracts and every formula, with its source, are in\n`reference.md`.\n\n| question | MCP tool | CLI |\n|---|---|---|\n| covariance, volatility, correlation of a history | `risk_covariance` | `riskdesk covariance --input PATH` |\n| which positions drive normal VaR and ES, and what removing one changes | `risk_var_attribution` | `riskdesk var-attribution --input PATH` |\n| which positions drive historical ES | `risk_es_attribution` | `riskdesk es-attribution --input PATH` |\n| factor betas and systematic versus idiosyncratic variance | `risk_factor_exposure` | `riskdesk factors --input PATH` |\n\nWorked inputs: `examples\u002Fdecomposition_covariance.json`,\n`examples\u002Fdecomposition_parametric.json`, `examples\u002Fdecomposition_historical.json`,\n`examples\u002Fdecomposition_factor.json`. All four are synthetic.\n\n## Inputs you must have before calling\n\nCurrency, as-of date, source, data mode, and the horizon each return row\nspans. Positions are signed market values already in the base currency, each\nwith `instrument_type: linear`, and each naming an asset that appears in\n`assets`. Return rows are simple returns, oldest first, one column per asset.\nNever invent a missing return, covariance entry, factor return or decay. If\nthe user did not give an EWMA decay, ask for it. The tool has no default.\n\n## What to report first\n\n1. `degraded` and `degraded_reason`, before any number.\n2. Currency, horizon in days, as-of date, method, and observations used.\n3. The total (VaR, ES or variance), then the contributions.\n\n## Sign conventions\n\nLoss is positive. A negative contribution means the position lowers\nportfolio risk at the margin: it is a hedge in this book. A percentage\ncontribution above 100 percent is possible when other positions offset it.\nMarginal VaR and ES are per 1 unit of currency added to that position.\nFactor exposure is currency P&L per 1.00 (100 percent) factor return.\n\n## What the numbers add up to\n\nComponent VaR sums to VaR, component ES sums to ES, percentages sum to one,\nand systematic plus idiosyncratic variance equals the sample variance of\nportfolio P&L. `scripts\u002Fcheck_artifact.py` checks these sums in one line.\nIncremental VaR does not sum to VaR, and is not meant to.\n\n## What not to claim\n\n- Parametric results assume normal P&L with zero mean. They are not\n  historical VaR. Quote them as \"normal VaR\" and do not mix them with\n  `risk_tail` figures in one sentence without naming both methods.\n- A covariance flagged not positive definite was not repaired. Say so, and\n  offer `ledoit_wolf` rather than altering the matrix by hand.\n- When historical ES is degraded for a tied tail boundary, the total is\n  sound but the split between positions depends on input order.\n- R squared and the variance split are in-sample. They are not forecasts,\n  and factor betas from a short history are noisy.\n- None of this is regulatory capital, a validated model, or advice.\n\n## Going deeper\n\n- `reference.md`: request contracts, every formula and sign convention,\n  and the paper or document behind each one with its section and equation.\n- `workflows\u002Fdecompose-portfolio-risk.md`: the order to run the tools in and\n  what to check before reporting.\n- `scripts\u002Fcheck_artifact.py`: run it on a saved result for a one line\n  OK, DEGRADED or FAIL verdict.\n","# Risk Attribution\n\nFour calculations, each a pure function over supplied data. None fetches\nmarket data. Contracts and every formula, with its source, are in\n`reference.md`.\n\n| question | MCP tool | CLI |\n|---|---|---|\n| covariance, volatility, correlation of a history | `risk_covariance` | `riskdesk covariance --input PATH` |\n| which positions drive normal VaR and ES, and what removing one changes | `risk_var_attribution` | `riskdesk var-attribution --input PATH` |\n| which positions drive historical ES | `risk_es_attribution` | `riskdesk es-attribution --input PATH` |\n| factor betas and systematic versus idiosyncratic variance | `risk_factor_exposure` | `riskdesk factors --input PATH` |\n\nWorked inputs: `examples\u002Fdecomposition_covariance.json`,\n`examples\u002Fdecomposition_parametric.json`, `examples\u002Fdecomposition_historical.json`,\n`examples\u002Fdecomposition_factor.json`. All four are synthetic.