[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M75MVCGZ17HHGH9DFNCPAZVT":3,"skill-same:01M75MVCGZ17HHGH9DFNCPAZVT":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},"01M75MVCGZ17HHGH9DFNCPAZVT","sim-zero-mode",null,"Use when building\u002Ftesting an app or agent that depends on paid APIs or LLM calls and you must exercise plumbing\u002FUI\u002Fharness without spend or real intelligence, for CI, demos, local dev. Activates on test without burning API budget, demo without live calls, or fakes\u002Foffline mode.","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\u002Fsim-zero-mode\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: sim-zero-mode\ndescription: Use when building\u002Ftesting an app or agent that depends on paid APIs or LLM calls and you must exercise plumbing\u002FUI\u002Fharness without spend or real intelligence, for CI, demos, local dev. Activates on test without burning API budget, demo without live calls, or fakes\u002Foffline mode.\n---\n\n# Sim-Zero Mode\n\nA whole-application mode where **everything runs on fake data with NO real LLM\u002Fpaid\u002Fexternal calls.** The app **still works end-to-end — it just knows nothing.** Every screen renders, every flow completes, every agent step fires; only the *intelligence* and the *spend* are absent.\n\nThis is **fakes-over-mocks elevated to a first-class runtime mode**, not a test-only scaffold.\n\n## What sim-zero proves (and doesn't)\n- **Proves:** plumbing, wiring, UI rendering, navigation, the agent harness\u002Forchestration, state flow, error handling, contracts between components.\n- **Does NOT prove:** answer quality, model behavior, real third-party correctness. (That's what live evals are for — keep them separate.)\n\nSo: a green sim-zero run means \"the machine moves correctly,\" not \"the machine is smart.\" Both matter; sim-zero isolates the first cheaply.\n\n## Design rules\n1. **One switch, whole app.** A single config\u002Fflag (`SIM_ZERO=1`) flips every external boundary to a fake — not per-call opt-in. The boundary, not the caller, decides.\n2. **Fakes return plausible, deterministic, shaped data** that satisfies the real contract (same schema\u002Ftypes), so downstream code and UI behave exactly as in production. Deterministic → CI-stable.\n3. **No network\u002Fsecret required.** Sim-zero must run with zero credentials and zero egress — that's what makes it safe for CI and untrusted demos.\n4. **Honest labeling.** The UI\u002Flogs should make it discoverable that data is simulated (so a demo isn't mistaken for real intelligence).\n5. **Cover the error paths too.** Fakes should be able to simulate failures\u002Ftimeouts\u002Fempties, not just happy-path data.\n\n## Where it pays off\n- **CI:** run the full app\u002Fagent harness on every PR with no spend and no flakiness from external services.\n- **Local dev:** work offline, fast, free.\n- **Demos:** show the product working safely without live keys or unpredictable model output.\n- **Plumbing regression:** catch \"the wiring broke\" independently of \"the model changed.\"\n\n## The analog to generalize from\nA trading\u002Fagent system's **paper-mode** (executes the full pipeline against simulated fills, no real orders\u002Fmoney) is sim-zero for that domain. Generalize the pattern: **every agent and app should ship a sim-zero mode.** If you can't run your app with all external intelligence\u002Fspend switched off, your boundaries aren't clean enough — fixing that is itself valuable.\n\n## Anti-patterns\n- Per-call mocks scattered through tests instead of one app-wide boundary switch → drift, partial coverage, \"works in tests, not in the app\".\n- Fakes that don't match the real contract → green sim-zero, broken production.\n- Non-deterministic fakes → flaky CI.\n- Sim-zero that secretly still calls something paid → defeats the purpose; assert zero egress.\n","# Sim-Zero Mode\n\nA whole-application mode where **everything runs on fake data with NO real LLM\u002Fpaid\u002Fexternal calls.** The app **still works end-to-end — it just knows nothing.** Every screen renders, every flow completes, every agent step fires; only the *intelligence* and the *spend* are absent.\n\nThis is **fakes-over-mocks elevated to a first-class runtime mode**, not a test-only scaffold.\n\n## What sim-zero proves (and doesn't)\n- **Proves:** plumbing, wiring, UI rendering, navigation, the agent harness\u002Forchestration, state flow, error handling, contracts between components.\n- **Does NOT prove:** answer quality, model behavior, real third-party correctness. (That's what live evals are for — keep them separate.)\n\nSo: a green sim-zero run means \"the machine moves correctly,\" not \"the machine is smart.\" Both matter; sim-zero isolates the first cheaply.\n\n## Design rules\n1. **One switch, whole app.** A single config\u002Fflag (`SIM_ZERO=1`) flips every external boundary to a fake — not per-call opt-in. The boundary, not the caller, decides.\n2. **Fakes return plausible, deterministic, shaped data** that satisfies the real contract (same schema\u002Ftypes), so downstream code and UI behave exactly as in production. Deterministic → CI-stable.\n3. **No network\u002Fsecret required.** Sim-zero must run with zero credentials and zero egress — that's what makes it safe for CI and untrusted demos.\n4. **Honest labeling.** The UI\u002Flogs should make it discoverable that data is simulated (so a demo isn't mistaken for real intelligence).\n5. **Cover the error paths too.** Fakes should be able to simulate failures\u002Ftimeouts\u002Fempties, not just happy-path data.\n\n## Where it pays off\n- **CI:** run the full app\u002Fagent harness on every PR with no spend and no flakiness from external services.\n- **Local dev:** work offline, fast, free.\n- **Demos:** show the product working safely without live keys or unpredictable model output.\n- **Plumbing regression:** catch \"the wiring broke\" independently of \"the model changed.\"\n\n## The analog to generalize from\nA trading\u002Fagent system's **paper-mode** (executes the full pipeline against simulated fills, no real orders\u002Fmoney) is sim-zero for that domain. Generalize the pattern: **every agent and app should ship a sim-zero mode.** If you can't run your app with all external intelligence\u002Fspend switched off, your boundaries aren't clean enough — fixing that is itself valuable.\n\n## Anti-patterns\n- Per-call mocks scattered through tests instead of one app-wide boundary switch → drift, partial coverage, \"works in tests, not in the app\".\n- Fakes that don't match the real contract → green sim-zero, broken production.\n- Non-deterministic fakes → flaky CI.\n- Sim-zero that secretly still calls something paid → defeats the purpose; assert zero egress.\n",{"name":5,"description":7},"main","54007b08157feb09e5bb9d7ff5ce4ddd21625dbf","skills\u002Fsim-zero-mode",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 sim-zero-mode",{"tool":37,"command":38},"bunx","bunx skills add selamy-labs\u002Fagent-skills --skill sim-zero-mode",{"tool":40,"command":41},"pnpm","pnpm dlx skills add selamy-labs\u002Fagent-skills --skill sim-zero-mode","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fselamy-labs\u002Fagent-skills\u002Fblob\u002Fmain\u002Fskills\u002Fsim-zero-mode\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",[],[]]