[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M75QJZ1434RFBZY188XAFZPH":3,"skill-same:01M75QJZ1434RFBZY188XAFZPH":50},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"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":23,"commitSha":24,"skillDirectory":25,"forksCount":26,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":29,"install":30,"resources":43},"01M75QJZ1434RFBZY188XAFZPH","cross-model-review-gate",null,"Two-model review before an irreversible step. A reviewer from a second lab checks the work, and every review is recorded against the exact commit and artifact hash. Learned from gnuchev's Open Research Club (a Claude author, an OpenAI reviewer, about three rounds per artifact). Use before submitting a structural benchmark row, publishing a tool or skill, declaring a route dead, or deploying.","odinfree\u002Fstorm-ecdsa-harness","odinfree","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F58338510?v=4","01M75QJA86AKR72RA1GBG2JGKV","01M75QJA8R22TWRQR8CYFXH6F7",4,"MIT","https:\u002F\u002Fgithub.com\u002Fodinfree\u002Fstorm-ecdsa-harness\u002Fblob\u002Fmain\u002Fskills\u002Fcross-model-review-gate\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: cross-model-review-gate\ndescription: \"Two-model review before an irreversible step. A reviewer from a second lab checks the work, and every review is recorded against the exact commit and artifact hash. Learned from gnuchev's Open Research Club (a Claude author, an OpenAI reviewer, about three rounds per artifact). Use before submitting a structural benchmark row, publishing a tool or skill, declaring a route dead, or deploying.\"\n---\n\n# Cross-model review gate\n\nA **receipt** is one reviewer's record of exactly what it checked about one exact revision. It reports checks; it does\nnot certify the claim. The gate: the irreversible step waits for a `no_concerns` receipt on the current revision **and**\nthe operator's go.\n\n## Loop\n\n1. **Author commits** the artifact. Record the commit id and every artifact hash the claim rests on (e.g. ops.bin\n   sha256, note file hash).\n2. **Reviewer = a different model family in a different harness** (Claude author -> GPT \u002F DeepSeek \u002F Kimi reviewer, or\n   the reverse). Brief it adversarially (\"refute this or name what was missed\") with paths, not conclusions. It writes a\n   receipt bound to that commit and those hashes:\n   - `checked` (each item, with method: re-ran, re-derived, read source at file:line, rebuilt `env -i`, ran the trusted\n     evaluator itself) and `not_checked` (explicit);\n   - observations, each a finding with severity;\n   - independence per axis (execution, implementation, data, design) and relationships (same operator: always yes);\n   - outcome: `no_concerns`, `concerns` or `serious_concerns`.\n3. **Author answers finding by finding**, adds **one regression check per finding**, lists what stays unverified, and\n   commits again.\n4. **Reviewer rechecks at the new commit** (only the delta plus the regression checks). Loop until `no_concerns`; about\n   three rounds is normal.\n5. **Gate:** submit \u002F publish \u002F seed only with `no_concerns` on the exact revision being shipped, plus the operator's go.\n   A changed byte means a new revision and a new receipt.\n\n## Benchmark variant (ecdsa.fail)\n\nThe strongest receipt is an independent rebuild: the reviewer rebuilds `env -i` from the committed defaults, checks the\nops sha256, runs the evaluator itself, and runs a fixed-input A\u002FB against the parent. A component another model wrote is\nchecked on live trajectories before integration. For notes: the reviewer checks every number against the logs, the\ncredits\u002Fdependencies against what was reused, and that required contract text is copied verbatim.\n\n## Wiring\n\nRun the reviewer read-only at its highest effort: a second CLI agent from another lab, or a Claude Fable subagent\n(`model: \"fable\"`; confirm the transcript reports the model you asked for, since a silent fallback voids the review).\nKeep each review record next to the artifact so the next revision's reviewer can diff against it.\n","# Cross-model review gate\n\nA **receipt** is one reviewer's record of exactly what it checked about one exact revision. It reports checks; it does\nnot certify the claim. The gate: the irreversible step waits for a `no_concerns` receipt on the current revision **and**\nthe operator's go.\n\n## Loop\n\n1. **Author commits** the artifact. Record the commit id and every artifact hash the claim rests on (e.g. ops.bin\n   sha256, note file hash).\n2. **Reviewer = a different model family in a different harness** (Claude author -> GPT \u002F DeepSeek \u002F Kimi reviewer, or\n   the reverse). Brief it adversarially (\"refute this or name what was missed\") with paths, not conclusions. It writes a\n   receipt bound to that commit and those hashes:\n   - `checked` (each item, with method: re-ran, re-derived, read source at file:line, rebuilt `env -i`, ran the trusted\n     evaluator itself) and `not_checked` (explicit);\n   - observations, each a finding with severity;\n   - independence per axis (execution, implementation, data, design) and relationships (same operator: always yes);\n   - outcome: `no_concerns`, `concerns` or `serious_concerns`.\n3. **Author answers finding by finding**, adds **one regression check per finding**, lists what stays unverified, and\n   commits again.\n4. **Reviewer rechecks at the new commit** (only the delta plus the regression checks). Loop until `no_concerns`; about\n   three rounds is normal.