[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M77VFHGGPAQY8ES364WB7GDZ":3,"skill-same:01M77VFHGGPAQY8ES364WB7GDZ":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},"01M77VFHGGPAQY8ES364WB7GDZ","using-ldd",null,"Use at the start of any conversation, and whenever the user mentions LDD, loss-driven development, loss, gradient, SGD on code, drift, refinement loop, outer loop, inner loop, method evolution, or says \"LDD:\" \u002F \"apply LDD\". Establishes how to dispatch the ten LDD skills and when each fires. Must be the first skill considered in any coding task where LDD is available.","CorvinLabs\u002FCorvinOS","CorvinLabs","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F289506478?v=4","01M77VCHYED8C391HPBTNYP0HS","01M77VCHZ5K92DH3W6SPN8Y4P2",25,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FCorvinLabs\u002FCorvinOS\u002Fblob\u002Fmain\u002Fcorvin_operator\u002Fbundle\u002Fskills\u002Fldd\u002Fusing-ldd\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: using-ldd\ndescription: Use at the start of any conversation, and whenever the user mentions LDD, loss-driven development, loss, gradient, SGD on code, drift, refinement loop, outer loop, inner loop, method evolution, or says \"LDD:\" \u002F \"apply LDD\". Establishes how to dispatch the ten LDD skills and when each fires. Must be the first skill considered in any coding task where LDD is available.\n---\n\n# Using LDD — the bundle entry-point\n\n## Overview\n\nLoss-Driven Development (LDD) is a ten-skill bundle that treats code changes as SGD steps and forbids overfitting to the current test. This entry-skill exists so you (the agent) know **when to reach for which LDD skill** without the user having to name each one by hand.\n\n**Core principle:** if the user prefixes their message with `LDD:` or mentions any of the trigger phrases below, LDD discipline is explicitly requested. Match their intent to the right sub-skill and announce which one you are applying.\n\n## Trigger phrases (user → skill mapping)\n\nWhen the user's message contains any of these patterns, invoke the paired skill.\n\n| User signal | Invoke |\n|---|---|\n| `LDD:` prefix, \"apply LDD\", \"use LDD\" | Enter full LDD mode — default entry = `loop-driven-engineering` unless a more specific sub-skill matches below |\n| \"failing test\", \"CI is red\", \"flaky\", \"one-off failure\", \"intermittent\" | First `reproducibility-first`, then `root-cause-by-layer` if the failure is real |\n| \"bug\", \"error\", \"exception\", \"unexpected behavior\", \"why is this breaking\" | `root-cause-by-layer` |\n| \"I've tried this 3 times\", \"keeps failing the same way\", five fix-commits in one area | `loss-backprop-lens` (local-minimum trap) |\n| \"this fix works but I'm not sure it generalizes\", \"will this break sibling tests\" | `loss-backprop-lens` (generalization check) |\n| \"I'm mid-debug\", \"is the fix done yet\", before closing any fix-loop | `e2e-driven-iteration` |\n| \"should we ship this\", \"is this the right approach\", design trade-off | `dialectical-reasoning` |\n| \"this doc\u002Fdiff\u002Foutput is okay but could be better\", \"polish this\" | `iterative-refinement` |\n| \"same thing keeps happening across tasks\", \"the skill itself might be wrong\" | `method-evolution` |\n| \"is this codebase healthy\", release-candidate review, weekly check | `drift-detection` |\n| \"about to commit\", \"ready to merge\", \"declaring this done\" | `docs-as-definition-of-done` |\n\n## The \"LDD:\" buzzword\n\nUsers who want **guaranteed** LDD activation (no reliance on auto-triggering) can prefix their message with `LDD:`. When you see this prefix:\n\n1. Load `loop-driven-engineering` as the orchestrating skill\n2. Before any code, announce in one sentence which sub-skill you are reaching for and why\n3. Apply that sub-skill's discipline literally, not \"in spirit\"\n4. Report which rubric items you satisfied at the end of the task\n\nExample:\n\n> User: `LDD: the checkout test is failing and I need to ship in an hour`\n> You: \"Invoking `reproducibility-first` first to check whether this is a real gradient or noise. [runs check] Confirmed reproducible — invoking `root-cause-by-layer` next to diagnose at layer 4\u002F5 before editing.\"\n\n## Announcing skill invocation\n\nEvery time you invoke an LDD skill — whether auto-triggered or via `LDD:` — **say which skill you are invoking, in one sentence, before applying it**. This is non-negotiable; it lets the user verify which discipline is in effect and override you if you picked wrong.