[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7AQ10NCMHGHTTR24ZHGQYY2":3,"skill-same:01M7AQ10NCMHGHTTR24ZHGQYY2":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},"01M7AQ10NCMHGHTTR24ZHGQYY2","ramza-parallel-spec",null,"TRANCE-only G3 evaluator-optimizer mode: fan out 2-4 perspective-diverse clean-context candidate specs, score with a bias-hardened evaluator anchored on ramza-score, judge-merge into ONE spec, terminate at confidence ≥85% or hard cap 3 iterations. Read-only; never the default — runs ONLY when the cortex authorizes TRANCE.","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\u002Framza\u002Fskills\u002Fparallel-spec\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: ramza-parallel-spec\ndescription: \"TRANCE-only G3 evaluator-optimizer mode: fan out 2-4 perspective-diverse clean-context candidate specs, score with a bias-hardened evaluator anchored on ramza-score, judge-merge into ONE spec, terminate at confidence ≥85% or hard cap 3 iterations. Read-only; never the default — runs ONLY when the cortex authorizes TRANCE.\"\nmetadata:\n  methodology: RAMZA\n  phase: TRANCE\n---\n\n# RAMZA — Parallel Spec Mode (G3 evaluator-optimizer)\n\nThis mode **wraps** the standard RS→S→P→E→C→T→R→A cycle — it does NOT replace it.\nIt operationalizes the G3 TRANCE form named in the nexus trance-matrix (\"Generator +\nevaluator + termination gate; cap 3 iterations\").\n\n## Activation — TRANCE-GATED (never default)\n\n**This mode is TRANCE-gated. Do NOT fan out candidate specs at standard tier; run\nthe single-pass RS→S→P→E→C→T→R→A cycle instead.**\n\nActivate ONLY when the cortex authorizes TRANCE — i.e. BOTH complexity AND stakes\nflags hold: complexity 10–12 (per `ramza-score --rubric complexity`) STRATEGIC\u002FCHANGE\nspecs, multi-service architecture, or high-rework-risk system design. At standard\ntier, fall back to the normal cycle.\n\n## Read-vs-write safety\n\nRAMZA is READ-ONLY in every phase (`DESIGN-RATIONALE.md` D2), so the parallel\ngenerator branches are the explicitly-SAFE parallel-READ case — **NO worktree\nisolation is required** (R1-01). This is distinct from Vivi\u002FAPIVR-Δ's\nparallel-WRITE, which does need worktree isolation.\n\n## The cycle: GENERATE → EVALUATE → JUDGE-MERGE → TERMINATE\n\n### 1. GENERATE (perspective-diverse fan-out)\n\nFan out **2-4 clean-context generator branches** (default 3, hard cap 4). Each\nbranch receives the SAME Scope + Pattern context but a DIFFERENT assigned\nperspective, producing a full candidate draft spec:\n\n- one **conservative** (low-risk, proven)\n- one **pattern-leveraging** (maximize reuse of existing conventions)\n- one **innovative** (novel approach)\n- optionally one **risk-minimizing** (blast-radius-first)\n\nPerspective diversity is **deliberate**, not naive N-identical sampling — quality\ndominates raw diversity, so cap at 3-4 high-quality branches, never spawn N clones\n(R3-04, R3-06; cost-ceiling C1 max 5 → capped at 4 here because spec generation is\nexpensive). Use **clean-context subagents** so branches cannot self-condition on each\nother's trajectory (R1-03).\n\n### 2. EVALUATE (bias-hardened scoring)\n\nA single evaluator scores each candidate through the tool — never hand-computed:\n\n```\necho '{\"alignment\":9,\"correctness\":8,\"maintainability\":7,\"performance\":7,\"simplicity\":6,\"risk\":7,\"innovation\":5}' \\\n  | ramza-score --rubric explore --state \u003Cstate> --label \"\u003Ccandidate-perspective>\"\n```\n\nThe 7-dimension weighted rubric (Alignment 25% + Correctness 20% +\nMaintainability 15% + Performance 15% + Simplicity 10% + Risk 10% + Innovation\n5%, see `docs\u002Fmethodology\u002Fscoring.md`) is arithmetic done by `ramza-score`, not\nthe evaluator — the evaluator's job is producing honest per-dimension inputs\nwhile applying EXPLICIT LLM-as-judge bias mitigations (R3-09):\n\n- **Strip authoring-branch identity\u002Flabel** from each candidate before scoring\n  (counters self-preference \u002F identity bias).\n- **Randomize \u002F rotate candidate presentation order** across the comparison\n  (counters position bias).\n- **Length-normalize** — judge on rubric-dimension content, not verbosity\n  (counters verbosity bias).\n- **Anchor on deterministic checks** — prefer `ramza-lint` \u002F `ramza-ears-lint`\n  and the dependency\u002Fconstraint layers already in the Test (T) phase as the\n  trust anchor over pure LLM judgment.