\n5. **Gate:** submit \u002F publish \u002F seed only with `no_concerns` on the exact revision being shipped, plus the operator's go.\n   A changed byte means a new revision and a new receipt.\n\n## Benchmark variant (ecdsa.fail)\n\nThe strongest receipt is an independent rebuild: the reviewer rebuilds `env -i` from the committed defaults, checks the\nops sha256, runs the evaluator itself, and runs a fixed-input A\u002FB against the parent. A component another model wrote is\nchecked on live trajectories before integration. For notes: the reviewer checks every number against the logs, the\ncredits\u002Fdependencies against what was reused, and that required contract text is copied verbatim.\n\n## Wiring\n\nRun the reviewer read-only at its highest effort: a second CLI agent from another lab, or a Claude Fable subagent\n(`model: \"fable\"`; confirm the transcript reports the model you asked for, since a silent fallback voids the review).\nKeep each review record next to the artifact so the next revision's reviewer can diff against it.\n",{"name":5,"description":7},"main","365c7327d2f1497e7febccb97758c0358e7e2579","skills\u002Fcross-model-review-gate",3,"https:\u002F\u002Fgithub.com\u002Fodinfree\u002Fstorm-ecdsa-harness","https:\u002F\u002Fgithub.com\u002Fodinfree","2026-10-30 23:13:43",{"source":8,"skillName":5,"commands":31,"prompt":41,"zipAvailable":42},[32,35,38],{"tool":33,"command":34},"npx","npx skills add odinfree\u002Fstorm-ecdsa-harness --skill cross-model-review-gate",{"tool":36,"command":37},"bunx","bunx skills add odinfree\u002Fstorm-ecdsa-harness --skill cross-model-review-gate",{"tool":39,"command":40},"pnpm","pnpm dlx skills add odinfree\u002Fstorm-ecdsa-harness --skill cross-model-review-gate","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fodinfree\u002Fstorm-ecdsa-harness\u002Fblob\u002Fmain\u002Fskills\u002Fcross-model-review-gate\u002FSKILL.md",true,[44],{"path":45,"resourceType":46,"resourceTypeDesc":47,"sizeBytes":48,"sourceHtmlUrl":49},"agents\u002Fopenai.yaml","REFERENCE","参考文档",176,"https:\u002F\u002Fgithub.com\u002Fodinfree\u002Fstorm-ecdsa-harness\u002Fblob\u002Fmain\u002Fskills\u002Fcross-model-review-gate\u002Fagents\u002Fopenai.yaml",[51,58,65,72,79,86],{"skillNo":52,"name":53,"nameZh":6,"description":54,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":55,"categories":56,"keywords":57,"publishedAt":18},"01M75QQC9A02AFE91366WNZZPA","verify-research-transfer","Check whether a literature finding supports a proposed performance optimization. Read the primary figures and the implementation source, then run a cheap falsifier before writing code or benchmarks.","https:\u002F\u002Fgithub.com\u002Fodinfree\u002Fstorm-ecdsa-harness\u002Fblob\u002Fmain\u002Fskills\u002Fverify-research-transfer\u002FSKILL.md",[],[],{"skillNo":59,"name":60,"nameZh":6,"description":61,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":62,"categories":63,"keywords":64,"publishedAt":18},"01M75QQ95WZ1J5HK6DNAGRPPYG","verify-paired-native-measurements","Audit the process, sample and archive evidence behind paired native benchmarks, especially wrappers around an unchanged official client. Use before admitting benchmark results or when reviewing the controller that produced them. Ordinary unit tests do not need this.","https:\u002F\u002Fgithub.com\u002Fodinfree\u002Fstorm-ecdsa-harness\u002Fblob\u002Fmain\u002Fskills\u002Fverify-paired-native-measurements\u002FSKILL.md",[],[],{"skillNo":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":18},"01M75QQ5CSVHARTW4XZ5SW9FBR","squares-in-squares-campaign","Pack n = 1..1000 unit squares into the smallest square (Kaggle \"Squares in Squares\", score sum L\u002Fsqrt(n) - 1). Use when improving, certifying or submitting packings, or when choosing the next search route. Covers the official-metric gates, the solver and MIS tools, the structure of the frontier, and the routes measured dead. The competition closed on 25 Oct 2026.","https:\u002F\u002Fgithub.com\u002Fodinfree\u002Fstorm-ecdsa-harness\u002Fblob\u002Fmain\u002Fskills\u002Fsquares-in-squares-campaign\u002FSKILL.md",[],[],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":18},"01M75QQ13S3G39R2VTAGF298ET","shot-autopsy","When a candidate fails shots its parent passes, find the structural cause before any nonce search. Reconstruct the exact failing shot, localize the first divergence, repair it by paying precision, and keep the case as a permanent regression. Learned from bulengerk's ecdsa.fail rows. Use when an edited candidate fails shots its parent passed, or when counts drift between builds.","https:\u002F\u002Fgithub.com\u002Fodinfree\u002Fstorm-ecdsa-harness\u002Fblob\u002Fmain\u002Fskills\u002Fshot-autopsy\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":18},"01M75QPY03H8X6CFN5YYY35E8R","send-to-claude-fable","Send a bounded task or review packet to the local Claude Code CLI on the Fable model and bring back its verdict. Use when you want an independent second opinion from a different model.","https:\u002F\u002Fgithub.com\u002Fodinfree\u002Fstorm-ecdsa-harness\u002Fblob\u002Fmain\u002Fskills\u002Fsend-to-claude-fable\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":18},"01M75QPVJ89VVS9KWEZ7JH27R4","rust-archive-build-binding","Prevent stale Cargo artifacts when a source archive is restored over a reused Rust target directory. Use for reproducible benchmark comparisons and for moving source archives between machines.","https:\u002F\u002Fgithub.com\u002Fodinfree\u002Fstorm-ecdsa-harness\u002Fblob\u002Fmain\u002Fskills\u002Frust-archive-build-binding\u002FSKILL.md",[],[]]