[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M746DZ3RNJBX5P9D1TCCCGEE":3,"skill-same:01M746DZ3RNJBX5P9D1TCCCGEE":58},{"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},"01M746DZ3RNJBX5P9D1TCCCGEE","options-backtest",null,"Test an option structure against real price history with modelled premiums, and run a paper forward test that records positions before their outcome is known and marks them against later chains. Reports win rate, mean return on capital at risk, drawdown, a permutation test, a bootstrap interval and a buy-and-hold benchmark. Use when the user asks whether a strategy has worked historically, to backtest or forward test something, whether an edge is real or chance, how a structure performed, or asks to paper trade, track a position, or mark a trade. Not for order placement and not for recommendations, and a backtest result is not a forecast.","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-options-desk-and-skills\u002Fskills\u002Foptions-backtest\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: options-backtest\ndescription: Test an option structure against real price history with modelled premiums, and run a paper forward test that records positions before their outcome is known and marks them against later chains. Reports win rate, mean return on capital at risk, drawdown, a permutation test, a bootstrap interval and a buy-and-hold benchmark. Use when the user asks whether a strategy has worked historically, to backtest or forward test something, whether an edge is real or chance, how a structure performed, or asks to paper trade, track a position, or mark a trade. Not for order placement and not for recommendations, and a backtest result is not a forecast.\n---\n\n# Backtest and forward test\n\nTwo different questions. A backtest asks what a rule would have done. A\nforward test asks what a position actually did from the moment it was\nwritten down.\n\n## Execution route\n\nPrefer the `option_backtest` MCP tool for a backtest and the\n`option_forward_test` MCP tool for the paper ledger. If the matching tool is\nnot available, use the `optiondesk` commands below. If neither MCP nor the\nCLI is available, say that no fresh result can be produced; do not invent\nfigures or present an example or remembered result as a new analysis.\n\n## Data boundary\n\nUse fresh provider data only when the tool reports that access is allowed.\nA local Yahoo adapter also requires the personal-use acknowledgement. A\nhosted tool must use a provider that is approved for public display, derived\noutputs, storage, and MCP delivery. Never bypass a provider refusal. When no\napproved tool is available, analyse a snapshot that the user supplied and\nhad the right to share. Otherwise, state that current figures are unavailable.\n\n## Backtest\n\n```\noptiondesk backtest SPY iron_condor --holding-days 30 --entry-every 5 --period 5y\n```\n\nEnters the structure on a fixed schedule, holds to expiry, settles against\nthe real close. Reports trades, win rate, mean return on capital at risk,\ntotal in risk units, drawdown, a permutation test, a bootstrap interval\nfor the mean, and the same schedule holding the underlying instead.\n\n## Forward test\n\n```\noptiondesk forward open --strategy iron_condor --thesis \"range bound into expiry\"\noptiondesk forward mark            # after a newer chain snapshot exists\noptiondesk forward status\noptiondesk forward close --id \u003Cid> --price 775\n```\n\n## What you must say about a result\n\nFour things, in this order, every time. The full argument for each is in\n`reference.md`; these are the versions you cannot skip.\n\n1. Quote the `honesty` field from the artifact before the headline number.\n   It is not boilerplate: premiums are modelled and entry and exit use the\n   same model, so the test cannot see an edge that comes from the market\n   disagreeing with that model.\n2. Give the benchmark alongside the result. A structure that is long the\n   market shows the market's drift, and without the benchmark that drift\n   gets credited to the strategy.\n3. Report the block sign-flip symmetry assumption and the block length.\n   Block boundaries can lose dependence. A strategy chosen after viewing\n   results needs a selection caveat. If the block covers the return sample,\n   the bootstrap has no variation; do not use its interval as evidence.\n4. Under thirty trades, decline to draw conclusions.\n\nFor a forward test, two more. It is paper, so entry and marks are mid\nquotes and a real entry would have crossed the spread on every leg; what it\nremoves is hindsight, not cost. And a position with a leg missing from the\nnewer chain comes back unmarkable rather than marked at zero. Report it\nthat way: a missing wing marked at zero turns a losing short spread into a\nfull credit win, which is the most flattering error available and appears\nexactly when the position is in trouble.\n\n## Reporting rules\n\nThese hold for every number this skill produces.\n\nCite the artifact path when reporting from it. The artifact is the record;\nprose is a summary of it, and a number quoted without its source cannot be\nchecked later.\n\nRead `degraded` before quoting anything. When it is true, say so and give\n`degraded_reason` first, in the same breath as the number rather than as a\nfootnote. Every command carries both fields in the summary it prints, not\nonly in the artifact.\n\nDo not re-derive numbers yourself. If a figure is not in the artifact, say\nit is not there rather than computing a replacement, and never substitute a\ndefault for a value the pipeline refused to produce.