\n\nFormat: `*Invoking \u003Cskill-name>*: \u003Cone-line reason>.`\n\nExample: `*Invoking root-cause-by-layer*: the symptom is a contract-violation `TypeError`; walking the 5-layer ladder before proposing a fix.`\n\n## The three loops — which one is active\n\nLDD distinguishes three optimization loops. Name which one you're in before iterating:\n\n| Loop | You edit | When |\n|---|---|---|\n| **Inner** | Code | Ordinary bug \u002F feature \u002F refactor |\n| **Refinement** (y-axis) | A deliverable (doc, diff, design) | \"Good enough, not great\" — polish |\n| **Outer** (θ-axis) | A skill \u002F rubric | Same rubric violation across ≥3 tasks |\n\nIf you cannot name which loop is active, stop and ask. Running the wrong loop wastes budget and can regress the artifact.\n\n## Minimum compliance behaviors\n\nEven without an explicit `LDD:` prefix, if the bundle is installed you are expected to:\n\n1. **Never ship a symptom patch** (`try\u002Fexcept`, `hasattr`-shim, retry loop, `xfail`) without first walking `root-cause-by-layer` to layers 4–5.\n2. **Never update code based on a single failed run** without invoking `reproducibility-first`.\n3. **Never declare \"done\"** without running `docs-as-definition-of-done` against the touched files.\n4. **Never give a non-trivial recommendation** without running `dialectical-reasoning` (thesis → antithesis → synthesis).\n5. **Never exceed K_MAX=5 iterations** silently — escalate per `loop-driven-engineering` § Escalation.\n\n## When LDD is not applicable\n\nSkip the bundle for:\n- Trivial edits (rename a variable, fix a typo, delete dead code you already understand)\n- Pure lookups (what does this function do — read it and answer)\n- Pure factual questions with no code change involved\n\nThe bundle is for **multi-step engineering under uncertainty**, not for every keystroke.\n\n## Discovery order for a new session\n\nAt session start, if LDD is installed:\n1. Read this skill's description.\n2. Note that the other nine are available.\n3. Apply the trigger-phrase table above to the user's first message.\n4. If the first message doesn't clearly trigger any specific skill, proceed normally — LDD discipline activates when a trigger appears later.\n\n## Compatibility with `superpowers`\n\nIf the `superpowers` plugin is also installed:\n- `loop-driven-engineering` will dispatch to `superpowers:brainstorming` \u002F `writing-plans` \u002F `test-driven-development` \u002F `verification-before-completion` \u002F `requesting-code-review` at the moments noted in its dispatch table.\n- `superpowers:systematic-debugging` overlaps with `root-cause-by-layer`: prefer `root-cause-by-layer` when you want the explicit 5-layer discipline, `systematic-debugging` for broader investigation framing.\n\n## Signal that LDD is working\n\nA session with LDD correctly applied shows:\n- At least one `*Invoking \u003Cskill>*:` announcement per non-trivial task\n- Commit messages that name layers \u002F structural origins \u002F Δloss when relevant\n- No symptom-patch constructs shipped under pressure\n- Doc updates in the same logical commit as behavior changes\n\nIf none of these appear in a long session, LDD is installed but dormant — re-check the trigger-phrase table, or ask the user to prefix `LDD:` explicitly.\n","# Using LDD — the bundle entry-point\n\n## Overview\n\nLoss-Driven Development (LDD) is a ten-skill bundle that treats code changes as SGD steps and forbids overfitting to the current test. This entry-skill exists so you (the agent) know **when to reach for which LDD skill** without the user having to name each one by hand.\n\n**Core principle:** if the user prefixes their message with `LDD:` or mentions any of the trigger phrases below, LDD discipline is explicitly requested. Match their intent to the right sub-skill and announce which one you are applying.\n\n## Trigger phrases (user → skill mapping)\n\nWhen the user's message contains any of these patterns, invoke the paired skill.