\n\n## Inputs you must have before calling\n\nCurrency, as-of date, source, data mode, and the horizon each return row\nspans. Positions are signed market values already in the base currency, each\nwith `instrument_type: linear`, and each naming an asset that appears in\n`assets`. Return rows are simple returns, oldest first, one column per asset.\nNever invent a missing return, covariance entry, factor return or decay. If\nthe user did not give an EWMA decay, ask for it. The tool has no default.\n\n## What to report first\n\n1. `degraded` and `degraded_reason`, before any number.\n2. Currency, horizon in days, as-of date, method, and observations used.\n3. The total (VaR, ES or variance), then the contributions.\n\n## Sign conventions\n\nLoss is positive. A negative contribution means the position lowers\nportfolio risk at the margin: it is a hedge in this book. A percentage\ncontribution above 100 percent is possible when other positions offset it.\nMarginal VaR and ES are per 1 unit of currency added to that position.\nFactor exposure is currency P&L per 1.00 (100 percent) factor return.\n\n## What the numbers add up to\n\nComponent VaR sums to VaR, component ES sums to ES, percentages sum to one,\nand systematic plus idiosyncratic variance equals the sample variance of\nportfolio P&L. `scripts\u002Fcheck_artifact.py` checks these sums in one line.\nIncremental VaR does not sum to VaR, and is not meant to.\n\n## What not to claim\n\n- Parametric results assume normal P&L with zero mean. They are not\n  historical VaR. Quote them as \"normal VaR\" and do not mix them with\n  `risk_tail` figures in one sentence without naming both methods.\n- A covariance flagged not positive definite was not repaired. Say so, and\n  offer `ledoit_wolf` rather than altering the matrix by hand.\n- When historical ES is degraded for a tied tail boundary, the total is\n  sound but the split between positions depends on input order.\n- R squared and the variance split are in-sample. They are not forecasts,\n  and factor betas from a short history are noisy.\n- None of this is regulatory capital, a validated model, or advice.\n\n## Going deeper\n\n- `reference.md`: request contracts, every formula and sign convention,\n  and the paper or document behind each one with its section and equation.\n- `workflows\u002Fdecompose-portfolio-risk.md`: the order to run the tools in and\n  what to check before reporting.\n- `scripts\u002Fcheck_artifact.py`: run it on a saved result for a one line\n  OK, DEGRADED or FAIL verdict.\n",{"name":5,"description":7},"main","347aedf8480cd92b21f761e97b7343a45898f5fa","plugins\u002FIman\u002Fagent-driven-risk-desk-and-skills\u002Fskills\u002Frisk-attribution",491,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins","https:\u002F\u002Fhol.org\u002Fplugins\u002Fbest-codex-plugins","https:\u002F\u002Fgithub.com\u002Fhashgraph-online","https:\u002F\u002Fhol.org","Open-source standards and developer tools for interoperable AI agents: discovery, identity, communication, payments, privacy and security.","2026-11-14 14:06:13",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":46},[36,39,42],{"tool":37,"command":38},"npx","npx skills add hashgraph-online\u002Fawesome-codex-plugins --skill risk-attribution",{"tool":40,"command":41},"bunx","bunx skills add hashgraph-online\u002Fawesome-codex-plugins --skill risk-attribution",{"tool":43,"command":44},"pnpm","pnpm dlx skills add hashgraph-online\u002Fawesome-codex-plugins --skill risk-attribution","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FIman\u002Fagent-driven-risk-desk-and-skills\u002Fskills\u002Frisk-attribution\u002FSKILL.md",true,[48,54,60],{"path":49,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":52,"sourceHtmlUrl":53},"reference.md","REFERENCE","参考文档",7756,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FIman\u002Fagent-driven-risk-desk-and-skills\u002Fskills\u002Frisk-attribution\u002Freference.md",{"path":55,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":58,"sourceHtmlUrl":59},"scripts\u002Fcheck_artifact.py","SCRIPT","脚本",2962,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FIman\u002Fagent-driven-risk-desk-and-skills\u002Fskills\u002Frisk-attribution\u002Fscripts\u002Fcheck_artifact.py",{"path":61,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":62,"sourceHtmlUrl":63},"workflows\u002Fdecompose-portfolio-risk.md",1910,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FIman\u002Fagent-driven-risk-desk-and-skills\u002Fskills\u002Frisk-attribution\u002Fworkflows\u002Fdecompose-portfolio-risk.md",[65,75,83,91,99,107],{"skillNo":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":69,"licenseFileUrl":70,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":74},"01M7DV332YQMGD8WTRJ9DZQXTB","worktable-review-with-annotations","Create, inspect, reply