\n\nPremiums are model values or mid quotes from delayed third-party data. They\nare not fills, and a real entry crosses the spread on every leg.\n\nNever recommend a trade, an entry, an exit or a size. This is research\nsoftware and it is not investment advice. Present the analysis and let the\nreader decide.\nThe full terms are in DISCLAIMER.md, which ships beside this skill when it\nis installed from a package and sits at the repository root otherwise. The\nsubstance is already above: research software, not advice, modelled numbers\nthat are not fills.\n\n\n## What an audit found in these numbers, and what to say about it\n\nThree independent verifications recomputed this project's arithmetic in\n2026. The backtest statistics reproduced bit for bit. Two things about how\nthey are read did not, and both change what a result means.\n\n**The windows overlap.** A thirty day hold entered every five trading days\nshares twenty-five of its thirty days with its neighbour. Measured\nautocorrelation is positive through lag five and collapses at lag six, and\nthe effective sample is 64 to 88 rather than 233. The significance test and\nthe interval now use blocks: the test flips block signs and the bootstrap\nresamples blocks. The CLI summary carries `overlap_block` when significance is available;\nthe artifact stores `significance.block` and `interval.block` in available\nresults. When the block is above one, say so: the\np-value beside it is a block p-value, and the trade count is not the number\nof independent observations. Correcting this moved four structures from\nbelow 0.05 to above it, one from 0.0005 to 0.148.\n\n**A structure can enter trades and report no statistics.** When the maximum\nloss is unbounded there is no capital at risk to divide by, so every return\non risk is undefined and the statistics object is empty. Read\n`trades_entered`, not a trade count of zero. The run worked; the ratio has\nno denominator. Saying \"no trades\" there is wrong and sends a reader\nlooking for missing price history.\n\nBoth are in the artifact. Neither is in the headline figure, so it falls to\nyou to say them.\n\n## Going deeper\n\n- `reference.md`: the honesty rule in full, how the statistics are computed, and the caveat that outranks all of them.\n- `workflows\u002Fevaluate-a-rule.md`: the four questions in the order that stops a backtest selling itself.\n","# Backtest and forward test\n\nTwo different questions. A backtest asks what a rule would have done. A\nforward test asks what a position actually did from the moment it was\nwritten down.\n\n## Execution route\n\nPrefer the `option_backtest` MCP tool for a backtest and the\n`option_forward_test` MCP tool for the paper ledger. If the matching tool is\nnot available, use the `optiondesk` commands below. If neither MCP nor the\nCLI is available, say that no fresh result can be produced; do not invent\nfigures or present an example or remembered result as a new analysis.\n\n## Data boundary\n\nUse fresh provider data only when the tool reports that access is allowed.\nA local Yahoo adapter also requires the personal-use acknowledgement. A\nhosted tool must use a provider that is approved for public display, derived\noutputs, storage, and MCP delivery. Never bypass a provider refusal. When no\napproved tool is available, analyse a snapshot that the user supplied and\nhad the right to share. Otherwise, state that current figures are unavailable.\n\n## Backtest\n\n```\noptiondesk backtest SPY iron_condor --holding-days 30 --entry-every 5 --period 5y\n```\n\nEnters the structure on a fixed schedule, holds to expiry, settles against\nthe real close. Reports trades, win rate, mean return on capital at risk,\ntotal in risk units, drawdown, a permutation test, a bootstrap interval\nfor the mean, and the same schedule holding the underlying instead.\n\n## Forward test\n\n```\noptiondesk forward open --strategy iron_condor --thesis \"range bound into expiry\"\noptiondesk forward mark            # after a newer chain snapshot exists\noptiondesk forward status\noptiondesk forward close --id \u003Cid> --price 775\n```\n\n## What you must say about a result\n\nFour things, in this order, every time. The full argument for each is in\n`reference.md`; these are the versions you cannot skip.\n\n1. Quote the `honesty` field from the artifact before the headline number.\n   It is not boilerplate: premiums are modelled and entry and exit use the\n   same model, so the test cannot see an edge that comes from the market\n   disagreeing with that model.\n2. Give the benchmark alongside the result. A structure that is long the\n   market shows the market's drift, and without the benchmark that drift\n   gets credited to the strategy.\n3. Report the block sign-flip symmetry assumption and the block length.\n   Block boundaries can lose dependence. A strategy chosen after viewing\n   results needs a selection caveat. If the block covers the return sample,\n   the bootstrap has no variation; do not use its interval as evidence.\n4. Under thirty trades, decline to draw conclusions.\n\nFor a forward test, two more. It is paper, so entry and marks are mid\nquotes and a real entry would have crossed the spread on every leg; what it\nremoves is hindsight, not cost. And a position with a leg missing from the\nnewer chain comes back unmarkable rather than marked at zero. Report it\nthat way: a missing wing marked at zero turns a losing short spread into a\nfull credit win, which is the most flattering error available and appears\nexactly when the position is in trouble.