[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6AC3MS7MX6WTJM0D66Y3SA5":3,"skill-same:01M6AC3MS7MX6WTJM0D66Y3SA5":96},{"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":36,"linkOnly":37,"markdownContent":38,"markdownBody":39,"frontMatter":40,"refName":41,"commitSha":42,"skillDirectory":43,"forksCount":44,"repositoryHtmlUrl":45,"repositoryHomepageUrl":46,"ownerHtmlUrl":47,"ownerBlogUrl":48,"ownerDescription":6,"updatedAt":49,"install":50,"resources":63},"01M6AC3MS7MX6WTJM0D66Y3SA5","changeset-validation",null,"Validate changesets in openai-agents-js using LLM judgment against git diffs (including uncommitted local changes). Use when packages\u002F or .changeset\u002F are modified, or when verifying PR changeset compliance and bump level.","openai\u002Fopenai-agents-js","openai","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F14957082?v=4","01M6AC29YGCR4S2NTJFV0G8B81","OpenAI","01M6AC3JCA5RPWKDHSP3JBJBH1",4011,"MIT","https:\u002F\u002Fgithub.com\u002Fopenai\u002Fopenai-agents-js\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fchangeset-validation\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,9,32,33,34,35],"validation","changeset validation","changeset","js","when","changes","judgment","local","changesets","bump","use","diffs","compliance","git","packages","pr","validate","2026-11-10 10:12:30",false,"---\nname: changeset-validation\ndescription: Validate changesets in openai-agents-js using LLM judgment against git diffs (including uncommitted local changes). Use when packages\u002F or .changeset\u002F are modified, or when verifying PR changeset compliance and bump level.\n---\n\n# Changeset Validation\n\n## Overview\n\nThis skill validates whether changesets correctly reflect package changes and follow the repository rules. It relies on the shared prompt in `references\u002Fvalidation-prompt.md` so local Codex reviews and GitHub Actions share the same logic.\nExperimental or preview-only feature additions that are explicitly labeled as such in the diff may remain a patch bump when they do not change existing behavior.\nMajor bumps are only allowed after the first major release; before that, do not use major bumps for feature-level changes.\n\n## Quick start\n\nLocal (Codex-driven):\n\n1. Run:\n   ```bash\n   pnpm changeset:validate-prompt\n   ```\n2. Apply the rules from `references\u002Fvalidation-prompt.md` to the generated prompt.\n3. Respond with a JSON verdict containing ok\u002Ferrors\u002Fwarnings\u002Frequired_bump (English-only strings).\n\nCI (Codex Action):\n\n1. Run:\n   ```bash\n   pnpm changeset:validate-prompt -- --ci --output .github\u002Fcodex\u002Fprompts\u002Fchangeset-validation.generated.md\n   ```\n2. Use `openai\u002Fcodex-action` with the generated prompt and JSON schema to get a structured verdict.\n\n## Workflow\n\n1. Generate the prompt context via `pnpm changeset:validate-prompt`.\n2. Apply the rules in `references\u002Fvalidation-prompt.md` to judge correctness.\n3. Provide a clear verdict and required bump (patch\u002Fminor\u002Fmajor\u002Fnone).\n4. If the changeset needs edits, update it and re-run the validation.\n\n## Branch-level changeset rule (do not skip)\n\n- If any `.changeset\u002F*.md` file is already present in the current branch diff, treat it as the active changeset. **Do not add a new changeset file.**\n- Instead, **update the existing changeset file** by rewriting its summary to reflect the **primary change relative to `main`**. Do not try to capture every incremental update.\n- Keep the summary at **one line**; replace the line as needed rather than appending. If you must include multiple points, compress them into a single line.\n\n## Shared source of truth\n\n- Keep the prompt file as the single source of validation rules.\n- Keep the script lightweight: it should only gather context and emit the prompt.\n\n## Resources\n\n- `references\u002Fvalidation-prompt.md`\n","# Changeset Validation\n\n## Overview\n\nThis skill validates whether changesets correctly reflect package changes and follow the repository rules. It relies on the shared prompt in `references\u002Fvalidation-prompt.md` so local Codex reviews and GitHub Actions share the same logic.\nExperimental or preview-only feature additions that are explicitly labeled as such in the diff may remain a patch bump when they do not change existing behavior.\nMajor bumps are only allowed after the first major release; before that, do not use major bumps for feature-level changes.\n\n## Quick start\n\nLocal (Codex-driven):\n\n1. Run:\n   ```bash\n   pnpm changeset:validate-prompt\n   ```\n2. Apply the rules from `references\u002Fvalidation-prompt.md` to the generated prompt.