[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M75FFH6EWRYJD9AM8AHZDXQB":3,"skill-same:01M75FFH6EWRYJD9AM8AHZDXQB":43},{"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":23,"commitSha":24,"skillDirectory":25,"forksCount":13,"repositoryHtmlUrl":26,"repositoryHomepageUrl":6,"ownerHtmlUrl":27,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":28,"install":29,"resources":42},"01M75FFH6EWRYJD9AM8AHZDXQB","verify-review-reservation",null,"Recheck the bounded identity-ledger reservation invariant after lock, hash-check or publication changes.","aharada54914\u002Fsdd-forge","aharada54914","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F40755043?v=4","01M75FFC4V7WXZF0PK9RYWHNGF","01M75FFC5YJJ11B7MDCRVWB9Z6",0,"MIT","https:\u002F\u002Fgithub.com\u002Faharada54914\u002Fsdd-forge\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fverify-review-reservation\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: verify-review-reservation\ndescription: Recheck the bounded identity-ledger reservation invariant after lock, hash-check or publication changes.\n---\n\n# Verify review reservation\n\nThis opt-in verification profile is for the sdd-forge source repository. It is\nsupplemental evidence; it never replaces normal tests, review or task gates.\n\n## Property and scope\n\nTwo contenders holding the same original ledger hash cannot both succeed in one\nreservation attempt. The user harm is two reviewers admitted against conflicting\nidentity history. `tests\u002Ffixtures\u002Fproject-skills\u002Fformal-review-reservation\u002Fmapping.json`\npins the source and maps atomic mkdir, the\npost-lock hash comparison, staged append\u002Frename and lock release to model actions.\nThe finite model has two actors, one attempt each, and no crash, retry, stale-lock\nrecovery, malicious filesystem or Windows semantics. All writers must honor the\nsame lock; mkdir and same-directory rename must be atomic and hashes collision-free.\nA finite-model PASS is not a proof of all implementation schedules or operating\nsystems.\n\nThe covered source is `plugins\u002Fsdd-quality-loop\u002Fscripts\u002Fvalidate-review-context-set.sh`\nin the combined integration candidate, SHA-256\n`8d4397f7120d07b6eb0513049c519367de7e9cd1d61ea2814c1b8ffcd28dedcf`.\nThe unchanged acquire\u002Fhash-check\u002Fappend\u002Frename\u002Frelease tail has SHA-256\n`099073aafef9082cab371bfab889a19afe4e40a3f9d791739ceb820052a4a92c`.\nEvidence for the combined candidate is in\n`reports\u002Fverification\u002Fformal-reservation-combined-20261028\u002F`. The separately\nrecorded historical asset check (id 683491413) is in\n`reports\u002Fverification\u002Fformal-reservation-asset-683491413-20261029\u002F`; earlier\nmain-based evidence remains historical. Use the local\n`pstack-maintain-formal-verification-skill` procedure when the mapping drifts.\n\n## Tool choice and setup\n\nTLC from the fixed `v1.7.4` release asset explores the interleavings directly\nand is smaller here than translating shell\u002Fjq\u002Ffilesystem operations into a\ncode-level verifier. Java must be installed. Release asset `184694200` is\navailable from `https:\u002F\u002Fgithub.com\u002Ftlaplus\u002Ftlaplus\u002Freleases\u002Fdownload\u002Fv1.7.4\u002Ftla2tools.jar`;\nquery `gh api repos\u002Ftlaplus\u002Ftlaplus\u002Freleases\u002Fassets\u002F184694200` for metadata.\nDownload the jar outside the repository and verify SHA-256\n`936a262061c914694dfd669a543be24573c45d5aa0ff20a8b96b23d01e050e88`.\nThe helper rejects all other bytes before creating an evidence directory.\nThese bytes report `TLC2 Version 2.19 of 08 August 2024 (rev: 5a47802)`.