[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7APYJ7TY8RH5WSDTSTY7VDC":3,"skill-same:01M7APYJ7TY8RH5WSDTSTY7VDC":50},{"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":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":27,"commitSha":28,"skillDirectory":29,"forksCount":30,"repositoryHtmlUrl":31,"repositoryHomepageUrl":6,"ownerHtmlUrl":32,"ownerBlogUrl":33,"ownerDescription":34,"updatedAt":35,"install":36,"resources":49},"01M7APYJ7TY8RH5WSDTSTY7VDC","kupo-keep-or-kick",null,"Phase K triage gate that decides whether Kupo will attempt a delegated micro-task or refuse cheaply. Use when a delegation arrives and Kupo must decide KEEP vs REFUSE\u002FESCALATE; runs once per delegation at the start of every KUPO cycle. Do NOT use during Phase U\u002FP\u002FO.","Rynaro\u002Fmagicite","Rynaro","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F5271543?v=4","01M70CFYFMB316W23THVQAQ42M","Henrique A. Lavezzo","01M7APN2KCVWBNY727T57KR2ZJ",2,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FRynaro\u002Fmagicite\u002Fblob\u002Fmain\u002F.eidolons\u002Fkupo\u002Fskills\u002Fkeep-or-kick\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: kupo-keep-or-kick\ndescription: Phase K triage gate that decides whether Kupo will attempt a delegated micro-task or refuse cheaply. Use when a delegation arrives and Kupo must decide KEEP vs REFUSE\u002FESCALATE; runs once per delegation at the start of every KUPO cycle. Do NOT use during Phase U\u002FP\u002FO.\nmetadata:\n  methodology: Kupo\n  phase: K\n---\n\n# Keep-or-Kick Skill — Kupo (Phase K triage)\n\n## When to use\n\nLoad during Phase K (triage). Runs once per delegation. Triage cost ≈ 1 step.\nDo not load during Phase U, P, or O.\n\nLoaded during Phase K. Runs once per delegation. Triage cost ≈ 1 step.\n\nPhase K is the additive-proof gate: Kupo only spends cycles on tasks it can\nplausibly win. Every task that fails triage bounces cheaply, making Kupo\nstructurally non-negative to the delegating planner's session.\n\n---\n\n## Decision Tree (run in order — first failure exits)\n\n### Step 1 — Localization check\n\nDoes the task require changes to **≤ 2 files** that form **one coherent change**?\n\n- **Yes** → continue to Step 2.\n- **No** (cross-cutting, > 2 files, or multiple unrelated concerns) →\n  `REFUSE{SCOPE_TOO_BROAD}` or `ESCALATE{to: apivr}` for a cross-cutting\n  refactor, or `ESCALATE{to: vivi}` for a loop-native coding campaign.\n\nOne coherent change means: changing file A causes file B to change as a direct\nmechanical consequence (e.g., rename a symbol + update one call site), not a\ncoincidental co-location.\n\n### Step 2 — Named-verifier predicate (structural KEEP gate)\n\nCan you name a **concrete external verifier** that will declare pass\u002Ffail on the\noutcome? The verifier must be one of: test runner, typecheck, linter, compiler,\ndiff, schema validator.\n\n\"I think it looks right\" is not a verifier. \"The TypeScript compiler will exit 0\"\nis a verifier.\n\n- **Yes, verifier named** → record it as `verifier` for Phase O. Continue to Step 3.\n- **No nameable verifier** → `REFUSE{NO_EXTERNAL_VERIFIER}`.\n\n### Step 3 — Scope-class match\n\nDoes the task fall into a KEEP class from the §3 taxonomy?\n\n**KEEP classes (pass → continue):**\n\n| Class | Key signal |\n|---|---|\n| rename \u002F symbol-move with compiler confirm | `git grep` shows bounded occurrences |\n| import \u002F path fix | broken import path, test as verifier |\n| lockfile \u002F dep-pin bump | version string change, build as verifier |\n| config-key edit versus schema | add \u002F change one config key, schema validate |\n| lint \u002F format autofix apply | pre-computed lint fix, linter exit-0 |\n| mechanical fixture update | fixture output changed, diff or test as verifier |\n| one-line failing-assertion fix | obvious off-by-one or stale expected value |\n| template boilerplate | fill a template slot, diff as verifier |\n| bounded grep-replace | scoped string substitution, test suite as verifier |\n\n**REFUSE \u002F ESCALATE classes (fail → exit):**\n\n| Class | Routing |\n|---|---|\n| Open-ended reasoning, design, or planning | `REFUSE{NOT_EXECUTOR_ROLE}` |\n| Cross-cutting refactor (> 2 files) | `REFUSE` or `ESCALATE{to: apivr}` |\n| Ambiguous spec or unclear target | `REFUSE{AMBIGUOUS_SPEC}` — clarify upstream |\n| Loop-native coding campaign | `ESCALATE{to: vivi}` or `ESCALATE{to: apivr}` |\n| No nameable external verifier | `REFUSE{NO_EXTERNAL_VERIFIER}` (Step 2 already catches) |\n\nIf none of the KEEP classes match and no REFUSE class applies, treat as\n`REFUSE{SCOPE_CLASS_UNKNOWN}` and surface the ambiguity to the delegating parent.