\n\n| User signal | Invoke |\n|---|---|\n| `LDD:` prefix, \"apply LDD\", \"use LDD\" | Enter full LDD mode — default entry = `loop-driven-engineering` unless a more specific sub-skill matches below |\n| \"failing test\", \"CI is red\", \"flaky\", \"one-off failure\", \"intermittent\" | First `reproducibility-first`, then `root-cause-by-layer` if the failure is real |\n| \"bug\", \"error\", \"exception\", \"unexpected behavior\", \"why is this breaking\" | `root-cause-by-layer` |\n| \"I've tried this 3 times\", \"keeps failing the same way\", five fix-commits in one area | `loss-backprop-lens` (local-minimum trap) |\n| \"this fix works but I'm not sure it generalizes\", \"will this break sibling tests\" | `loss-backprop-lens` (generalization check) |\n| \"I'm mid-debug\", \"is the fix done yet\", before closing any fix-loop | `e2e-driven-iteration` |\n| \"should we ship this\", \"is this the right approach\", design trade-off | `dialectical-reasoning` |\n| \"this doc\u002Fdiff\u002Foutput is okay but could be better\", \"polish this\" | `iterative-refinement` |\n| \"same thing keeps happening across tasks\", \"the skill itself might be wrong\" | `method-evolution` |\n| \"is this codebase healthy\", release-candidate review, weekly check | `drift-detection` |\n| \"about to commit\", \"ready to merge\", \"declaring this done\" | `docs-as-definition-of-done` |\n\n## The \"LDD:\" buzzword\n\nUsers who want **guaranteed** LDD activation (no reliance on auto-triggering) can prefix their message with `LDD:`. When you see this prefix:\n\n1. Load `loop-driven-engineering` as the orchestrating skill\n2. Before any code, announce in one sentence which sub-skill you are reaching for and why\n3. Apply that sub-skill's discipline literally, not \"in spirit\"\n4. Report which rubric items you satisfied at the end of the task\n\nExample:\n\n> User: `LDD: the checkout test is failing and I need to ship in an hour`\n> You: \"Invoking `reproducibility-first` first to check whether this is a real gradient or noise. [runs check] Confirmed reproducible — invoking `root-cause-by-layer` next to diagnose at layer 4\u002F5 before editing.\"\n\n## Announcing skill invocation\n\nEvery time you invoke an LDD skill — whether auto-triggered or via `LDD:` — **say which skill you are invoking, in one sentence, before applying it**. This is non-negotiable; it lets the user verify which discipline is in effect and override you if you picked wrong.\n\nFormat: `*Invoking \u003Cskill-name>*: \u003Cone-line reason>.`\n\nExample: `*Invoking root-cause-by-layer*: the symptom is a contract-violation `TypeError`; walking the 5-layer ladder before proposing a fix.`\n\n## The three loops — which one is active\n\nLDD distinguishes three optimization loops. Name which one you're in before iterating:\n\n| Loop | You edit | When |\n|---|---|---|\n| **Inner** | Code | Ordinary bug \u002F feature \u002F refactor |\n| **Refinement** (y-axis) | A deliverable (doc, diff, design) | \"Good enough, not great\" — polish |\n| **Outer** (θ-axis) | A skill \u002F rubric | Same rubric violation across ≥3 tasks |\n\nIf you cannot name which loop is active, stop and ask. Running the wrong loop wastes budget and can regress the artifact.\n\n## Minimum compliance behaviors\n\nEven without an explicit `LDD:` prefix, if the bundle is installed you are expected to:\n\n1. **Never ship a symptom patch** (`try\u002Fexcept`, `hasattr`-shim, retry loop, `xfail`) without first walking `root-cause-by-layer` to layers 4–5.\n2. **Never update code based on a single failed run** without invoking `reproducibility-first`.\n3. **Never declare \"done\"** without running `docs-as-definition-of-done` against the touched files.\n4. **Never give a non-trivial recommendation** without running `dialectical-reasoning` (thesis → antithesis → synthesis).\n5. **Never exceed K_MAX=5 iterations** silently — escalate per `loop-driven-engineering` § Escalation.\n\n## When LDD is not applicable\n\nSkip the bundle for:\n- Trivial edits (rename a variable, fix a typo, delete dead code you already understand)\n- Pure lookups (what does this function do — read it and answer)\n- Pure factual questions with no code change involved\n\nThe bundle is for **multi-step engineering under uncertainty**, not for every keystroke.\n\n## Discovery order for a new session\n\nAt session start, if LDD is installed:\n1. Read this skill's description.\n2. Note that the other nine are available.\n3. Apply the trigger-phrase table above to the user's first message.\n4. If the first message doesn't clearly trigger any specific skill, proceed normally — LDD discipline activates when a trigger appears later.