\n\n## Reporting rules\n\nThese hold for every number this skill produces.\n\nCite the artifact path when reporting from it. The artifact is the record;\nprose is a summary of it, and a number quoted without its source cannot be\nchecked later.\n\nRead `degraded` before quoting anything. When it is true, say so and give\n`degraded_reason` first, in the same breath as the number rather than as a\nfootnote. Every command carries both fields in the summary it prints, not\nonly in the artifact.\n\nDo not re-derive numbers yourself. If a figure is not in the artifact, say\nit is not there rather than computing a replacement, and never substitute a\ndefault for a value the pipeline refused to produce.\n\nPremiums are model values or mid quotes from delayed third-party data. They\nare not fills, and a real entry crosses the spread on every leg.\n\nNever recommend a trade, an entry, an exit or a size. This is research\nsoftware and it is not investment advice. Present the analysis and let the\nreader decide.\nThe full terms are in DISCLAIMER.md, which ships beside this skill when it\nis installed from a package and sits at the repository root otherwise. The\nsubstance is already above: research software, not advice, modelled numbers\nthat are not fills.\n\n\n## What an audit found in these numbers, and what to say about it\n\nThree independent verifications recomputed this project's arithmetic in\n2026. The backtest statistics reproduced bit for bit. Two things about how\nthey are read did not, and both change what a result means.\n\n**The windows overlap.** A thirty day hold entered every five trading days\nshares twenty-five of its thirty days with its neighbour. Measured\nautocorrelation is positive through lag five and collapses at lag six, and\nthe effective sample is 64 to 88 rather than 233. The significance test and\nthe interval now use blocks: the test flips block signs and the bootstrap\nresamples blocks. The CLI summary carries `overlap_block` when significance is available;\nthe artifact stores `significance.block` and `interval.block` in available\nresults. When the block is above one, say so: the\np-value beside it is a block p-value, and the trade count is not the number\nof independent observations. Correcting this moved four structures from\nbelow 0.05 to above it, one from 0.0005 to 0.148.\n\n**A structure can enter trades and report no statistics.** When the maximum\nloss is unbounded there is no capital at risk to divide by, so every return\non risk is undefined and the statistics object is empty. Read\n`trades_entered`, not a trade count of zero. The run worked; the ratio has\nno denominator. Saying \"no trades\" there is wrong and sends a reader\nlooking for missing price history.\n\nBoth are in the artifact. Neither is in the headline figure, so it falls to\nyou to say them.\n\n## Going deeper\n\n- `reference.md`: the honesty rule in full, how the statistics are computed, and the caveat that outranks all of them.\n- `workflows\u002Fevaluate-a-rule.md`: the four questions in the order that stops a backtest selling itself.\n",{"name":5,"description":7},"main","347aedf8480cd92b21f761e97b7343a45898f5fa","plugins\u002FIman\u002Fagent-driven-options-desk-and-skills\u002Fskills\u002Foptions-backtest",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 options-backtest",{"tool":40,"command":41},"bunx","bunx skills add hashgraph-online\u002Fawesome-codex-plugins --skill options-backtest",{"tool":43,"command":44},"pnpm","pnpm dlx skills add hashgraph-online\u002Fawesome-codex-plugins --skill options-backtest","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FIman\u002Fagent-driven-options-desk-and-skills\u002Fskills\u002Foptions-backtest\u002FSKILL.md",true,[48,54],{"path":49,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":52,"sourceHtmlUrl":53},"reference.md","REFERENCE","参考文档",3609,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FIman\u002Fagent-driven-options-desk-and-skills\u002Fskills\u002Foptions-backtest\u002Freference.md",{"path":55,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":56,"sourceHtmlUrl":57},"workflows\u002Fevaluate-a-rule.md",1172,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FIman\u002Fagent-driven-options-desk-and-skills\u002Fskills\u002Foptions-backtest\u002Fworkflows\u002Fevaluate-a-rule.md",[59,69,77,85,93,101],{"skillNo":60,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":63,"licenseFileUrl":64,"sourceHtmlUrl":65,"categories":66,"keywords":67,"publishedAt":68},"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":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":63,"licenseFileUrl":73,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":68},"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":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":63,"licenseFileUrl":81,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":68},"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":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":63,"licenseFileUrl":89,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":68},"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":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":63,"licenseFileUrl":97,"sourceHtmlUrl":98,"categories":99,"keywords":100,"publishedAt":68},"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":102,"name":103,"nameZh":6,"description":104,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":63,"licenseFileUrl":105,"sourceHtmlUrl":106,"categories":107,"keywords":108,"publishedAt":68},"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",[],[]]