\n\n### Step 4 — Economic gate\n\nIs the **expected pass-rate > ~0.20**? The threshold is approximate: haiku→opus\ncost ratio implies Kupo must succeed on roughly 1 in 5 delegations to break even.\n\nAsk: is the task clearly mechanical (high confidence → proceed) or speculative\n(low confidence → refuse)?\n\n- **High confidence** (pass-rate clearly > 0.20) → `KEEP{verifier: \u003Cnamed>}`.\n- **Borderline** (unsure) → default `REFUSE{PASS_RATE_UNCERTAIN}` and return the\n  task to the delegating parent with a note.\n- **Low confidence** (pass-rate clearly ≤ 0.20) → `REFUSE{PASS_RATE_LOW}`.\n\n---\n\n## Output format\n\nEmit exactly one of:\n\n```\nKEEP{verifier: \"\u003Cverifier command or class>\"}\n```\n```\nREFUSE{code: \"\u003CREFUSE_CODE>\", note: \"\u003Cone sentence for the parent>\"}\n```\n```\nESCALATE{to: \"\u003Cvivi|apivr|spectra|orchestrator>\", code: \"\u003CESCALATE_CODE>\", note: \"\u003Cone sentence>\"}\n```\n\nThe output of Phase K is the `verifier` field carried forward into Phase O.\nNo other state from K enters Phase U; K is a one-shot gate.\n\n---\n\n## Notes\n\n- **Triage cost = ~1 step.** K must be cheap; if K itself is expensive, the\n  additive-proof breaks. Do not invoke atlas-aci during K — gather happens in U.\n- **Structural, not verbal.** KEEP iff a verifier can be named; escalation\n  triggers are structural (files > 2, loop-native pattern) not introspective.\n- **Loop-native campaigns always ESCALATE.** If the task description mentions\n  \"iterative\", \"implement feature X end-to-end\", \"write the whole module\", or\n  similar — it's a campaign, not a micro-task. Escalate immediately.\n- **REFUSE is cheap and correct.** The parent can always re-delegate to a heavier\n  Eidolon. A fast REFUSE is more valuable than a slow failure.\n\n---\n\n*Keep-or-Kick Skill — Kupo Phase K triage*\n","# Keep-or-Kick Skill — Kupo (Phase K triage)\n\n## When to use\n\nLoad during Phase K (triage). Runs once per delegation. Triage cost ≈ 1 step.\nDo not load during Phase U, P, or O.\n\nLoaded during Phase K. Runs once per delegation. Triage cost ≈ 1 step.\n\nPhase K is the additive-proof gate: Kupo only spends cycles on tasks it can\nplausibly win. Every task that fails triage bounces cheaply, making Kupo\nstructurally non-negative to the delegating planner's session.\n\n---\n\n## Decision Tree (run in order — first failure exits)\n\n### Step 1 — Localization check\n\nDoes the task require changes to **≤ 2 files** that form **one coherent change**?\n\n- **Yes** → continue to Step 2.\n- **No** (cross-cutting, > 2 files, or multiple unrelated concerns) →\n  `REFUSE{SCOPE_TOO_BROAD}` or `ESCALATE{to: apivr}` for a cross-cutting\n  refactor, or `ESCALATE{to: vivi}` for a loop-native coding campaign.\n\nOne coherent change means: changing file A causes file B to change as a direct\nmechanical consequence (e.g., rename a symbol + update one call site), not a\ncoincidental co-location.\n\n### Step 2 — Named-verifier predicate (structural KEEP gate)\n\nCan you name a **concrete external verifier** that will declare pass\u002Ffail on the\noutcome? The verifier must be one of: test runner, typecheck, linter, compiler,\ndiff, schema validator.\n\n\"I think it looks right\" is not a verifier. \"The TypeScript compiler will exit 0\"\nis a verifier.\n\n- **Yes, verifier named** → record it as `verifier` for Phase O. Continue to Step 3.\n- **No nameable verifier** → `REFUSE{NO_EXTERNAL_VERIFIER}`.