\n\nThe previously selected v1.8.0 asset `683491413` returned HTTP 404 on 2026-10-31;\nassets under that tag had already been replaced repeatedly. The stable release\nis sufficient for this unchanged finite model and avoids following the moving\nasset. This does not guarantee perpetual upstream availability: if the exact\nasset disappears or differs, stop rather than accepting a new jar implicitly.\nHistorical v1.8.0 evidence remains unchanged. The new tool's negative, baseline\nand actual-code race observations are recorded separately in\n`reports\u002Fverification\u002Fformal-reservation-stable-20261031\u002F`.\nBash, jq and sha256sum are required for the Linux real-code replay. No network\ncall occurs during verification.\n\n## Run and observe\n\nFrom the source repository, execute:\n\n```sh\npython3 tests\u002Fverify-review-reservation.py --jar \u002Fpath\u002Fto\u002Ftla2tools-1.7.4.jar --output \u002Fpath\u002Fto\u002Fnew-evidence-directory\n```\n\nThe output directory must not exist. The helper first verifies the source pin,\nthen runs the lock-removed negative model and the intact baseline. It retains TLC\nlogs, counterexample traces, tool hash, source hash and measured time. It also\nextracts the actual reservation transaction from the pinned Bash script into\nisolated scratch state and invokes two competing processes. The negative mutates\nthat extracted code's acquire\u002Frelease guard; both calls must succeed. The intact\ncode must accept only one. The fixture replaces unrelated input-validation setup,\nso this proves the reservation tail's observed behavior, not the whole review CLI.\nFor the negative replay the parent releases both contenders only after both\nreach the post-hash-check barrier; timeout is a synchronization failure.\n\n## Maintenance and cleanup\n\nA source-pin mismatch is blocked. Inspect changed code\u002Fmodel correspondence before\nupdating the pin; do not update it solely to make the command pass. A baseline\ncounterexample is a product\u002Fmodel investigation, never permission to weaken the\nproperty. Scratch mutations stay outside the product checkout and are removed\nwhen each replay finishes; retained evidence survives. No scheduled invocation or\nhost-support claim is implied. Re-run normal project tests independently.\n","# Verify review reservation\n\nThis opt-in verification profile is for the sdd-forge source repository. It is\nsupplemental evidence; it never replaces normal tests, review or task gates.\n\n## Property and scope\n\nTwo contenders holding the same original ledger hash cannot both succeed in one\nreservation attempt. The user harm is two reviewers admitted against conflicting\nidentity history. `tests\u002Ffixtures\u002Fproject-skills\u002Fformal-review-reservation\u002Fmapping.json`\npins the source and maps atomic mkdir, the\npost-lock hash comparison, staged append\u002Frename and lock release to model actions.\nThe finite model has two actors, one attempt each, and no crash, retry, stale-lock\nrecovery, malicious filesystem or Windows semantics. All writers must honor the\nsame lock; mkdir and same-directory rename must be atomic and hashes collision-free.\nA finite-model PASS is not a proof of all implementation schedules or operating\nsystems.\n\nThe covered source is `plugins\u002Fsdd-quality-loop\u002Fscripts\u002Fvalidate-review-context-set.sh`\nin the combined integration candidate, SHA-256\n`8d4397f7120d07b6eb0513049c519367de7e9cd1d61ea2814c1b8ffcd28dedcf`.\nThe unchanged acquire\u002Fhash-check\u002Fappend\u002Frename\u002Frelease tail has SHA-256\n`099073aafef9082cab371bfab889a19afe4e40a3f9d791739ceb820052a4a92c`.