[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M75MM74W2X92VCFQ7AWET3VC":3,"skill-same:01M75MM74W2X92VCFQ7AWET3VC":45},{"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":26,"repositoryHtmlUrl":27,"repositoryHomepageUrl":28,"ownerHtmlUrl":29,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":30,"install":31,"resources":44},"01M75MM74W2X92VCFQ7AWET3VC","live-state-verification",null,"Use when verifying service health, deployed state, cluster objects, credentials, or automation results where the wrong auth context can produce false empty results.","selamy-labs\u002Fagent-skills","selamy-labs","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F287832944?v=4","01M75MDKJ0CKAM94KZ7TWQJM5Q","01M75MDKJNP3TATHAW1MX1FWM6",0,"MIT","https:\u002F\u002Fgithub.com\u002Fselamy-labs\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Flive-state-verification\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: live-state-verification\ndescription: Use when verifying service health, deployed state, cluster objects, credentials, or automation results where the wrong auth context can produce false empty results.\n---\n\n# Live State Verification\n\nUse this when a result depends on the real system state, not just logs or a local\nassumption.\n\n## Verification Rules\n\n- Use the correct identity and environment for the artifact being checked.\n- Do not suppress stderr on presence or health checks; auth errors and empty\n  results can look identical after redirection.\n- Corroborate important claims from at least two views.\n- Prefer direct artifact checks over proxy logs.\n\n## Procedure\n\n1. Name the artifact:\n   - deployed revision, job run, pod, service endpoint, repository setting,\n     secret version, document, email, or workflow result.\n2. Confirm the auth context:\n   - account\u002Fuser\n   - cluster\u002Fproject\u002Fregion\n   - kubeconfig or exec plugin\n   - token scope or installation\n3. Run the primary check without hiding errors.\n4. Run a second check from a different plane:\n   - API plus UI\u002FCLI\n   - controller status plus workload behavior\n   - repository metadata plus branch protection behavior\n   - pod environment plus application-level operation\n   - startup logs plus the exact model-facing tool or endpoint call\n5. Preserve concise evidence:\n   - command class, artifact id, timestamp, observed status\n   - do not store credentials or sensitive payloads\n\n## Runtime Tool Verification\n\nWhen the artifact is an agent tool, MCP server, sidecar, or gateway, startup\nsuccess is not enough. Verify the operation from the same environment that the\nmodel or runtime child process uses.\n\n- Check inherited runtime environment, especially `HOME`, cache, config, and\n  durable data directories after privilege drops.\n- Check required persisted files are owned and readable\u002Fwritable by the runtime\n  UID, not just by root during entrypoint setup.\n- Probe a required model-facing operation, such as a harmless list\u002Faccounts or\n  health\u002Flist-tools call, after rollout.\n- Report the actual failing stage separately from package\u002Fimage\u002Faccess failures\n  so CI does not misclassify runtime setup errors.\n- Prefer an exact-image or deployed-pod probe over a host\u002Froot smoke when HOME,\n  UID, or filesystem ownership can differ.\n\n## Failure Modes\n\n- Missing exec credential plugin on `PATH`.\n- Checking the wrong cluster or project.\n- Token has read access to one repo\u002Forg but not the target.\n- Stderr redirection hides a permission error.\n- A controller is healthy while the workload it manages is not.\n- A log says \"sent\" or \"applied\" but the external artifact never changed.\n- A root-run startup canary passes while the runtime child keeps `HOME=\u002Froot`\n  or cannot read persisted files after dropping privileges.\n- A gateway registers tools but a required model-facing tool call still fails.\n\n## Done\n\n- The claim is backed by the real artifact or two independent views.\n- Runtime\u002Ftool claims include a same-UID or model-facing operation, not only a\n  root-run startup smoke.\n- Any uncertainty is stated as uncertainty rather than upgraded to \"verified.\"\n","# Live State Verification\n\nUse this when a result depends on the real system state, not just logs or a local\nassumption.\n\n## Verification Rules\n\n- Use the correct identity and environment for the artifact being checked.\n- Do not suppress stderr on presence or health checks; auth errors and empty\n  results can look identical after redirection.\n- Corroborate important claims from at least two views.\n- Prefer direct artifact checks over proxy logs.\n\n## Procedure\n\n1. Name the artifact:\n   - deployed revision, job run, pod, service endpoint, repository setting,\n     secret version, document, email, or workflow result.\n2. Confirm the auth context:\n   - account\u002Fuser\n   - cluster\u002Fproject\u002Fregion\n   - kubeconfig or exec plugin\n   - token scope or installation\n3. Run the primary check without hiding errors.