\n\n### Step 3 — Scope-class match\n\nDoes the task fall into a KEEP class from the §3 taxonomy?\n\n**KEEP classes (pass → continue):**\n\n| Class | Key signal |\n|---|---|\n| rename \u002F symbol-move with compiler confirm | `git grep` shows bounded occurrences |\n| import \u002F path fix | broken import path, test as verifier |\n| lockfile \u002F dep-pin bump | version string change, build as verifier |\n| config-key edit versus schema | add \u002F change one config key, schema validate |\n| lint \u002F format autofix apply | pre-computed lint fix, linter exit-0 |\n| mechanical fixture update | fixture output changed, diff or test as verifier |\n| one-line failing-assertion fix | obvious off-by-one or stale expected value |\n| template boilerplate | fill a template slot, diff as verifier |\n| bounded grep-replace | scoped string substitution, test suite as verifier |\n\n**REFUSE \u002F ESCALATE classes (fail → exit):**\n\n| Class | Routing |\n|---|---|\n| Open-ended reasoning, design, or planning | `REFUSE{NOT_EXECUTOR_ROLE}` |\n| Cross-cutting refactor (> 2 files) | `REFUSE` or `ESCALATE{to: apivr}` |\n| Ambiguous spec or unclear target | `REFUSE{AMBIGUOUS_SPEC}` — clarify upstream |\n| Loop-native coding campaign | `ESCALATE{to: vivi}` or `ESCALATE{to: apivr}` |\n| No nameable external verifier | `REFUSE{NO_EXTERNAL_VERIFIER}` (Step 2 already catches) |\n\nIf none of the KEEP classes match and no REFUSE class applies, treat as\n`REFUSE{SCOPE_CLASS_UNKNOWN}` and surface the ambiguity to the delegating parent.\n\n### Step 4 — Economic gate\n\nIs the **expected pass-rate > ~0.20**? The threshold is approximate: haiku→opus\ncost ratio implies Kupo must succeed on roughly 1 in 5 delegations to break even.\n\nAsk: is the task clearly mechanical (high confidence → proceed) or speculative\n(low confidence → refuse)?\n\n- **High confidence** (pass-rate clearly > 0.20) → `KEEP{verifier: \u003Cnamed>}`.\n- **Borderline** (unsure) → default `REFUSE{PASS_RATE_UNCERTAIN}` and return the\n  task to the delegating parent with a note.\n- **Low confidence** (pass-rate clearly ≤ 0.20) → `REFUSE{PASS_RATE_LOW}`.\n\n---\n\n## Output format\n\nEmit exactly one of:\n\n```\nKEEP{verifier: \"\u003Cverifier command or class>\"}\n```\n```\nREFUSE{code: \"\u003CREFUSE_CODE>\", note: \"\u003Cone sentence for the parent>\"}\n```\n```\nESCALATE{to: \"\u003Cvivi|apivr|spectra|orchestrator>\", code: \"\u003CESCALATE_CODE>\", note: \"\u003Cone sentence>\"}\n```\n\nThe output of Phase K is the `verifier` field carried forward into Phase O.\nNo other state from K enters Phase U; K is a one-shot gate.\n\n---\n\n## Notes\n\n- **Triage cost = ~1 step.** K must be cheap; if K itself is expensive, the\n  additive-proof breaks. Do not invoke atlas-aci during K — gather happens in U.\n- **Structural, not verbal.** KEEP iff a verifier can be named; escalation\n  triggers are structural (files > 2, loop-native pattern) not introspective.\n- **Loop-native campaigns always ESCALATE.** If the task description mentions\n  \"iterative\", \"implement feature X end-to-end\", \"write the whole module\", or\n  similar — it's a campaign, not a micro-task. Escalate immediately.\n- **REFUSE is cheap and correct.** The parent can always re-delegate to a heavier\n  Eidolon. A fast REFUSE is more valuable than a slow failure.\n\n---\n\n*Keep-or-Kick Skill — Kupo Phase K triage*\n",{"name":5,"metadata":24,"description":7},{"phase":25,"methodology":26},"K","Kupo","main","38c3a82583abf9806de764f89ac0099ad690933a",".eidolons\u002Fkupo\u002Fskills\u002Fkeep-or-kick",0,"https:\u002F\u002Fgithub.com\u002FRynaro\u002Fmagicite","https:\u002F\u002Fgithub.com\u002FRynaro","https:\u002F\u002Fhlavezzo.me","A Code Alchemist with a passion for weaving tales and inscribing transmutation circles in pure code.","2026-10-14 02:35:37",{"source":8,"skillName":5,"commands":37,"prompt":47,"zipAvailable":48},[38,41,44],{"tool":39,"command":40},"npx","npx skills add Rynaro\u002Fmagicite --skill kupo-keep-or-kick",{"tool":42,"command":43},"bunx","bunx skills add Rynaro\u002Fmagicite --skill