\n3. Respond with a JSON verdict containing ok\u002Ferrors\u002Fwarnings\u002Frequired_bump (English-only strings).\n\nCI (Codex Action):\n\n1. Run:\n   ```bash\n   pnpm changeset:validate-prompt -- --ci --output .github\u002Fcodex\u002Fprompts\u002Fchangeset-validation.generated.md\n   ```\n2. Use `openai\u002Fcodex-action` with the generated prompt and JSON schema to get a structured verdict.\n\n## Workflow\n\n1. Generate the prompt context via `pnpm changeset:validate-prompt`.\n2. Apply the rules in `references\u002Fvalidation-prompt.md` to judge correctness.\n3. Provide a clear verdict and required bump (patch\u002Fminor\u002Fmajor\u002Fnone).\n4. If the changeset needs edits, update it and re-run the validation.\n\n## Branch-level changeset rule (do not skip)\n\n- If any `.changeset\u002F*.md` file is already present in the current branch diff, treat it as the active changeset. **Do not add a new changeset file.**\n- Instead, **update the existing changeset file** by rewriting its summary to reflect the **primary change relative to `main`**. Do not try to capture every incremental update.\n- Keep the summary at **one line**; replace the line as needed rather than appending. If you must include multiple points, compress them into a single line.\n\n## Shared source of truth\n\n- Keep the prompt file as the single source of validation rules.\n- Keep the script lightweight: it should only gather context and emit the prompt.\n\n## Resources\n\n- `references\u002Fvalidation-prompt.md`\n",{"name":5,"description":7},"main","9b33d73a3ad696f0c43689d1428e901bfdc37fa0",".agents\u002Fskills\u002Fchangeset-validation",1017,"https:\u002F\u002Fgithub.com\u002Fopenai\u002Fopenai-agents-js","https:\u002F\u002Fopenai.github.io\u002Fopenai-agents-js\u002F","https:\u002F\u002Fgithub.com\u002Fopenai","https:\u002F\u002Fopenai.com\u002F","2026-11-13 03:14:49",{"source":8,"skillName":5,"commands":51,"prompt":61,"zipAvailable":62},[52,55,58],{"tool":53,"command":54},"npx","npx skills add openai\u002Fopenai-agents-js --skill changeset-validation",{"tool":56,"command":57},"bunx","bunx skills add openai\u002Fopenai-agents-js --skill changeset-validation",{"tool":59,"command":60},"pnpm","pnpm dlx skills add openai\u002Fopenai-agents-js --skill changeset-validation","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fopenai\u002Fopenai-agents-js\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fchangeset-validation\u002FSKILL.md",true,[64,70,74,80,84,88,92],{"path":65,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":68,"sourceHtmlUrl":69},"agents\u002Fopenai.yaml","REFERENCE","参考文档",276,"https:\u002F\u002Fgithub.com\u002Fopenai\u002Fopenai-agents-js\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fchangeset-validation\u002Fagents\u002Fopenai.yaml",{"path":71,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":72,"sourceHtmlUrl":73},"references\u002Fvalidation-prompt.md",4632,"https:\u002F\u002Fgithub.com\u002Fopenai\u002Fopenai-agents-js\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fchangeset-validation\u002Freferences\u002Fvalidation-prompt.md",{"path":75,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":78,"sourceHtmlUrl":79},"scripts\u002Fchangeset-assign-milestone.mjs","SCRIPT","脚本",7079,"https:\u002F\u002Fgithub.com\u002Fopenai\u002Fopenai-agents-js\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fchangeset-validation\u002Fscripts\u002Fchangeset-assign-milestone.mjs",{"path":81,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":82,"sourceHtmlUrl":83},"scripts\u002Fchangeset-prompt.mjs",14378,"https:\u002F\u002Fgithub.com\u002Fopenai\u002Fopenai-agents-js\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fchangeset-validation\u002Fscripts\u002Fchangeset-prompt.mjs",{"path":85,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":86,"sourceHtmlUrl":87},"scripts\u002Fchangeset-prompt.test.mjs",7926,"https:\u002F\u002Fgithub.com\u002Fopenai\u002Fopenai-agents-js\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fchangeset-validation\u002Fscripts\u002Fchangeset-prompt.test.mjs",{"path":89,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":90,"sourceHtmlUrl":91},"scripts\u002Fchangeset-validation-result.mjs",1691,"https:\u002F\u002Fgithub.com\u002Fopenai\u002Fopenai-agents-js\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fchangeset-validation\u002Fscripts\u002Fchangeset-validation-result.mjs",{"path":93,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":94,"sourceHtmlUrl":95},"scripts\u002Frun-fixtures.sh",4978,"https:\u002F\u002Fgithub.com\u002Fopenai\u002Fopenai-agents-js\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fchangeset-validation\u002Fscripts\u002Frun-fixtures.sh",[97,117,133,150,169,183],{"skillNo":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":108,"publishedAt":36},"01M6AC4R0A34BEB9E1929JHSQR","csv-workbench","Analyze