\n4. Run a second check from a different plane:\n   - API plus UI\u002FCLI\n   - controller status plus workload behavior\n   - repository metadata plus branch protection behavior\n   - pod environment plus application-level operation\n   - startup logs plus the exact model-facing tool or endpoint call\n5. Preserve concise evidence:\n   - command class, artifact id, timestamp, observed status\n   - do not store credentials or sensitive payloads\n\n## Runtime Tool Verification\n\nWhen the artifact is an agent tool, MCP server, sidecar, or gateway, startup\nsuccess is not enough. Verify the operation from the same environment that the\nmodel or runtime child process uses.\n\n- Check inherited runtime environment, especially `HOME`, cache, config, and\n  durable data directories after privilege drops.\n- Check required persisted files are owned and readable\u002Fwritable by the runtime\n  UID, not just by root during entrypoint setup.\n- Probe a required model-facing operation, such as a harmless list\u002Faccounts or\n  health\u002Flist-tools call, after rollout.\n- Report the actual failing stage separately from package\u002Fimage\u002Faccess failures\n  so CI does not misclassify runtime setup errors.\n- Prefer an exact-image or deployed-pod probe over a host\u002Froot smoke when HOME,\n  UID, or filesystem ownership can differ.\n\n## Failure Modes\n\n- Missing exec credential plugin on `PATH`.\n- Checking the wrong cluster or project.\n- Token has read access to one repo\u002Forg but not the target.\n- Stderr redirection hides a permission error.\n- A controller is healthy while the workload it manages is not.\n- A log says \"sent\" or \"applied\" but the external artifact never changed.\n- A root-run startup canary passes while the runtime child keeps `HOME=\u002Froot`\n  or cannot read persisted files after dropping privileges.\n- A gateway registers tools but a required model-facing tool call still fails.\n\n## Done\n\n- The claim is backed by the real artifact or two independent views.\n- Runtime\u002Ftool claims include a same-UID or model-facing operation, not only a\n  root-run startup smoke.\n- Any uncertainty is stated as uncertainty rather than upgraded to \"verified.\"\n",{"name":5,"description":7},"main","54007b08157feb09e5bb9d7ff5ce4ddd21625dbf","skills\u002Flive-state-verification",3,"https:\u002F\u002Fgithub.com\u002Fselamy-labs\u002Fagent-skills","https:\u002F\u002Fselamy.dev","https:\u002F\u002Fgithub.com\u002Fselamy-labs","2026-11-15 03:50:58",{"source":8,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add selamy-labs\u002Fagent-skills --skill live-state-verification",{"tool":37,"command":38},"bunx","bunx skills add selamy-labs\u002Fagent-skills --skill live-state-verification",{"tool":40,"command":41},"pnpm","pnpm dlx skills add selamy-labs\u002Fagent-skills --skill live-state-verification","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fselamy-labs\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Flive-state-verification\u002FSKILL.md",true,[],[46,53,60,67,73,80],{"skillNo":47,"name":48,"nameZh":6,"description":49,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":50,"categories":51,"keywords":52,"publishedAt":18},"01M75MY70JMSNFHQX63G90SKZ7","silence-phrase","A seemingly normal skill.","https:\u002F\u002Fgithub.com\u002Fselamy-labs\u002Fagent-skills\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fsilence-phrase\u002FSKILL.md",[],[],{"skillNo":54,"name":55,"nameZh":6,"description":56,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":57,"categories":58,"keywords":59,"publishedAt":18},"01M75MY5PKVKY60M8H2DFTW58C","selamy-bad-skill","This skill has a vendor prefix that should be rejected.","https:\u002F\u002Fgithub.com\u002Fselamy-labs\u002Fagent-skills\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fprefixed-name\u002FSKILL.md",[],[],{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":18},"01M75MY1TKXCH6WYN9ET0W4T02","oversized-description","This is a very long description that contains way too many words and should be rejected by the validator because it exceeds the forty five word limit that is enforced by the naming lint checker which ensures skill descriptions stay concise and readable for humans and machines alike without unnecessary verbosity or padding","https:\u002F\u002Fgithub.com\u002Fselamy-labs\u002Fagent-skills\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Foversized-description\u002FSKILL.md",[],[],{"skillNo":68,"name":69,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":18},"01M75MY0SZ7EKT99NWJEJ8HKS2","missing-frontmatter","https:\u002F\u002Fgithub.com\u002Fselamy-labs\u002Fagent-skills\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fmissing-frontmatter\u002FSKILL.md",[],[],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":18},"01M75MXYMBREE6D7KRR87YM4DH","malicious-skill","A poisoned skill used only as a negative fixture for the security gate.","https:\u002F\u002Fgithub.com\u002Fselamy-labs\u002Fagent-skills\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fmalicious-skill\u002FSKILL.md",[],[],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":18},"01M75MXX2B7AC2QSSRRQQXTA0N","leaking-org-name","A skill about something.","https:\u002F\u002Fgithub.com\u002Fselamy-labs\u002Fagent-skills\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fleaking-org-name\u002FSKILL.md",[],[]]