kupo-keep-or-kick",{"tool":45,"command":46},"pnpm","pnpm dlx skills add Rynaro\u002Fmagicite --skill kupo-keep-or-kick","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FRynaro\u002Fmagicite\u002Fblob\u002Fmain\u002F.eidolons\u002Fkupo\u002Fskills\u002Fkeep-or-kick\u002FSKILL.md",true,[],[51,58,65,72,79,86],{"skillNo":52,"name":53,"nameZh":6,"description":54,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":55,"categories":56,"keywords":57,"publishedAt":19},"01M7AQ4GHJQVV8TJBJ8T1V7ZQ9","wine-dxvk-cache-clear","Clear a stale DXVK shader cache that is causing graphical corruption in a\nWine or Proton game. Use when: a game shows corrupted textures or shader\nflicker that started after a driver or DXVK version change.","https:\u002F\u002Fgithub.com\u002FRynaro\u002Fmagicite\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Ftoy-registry\u002Fskills\u002Fwine-dxvk-cache-clear\u002FSKILL.md",[],[],{"skillNo":59,"name":60,"nameZh":6,"description":61,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":62,"categories":63,"keywords":64,"publishedAt":19},"01M7AQ4CY1NHSMY1HCZ91387YY","steam-download-region-fix","Fix a Steam client stuck at very low download speed by changing its\ndownload region. Use when: Steam downloads are far below the local\ninternet speed for every game, not just one.","https:\u002F\u002Fgithub.com\u002FRynaro\u002Fmagicite\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Ftoy-registry\u002Fskills\u002Fsteam-download-region-fix\u002FSKILL.md",[],[],{"skillNo":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":19},"01M7AQ49P7Y0CDRSYMPVABX80K","proton-battleye-eac-toggle","Toggle BattlEye or Easy Anti-Cheat runtime support for a Steam Proton game.\nUse when: a multiplayer game refuses to launch with an anti-cheat error under Proton.","https:\u002F\u002Fgithub.com\u002FRynaro\u002Fmagicite\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Ftoy-registry\u002Fskills\u002Fproton-battleye-eac-toggle\u002FSKILL.md",[],[],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":19},"01M7AQ45326FAP3X4Q86FK1X4N","vivi-verify-incoming","Load when reading any upstream artefact handed off to Vivi that carries a sibling .envelope.json. BLOCKING per ECL §6.2.2: the orchestrator MUST have verified the envelope's SHA-256 (eidolons verify-envelope --block \u002F eidolons run --verify) and recorded a verify_pass before dispatch. If no verify_pass exists for the message_id, or a verify_fail is present, REFUSE to process the payload and hand back to the orchestrator. Symmetric receiver gate — every Eidolon enforces it identically.","https:\u002F\u002Fgithub.com\u002FRynaro\u002Fmagicite\u002Fblob\u002Fmain\u002F.eidolons\u002Fvivi\u002Fskills\u002Fverify-incoming\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":19},"01M7AQ402861P0P3C2TEGFGMA1","vivi-parallel-tracks","Load ONLY under TRANCE authorization when the Plan phase yields N independent, non-overlapping implementation tracks (disjoint file sets). Operationalizes the TRANCE G4 form — parallel multi-track implementation in mandatory git-worktree isolation, max 5 clean-context tracks, a per-track verifier cascade, a non-fungible per-track ≤3 reflection budget, explicit stop conditions, and a single-threaded merge\u002Faggregation step. Absent TRANCE gating, Vivi runs exactly as today: single-track A→P→I→V→Δ\u002FR.","https:\u002F\u002Fgithub.com\u002FRynaro\u002Fmagicite\u002Fblob\u002Fmain\u002F.eidolons\u002Fvivi\u002Fskills\u002Fparallel-tracks\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":19},"01M7AQ3RH9BZF9ZMTC7VG5P7PB","vivi-methodology","Full Vivi cycle reference — A(nalyze) → P(lan) → I(mplement) → V(erify) → Δ(Delta)\u002FR(eflect). Use when the task is a non-trivial feature implementation in a brownfield codebase and you need the complete methodology reference: complexity routing, evidence-grounded planning rules, test-anchoring requirements, and failure-escalation thresholds.","https:\u002F\u002Fgithub.com\u002FRynaro\u002Fmagicite\u002Fblob\u002Fmain\u002F.eidolons\u002Fvivi\u002Fskills\u002Fmethodology\u002FSKILL.md",[],[]]