to, update, or resolve situated Worktable annotations. Use when feedback belongs to a Doc section, block, text range, or HTML Doc, or when the user asks to address existing review feedback and coordinate a requested artifact edit.","MIT","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-review-with-annotations\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-review-with-annotations\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"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":69,"licenseFileUrl":79,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":74},"01M7DV2YGHCZVBEB1AHYB6CGHE","worktable-find-and-synthesize-context","Find, assess, and synthesize context from Worktable Docs and Records. Use when the user asks what a workspace contains, wants workspace-backed research, needs current facts reconciled across artifacts, or requests a cited synthesis without changing workspace state.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-find-and-synthesize-context\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-find-and-synthesize-context\u002FSKILL.md",[],[],{"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":69,"licenseFileUrl":87,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":74},"01M7DV2TQN1H11ME2SAF9MXN7V","worktable-create-or-update-docs","Create, edit, rename, or maintain narrative Worktable Docs. Use for plans, decisions, briefs, notes, research syntheses, and other durable prose when the user requests a new artifact or a safe update to an existing one.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-update-docs\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-update-docs\u002FSKILL.md",[],[],{"skillNo":92,"name":93,"nameZh":6,"description":94,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":69,"licenseFileUrl":95,"sourceHtmlUrl":96,"categories":97,"keywords":98,"publishedAt":74},"01M7DV2NE452NEA8TXATKSNAJH","worktable-create-or-manage-records","Organize repeated structured information as durable Worktable Records. Use for research datasets, inventories, directories, pipelines, trackers, and other collections whose items need identity, fields, filtering, links, validation, or individual updates.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-records\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-records\u002FSKILL.md",[],[],{"skillNo":100,"name":101,"nameZh":6,"description":102,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":69,"licenseFileUrl":103,"sourceHtmlUrl":104,"categories":105,"keywords":106,"publishedAt":74},"01M7DV2HENRBR2KSCVM064WH0Y","worktable-create-or-manage-interactive-html","Create or improve durable visual and interactive artifacts in Worktable. Use for dashboards, trackers, calculators, mini apps, slide presentations, and other requests that benefit from a polished HTML Doc.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-interactive-html\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-interactive-html\u002FSKILL.md",[],[],{"skillNo":108,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":69,"licenseFileUrl":111,"sourceHtmlUrl":112,"categories":113,"keywords":114,"publishedAt":74},"01M7DV2CADR5R7RQFFYPNAGR9Y","worktable-collaborate-threads","Read, answer, and hand off messages through durable Worktable threads with users or other authenticated participants. Use when the user asks to check addressed messages, reply to a participant, continue a thread, request another agent's help, wait briefly for a response, or watch for comments and messages sent to the agent.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-collaborate-threads\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-collaborate-threads\u002FSKILL.md",[],[]]