\nEvidence for the combined candidate is in\n`reports\u002Fverification\u002Fformal-reservation-combined-20261028\u002F`. The separately\nrecorded historical asset check (id 683491413) is in\n`reports\u002Fverification\u002Fformal-reservation-asset-683491413-20261029\u002F`; earlier\nmain-based evidence remains historical. Use the local\n`pstack-maintain-formal-verification-skill` procedure when the mapping drifts.\n\n## Tool choice and setup\n\nTLC from the fixed `v1.7.4` release asset explores the interleavings directly\nand is smaller here than translating shell\u002Fjq\u002Ffilesystem operations into a\ncode-level verifier. Java must be installed. Release asset `184694200` is\navailable from `https:\u002F\u002Fgithub.com\u002Ftlaplus\u002Ftlaplus\u002Freleases\u002Fdownload\u002Fv1.7.4\u002Ftla2tools.jar`;\nquery `gh api repos\u002Ftlaplus\u002Ftlaplus\u002Freleases\u002Fassets\u002F184694200` for metadata.\nDownload the jar outside the repository and verify SHA-256\n`936a262061c914694dfd669a543be24573c45d5aa0ff20a8b96b23d01e050e88`.\nThe helper rejects all other bytes before creating an evidence directory.\nThese bytes report `TLC2 Version 2.19 of 08 August 2024 (rev: 5a47802)`.\n\nThe previously selected v1.8.0 asset `683491413` returned HTTP 404 on 2026-10-31;\nassets under that tag had already been replaced repeatedly. The stable release\nis sufficient for this unchanged finite model and avoids following the moving\nasset. This does not guarantee perpetual upstream availability: if the exact\nasset disappears or differs, stop rather than accepting a new jar implicitly.\nHistorical v1.8.0 evidence remains unchanged. The new tool's negative, baseline\nand actual-code race observations are recorded separately in\n`reports\u002Fverification\u002Fformal-reservation-stable-20261031\u002F`.\nBash, jq and sha256sum are required for the Linux real-code replay. No network\ncall occurs during verification.\n\n## Run and observe\n\nFrom the source repository, execute:\n\n```sh\npython3 tests\u002Fverify-review-reservation.py --jar \u002Fpath\u002Fto\u002Ftla2tools-1.7.4.jar --output \u002Fpath\u002Fto\u002Fnew-evidence-directory\n```\n\nThe output directory must not exist. The helper first verifies the source pin,\nthen runs the lock-removed negative model and the intact baseline. It retains TLC\nlogs, counterexample traces, tool hash, source hash and measured time. It also\nextracts the actual reservation transaction from the pinned Bash script into\nisolated scratch state and invokes two competing processes. The negative mutates\nthat extracted code's acquire\u002Frelease guard; both calls must succeed. The intact\ncode must accept only one. The fixture replaces unrelated input-validation setup,\nso this proves the reservation tail's observed behavior, not the whole review CLI.\nFor the negative replay the parent releases both contenders only after both\nreach the post-hash-check barrier; timeout is a synchronization failure.\n\n## Maintenance and cleanup\n\nA source-pin mismatch is blocked. Inspect changed code\u002Fmodel correspondence before\nupdating the pin; do not update it solely to make the command pass. A baseline\ncounterexample is a product\u002Fmodel investigation, never permission to weaken the\nproperty. Scratch mutations stay outside the product checkout and are removed\nwhen each replay finishes; retained evidence survives. No scheduled invocation or\nhost-support claim is implied. Re-run normal project tests independently.