\n\n## Compatibility with `superpowers`\n\nIf the `superpowers` plugin is also installed:\n- `loop-driven-engineering` will dispatch to `superpowers:brainstorming` \u002F `writing-plans` \u002F `test-driven-development` \u002F `verification-before-completion` \u002F `requesting-code-review` at the moments noted in its dispatch table.\n- `superpowers:systematic-debugging` overlaps with `root-cause-by-layer`: prefer `root-cause-by-layer` when you want the explicit 5-layer discipline, `systematic-debugging` for broader investigation framing.\n\n## Signal that LDD is working\n\nA session with LDD correctly applied shows:\n- At least one `*Invoking \u003Cskill>*:` announcement per non-trivial task\n- Commit messages that name layers \u002F structural origins \u002F Δloss when relevant\n- No symptom-patch constructs shipped under pressure\n- Doc updates in the same logical commit as behavior changes\n\nIf none of these appear in a long session, LDD is installed but dormant — re-check the trigger-phrase table, or ask the user to prefix `LDD:` explicitly.\n",{"name":5,"description":7},"main","3f28cfd9b82326ff325e645ff041589c3220d813","corvin_operator\u002Fbundle\u002Fskills\u002Fldd\u002Fusing-ldd",4,"https:\u002F\u002Fgithub.com\u002FCorvinLabs\u002FCorvinOS","https:\u002F\u002Fcorvin-labs.com, https:\u002F\u002Fwww.youtube.com\u002F@Corvin-Labs","https:\u002F\u002Fgithub.com\u002FCorvinLabs","2026-11-14 23:30:13",{"source":8,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add CorvinLabs\u002FCorvinOS --skill using-ldd",{"tool":37,"command":38},"bunx","bunx skills add CorvinLabs\u002FCorvinOS --skill using-ldd",{"tool":40,"command":41},"pnpm","pnpm dlx skills add CorvinLabs\u002FCorvinOS --skill using-ldd","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FCorvinLabs\u002FCorvinOS\u002Fblob\u002Fmain\u002Fcorvin_operator\u002Fbundle\u002Fskills\u002Fldd\u002Fusing-ldd\u002FSKILL.md",true,[],[46,53,59,65,72,78],{"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},"01M77VGAEV6EQA3C62F78EDHQ3","voice","Voice mode for Claude Code — automatically reads assistant replies aloud via TTS, with German\u002FEnglish auto-detection and optional summarization for long responses. Trigger when the user mentions voice, vorlesen, sprachausgabe, TTS, \"speak\", \"say it out loud\", or asks about \u002Fvoice-* commands.","https:\u002F\u002Fgithub.com\u002FCorvinLabs\u002FCorvinOS\u002Fblob\u002Fmain\u002Fcorvin_operator\u002Fvoice\u002Fskills\u002Fvoice\u002FSKILL.md",[],[],{"skillNo":54,"name":55,"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":56,"categories":57,"keywords":58,"publishedAt":18},"01M77VG6N69YBC0CR0TSMGXHTV","paper-generator-orchestrator","https:\u002F\u002Fgithub.com\u002FCorvinLabs\u002FCorvinOS\u002Fblob\u002Fmain\u002Fcorvin_operator\u002Fskills\u002Fpaper-generator-orchestrator\u002FSKILL.md",[],[],{"skillNo":60,"name":61,"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":62,"categories":63,"keywords":64,"publishedAt":18},"01M77VG3DTRSZ1C4N57KNFARD5","academic-paper-generation","https:\u002F\u002Fgithub.com\u002FCorvinLabs\u002FCorvinOS\u002Fblob\u002Fmain\u002Fcorvin_operator\u002Fskills\u002Facademic-paper-generation\u002FSKILL.md",[],[],{"skillNo":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":18},"01M77VFXA58C38HG5K5J4Q67MF","forge","Forge schema-bound, sandboxed tools at runtime. Paired with the cowork `forge` persona for chat-driven use in the voice-skill bridge. Use when you would otherwise write the same Bash snippet ≥3× with different parameters, when you need precise numerical results over a dataset, or when the user wants reproducible\u002Fdeterministic output written to a file.","https:\u002F\u002Fgithub.com\u002FCorvinLabs\u002FCorvinOS\u002Fblob\u002Fmain\u002Fcorvin_operator\u002Fforge\u002FSKILL.md",[],[],{"skillNo":73,"name":74,"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":75,"categories":76,"keywords":77,"publishedAt":18},"01M77VFTJ8KS80R6PVPTBH4CWV","cowork","https:\u002F\u002Fgithub.com\u002FCorvinLabs\u002FCorvinOS\u002Fblob\u002Fmain\u002Fcorvin_operator\u002Fcowork\u002Fskills\u002Fcowork\u002FSKILL.md",[],[],{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":18},"01M77VFQTC6WR708YMVHAKQWWN","quality-layer-control","Toggle quality disciplines (ADR Gate, docs-as-definition-of-done, etc.) on or off globally","https:\u002F\u002Fgithub.com\u002FCorvinLabs\u002FCorvinOS\u002Fblob\u002Fmain\u002Fcorvin_operator\u002Fbundle\u002Fskills\u002Fquality-layer-control\u002FSKILL.md",[],[]]