CSV files in \u002Fmnt\u002Fdata and return concise numeric summaries.","https:\u002F\u002Fgithub.com\u002Fopenai\u002Fopenai-agents-js\u002Fblob\u002Fmain\u002Fexamples\u002Ftools\u002Fskills\u002Fcsv-workbench\u002FSKILL.md",[103],{"categoryNo":104,"categoryName":105,"taxonomyType":106,"taxonomyTypeDesc":107},"01JBSEEDCAT000000000000004","电子表格","SCENARIO","使用场景",[109,110,111,112,113,114,115,116],"csv workbench","csv","analyze csv files","summaries","concise","files","analyze","data",{"skillNo":118,"name":119,"nameZh":6,"description":120,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":121,"categories":122,"keywords":123,"publishedAt":36},"01M6AC4P55NFYE63B8X4TZ1YFB","credit-note-fixer","Fix the tiny credit-note formatting bug and rerun the exact targeted test command.","https:\u002F\u002Fgithub.com\u002Fopenai\u002Fopenai-agents-js\u002Fblob\u002Fmain\u002Fexamples\u002Fsandbox\u002Fdata\u002Fcoding-task\u002Fskills\u002Fcredit-note-fixer\u002FSKILL.md",[],[124,125,126,127,128,129,130,131,132],"credit note fixer","fixer","note","test","command","fix","bug","formatting","rerun",{"skillNo":134,"name":135,"nameZh":6,"description":136,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":137,"categories":138,"keywords":144,"publishedAt":36},"01M6AC4MKZF8EC8A477XH8Z87Y","invoice-total-fixer","Use when fixing invoice total calculations in the sandbox quickstart repository.","https:\u002F\u002Fgithub.com\u002Fopenai\u002Fopenai-agents-js\u002Fblob\u002Fmain\u002Fexamples\u002Fdocs\u002Fsandbox-agents\u002Fskills\u002Finvoice-total-fixer\u002FSKILL.md",[139],{"categoryNo":140,"categoryName":141,"taxonomyType":142,"taxonomyTypeDesc":143},"01JBSEEDCAT000000000000040","财务","PROFESSION","适用职业",[145,125,146,147,148,149,29,23],"invoice total fixer","invoice","sandbox","quickstart","repository",{"skillNo":151,"name":152,"nameZh":6,"description":153,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":154,"categories":155,"keywords":159,"publishedAt":36},"01M6AC4JTG74J4VWHBWJ1F2N20","test-coverage-improver","Measure JS SDK coverage or address measured coverage gaps. Use for coverage audits and metric regressions, not routine test additions.","https:\u002F\u002Fgithub.com\u002Fopenai\u002Fopenai-agents-js\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Ftest-coverage-improver\u002FSKILL.md",[156],{"categoryNo":157,"categoryName":158,"taxonomyType":106,"taxonomyTypeDesc":107},"01JBSEEDCAT000000000000008","测试与质量",[160,161,162,127,163,164,165,166,167,29,168,22],"test coverage","coverage","test coverage improver","for","metric","gaps","routine","coverage gaps","sdk",{"skillNo":170,"name":171,"nameZh":6,"description":172,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":173,"categories":174,"keywords":175,"publishedAt":36},"01M6AC4GVZRPJYWK9HTDD6M11N","sensitive-logging-audit","Audit or fix sensitive-data exposure in JS SDK diagnostics, exceptions, logging, and telemetry.","https:\u002F\u002Fgithub.com\u002Fopenai\u002Fopenai-agents-js\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fsensitive-logging-audit\u002FSKILL.md",[],[176,177,178,168,179,180,116,181,22,129,182],"audit","logging","sensitive logging audit","telemetry","diagnostics","sensitive-data","data exposure",{"skillNo":184,"name":185,"nameZh":6,"description":186,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":187,"categories":188,"keywords":192,"publishedAt":36},"01M6AC4EAT4R58F8R0R24GTT5N","runtime-behavior-probe","Plan and, after explicit approval, execute runtime-behavior probes for local or live integrations. Use only when explicitly invoked to verify behavior that code review and normal tests cannot settle; define a controlled validation matrix, keep disposable JS probes outside tracked paths, and report observed evidence.","https:\u002F\u002Fgithub.com\u002Fopenai\u002Fopenai-agents-js\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fruntime-behavior-probe\u002FSKILL.md",[189],{"categoryNo":190,"categoryName":191,"taxonomyType":106,"taxonomyTypeDesc":107},"01JBSEEDCAT000000000000007","代码审查",[193,194,195,196,197,198,199,200,19,201,202,29,203,204,26,205,206,207,163,23,208,209],"runtime","probe","behavior","runtime behavior probe","normal","review","code","report","plan","integrations","only","evidence","define","tests","keep","settle","code review"]