\n",{"name":5,"description":7},"main","0f4e3268b5403855008ae089d3c1611430a41987",".agents\u002Fskills\u002Fverify-review-reservation","https:\u002F\u002Fgithub.com\u002Faharada54914\u002Fsdd-forge","https:\u002F\u002Fgithub.com\u002Faharada54914","2026-11-15 02:49:38",{"source":8,"skillName":5,"commands":30,"prompt":40,"zipAvailable":41},[31,34,37],{"tool":32,"command":33},"npx","npx skills add aharada54914\u002Fsdd-forge --skill verify-review-reservation",{"tool":35,"command":36},"bunx","bunx skills add aharada54914\u002Fsdd-forge --skill verify-review-reservation",{"tool":38,"command":39},"pnpm","pnpm dlx skills add aharada54914\u002Fsdd-forge --skill verify-review-reservation","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Faharada54914\u002Fsdd-forge\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fverify-review-reservation\u002FSKILL.md",true,[],[44,52,57,64,71,78],{"skillNo":45,"name":46,"nameZh":6,"description":47,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":48,"categories":49,"keywords":50,"publishedAt":51},"01M7DY6PWMGRM0GFNBXAE2RP3K","status","Show a read-only Jira-style six-view SDD dashboard in the initiating parent's Sites or Claude Artifacts, with source freshness and failure visibility.","https:\u002F\u002Fgithub.com\u002Faharada54914\u002Fsdd-forge\u002Fblob\u002Fmain\u002Fplugins\u002Fsdd-ship\u002Fskills\u002Fstatus\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"skillNo":53,"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":54,"categories":55,"keywords":56,"publishedAt":18},"01M75FN16WRENJ2A9CXZCXVKBQ","https:\u002F\u002Fgithub.com\u002Faharada54914\u002Fsdd-forge\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fproject-skills\u002Fformal-review-reservation\u002FSKILL.md",[],[],{"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":14,"licenseFileUrl":6,"sourceHtmlUrl":61,"categories":62,"keywords":63,"publishedAt":18},"01M75FMW90YZDCB7QNJ8K5KGKG","aws-cdk","Authors, deploys, and troubleshoots AWS infrastructure using CDK with TypeScript or Python. Covers best practices, stack architecture, and construct patterns. Applies when writing CDK constructs, bootstrapping environments, running cdk deploy\u002Fsynth\u002Fdiff, fixing CDK or CloudFormation errors, planning stack structure, importing existing resources, resolving drift, or refactoring stacks without resource replacement.","https:\u002F\u002Fgithub.com\u002Faharada54914\u002Fsdd-forge\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fcloud-orchestration\u002Faws-bundle\u002Fupstream\u002Fplugins\u002Faws-core\u002Fskills\u002Faws-cdk\u002FSKILL.md",[],[],{"skillNo":65,"name":66,"nameZh":6,"description":67,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":68,"categories":69,"keywords":70,"publishedAt":18},"01M75FMSTFNT7EQSZY81T4WRHN","quality-gate","Independently verify an Implementation Complete task with a Default-FAIL verification contract, deterministic checks, and an isolated critical reviewer, then decide whether it is Done.","https:\u002F\u002Fgithub.com\u002Faharada54914\u002Fsdd-forge\u002Fblob\u002Fmain\u002Fspecs\u002Fsdd-domain-multitarget\u002Fverification\u002FT-003\u002Fattempt10-20261016\u002Fbaseline\u002Fplugins\u002Fsdd-quality-loop\u002Fskills\u002Fquality-gate\u002FSKILL.md",[],[],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":18},"01M75FMPM8FDE4NQ6FFY7KB83Y","ship","Implement approved SDD tasks through the quality gate to Done — the second of the two-command workflow. Run after \u002Fsdd-bootstrap:bootstrap and human task approval.","https:\u002F\u002Fgithub.com\u002Faharada54914\u002Fsdd-forge\u002Fblob\u002Fmain\u002Fspecs\u002Fquality-loop-fixes\u002Fhuman-copy\u002Fplugins\u002Fsdd-ship\u002Fskills\u002Fship\u002FSKILL.md",[],[],{"skillNo":79,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":18},"01M75FMK3G0EPXW77XK8ED3F2E","https:\u002F\u002Fgithub.com\u002Faharada54914\u002Fsdd-forge\u002Fblob\u002Fmain\u002Fspecs\u002Fmcp-readonly-preflight\u002Fhuman-copy\u002Fplugins\u002Fsdd-ship\u002Fskills\u002Fship\u002FSKILL.md",[],[]]