\n\nRecord the per-candidate `ramza-score` results (each call appends to the state\nfile's `gates[]` and the calibration log) and the bias mitigations applied, so\nthe evaluation is auditable in the final spec.\n\n### 3. JUDGE-MERGE (mandatory aggregation)\n\nSynthesize ONE spec by taking the **highest-scoring approach per dimension**:\n\n- Record which candidate won each dimension and why, via `[DECISION]` markers\n  (per-dimension provenance table).\n- Carry every rejected candidate's rationale into the **Rejected Alternatives**\n  section (a full-tier-required section, see `docs\u002Fmethodology\u002Ftiers.md`) —\n  never silently discard a losing branch.\n\nThe result is one synthesized dual-format spec (Markdown + YAML\u002FJSON) that\nstill passes through the normal Assemble exit gates — `ramza-freeze`, then\n`ramza-verify-emit` before any envelope is emitted. Downstream sees exactly one\nspec + one validated ECL envelope, identical to the standard cycle. The\nparallel mode is invisible at the hand-off boundary.\n\n### 4. TERMINATE (bounded)\n\nStop when the merged-spec confidence **≥85%** (`ramza-score --rubric\nconfidence` at the Assemble gate) OR the iteration count reaches the **hard cap\nof 3** — whichever comes first. The cap is inviolable (inherited unchanged from\nSPECTRA, `DESIGN-RATIONALE.md` D2; the nexus trance-matrix R4 refusal gate). On\nnon-convergence, emit a `[GAP]`\u002F`[BLOCKED]` gap report and escalate to the\nhuman — **do not loop past the cap**.\n\n## Hard constraints (P0)\n\n1. TRANCE-only — never the default; standard tier runs the single-pass cycle.\n2. READ-ONLY; no worktree isolation needed (read-only ⇒ safe parallel).\n3. Cap branches at 4 (default 3); cap iterations at 3.\n4. Evaluator MUST apply identity-strip + order-rotate + length-normalize +\n   deterministic-anchor and record them auditably; scoring arithmetic always\n   runs through `ramza-score`, never hand-computed.\n5. JUDGE-MERGE produces ONE spec with per-dimension `[DECISION]` provenance,\n   and still passes through `ramza-freeze` + `ramza-verify-emit` before\n   emission.\n6. Non-convergence → `[GAP]` escalation, never an unbounded loop.\n\nSee `SPEC.md` \"## Parallel spec mode (TRANCE-gated)\" for the\nfull methodology section and `DESIGN-RATIONALE.md` for the succession's\nresearch basis.\n\n---\n\n*RAMZA — Parallel Spec Mode (TRANCE \u002F G3)*\n","# RAMZA — Parallel Spec Mode (G3 evaluator-optimizer)\n\nThis mode **wraps** the standard RS→S→P→E→C→T→R→A cycle — it does NOT replace it.\nIt operationalizes the G3 TRANCE form named in the nexus trance-matrix (\"Generator +\nevaluator + termination gate; cap 3 iterations\").\n\n## Activation — TRANCE-GATED (never default)\n\n**This mode is TRANCE-gated. Do NOT fan out candidate specs at standard tier; run\nthe single-pass RS→S→P→E→C→T→R→A cycle instead.**\n\nActivate ONLY when the cortex authorizes TRANCE — i.e. BOTH complexity AND stakes\nflags hold: complexity 10–12 (per `ramza-score --rubric complexity`) STRATEGIC\u002FCHANGE\nspecs, multi-service architecture, or high-rework-risk system design. At standard\ntier, fall back to the normal cycle.\n\n## Read-vs-write safety\n\nRAMZA is READ-ONLY in every phase (`DESIGN-RATIONALE.md` D2), so the parallel\ngenerator branches are the explicitly-SAFE parallel-READ case — **NO worktree\nisolation is required** (R1-01). This is distinct from Vivi\u002FAPIVR-Δ's\nparallel-WRITE, which does need worktree isolation.\n\n## The cycle: GENERATE → EVALUATE → JUDGE-MERGE → TERMINATE\n\n### 1. GENERATE (perspective-diverse fan-out)\n\nFan out **2-4 clean-context generator branches** (default 3, hard cap 4). Each\nbranch receives the SAME Scope + Pattern context but a DIFFERENT assigned\nperspective, producing a full candidate draft spec:\n\n- one **conservative** (low-risk, proven)\n- one **pattern-leveraging** (maximize reuse of existing conventions)\n- one **innovative** (novel approach)\n- optionally one **risk-minimizing** (blast-radius-first)\n\nPerspective diversity is **deliberate**, not naive N-identical sampling — quality\ndominates raw diversity, so cap at 3-4 high-quality branches, never spawn N clones\n(R3-04, R3-06; cost-ceiling C1 max 5 → capped at 4 here because spec generation is\nexpensive). Use **clean-context subagents** so branches cannot self-condition on each\nother's trajectory (R1-03).\n\n### 2. EVALUATE (bias-hardened scoring)\n\nA single evaluator scores each candidate through the tool — never hand-computed:\n\n```\necho '{\"alignment\":9,\"correctness\":8,\"maintainability\":7,\"performance\":7,\"simplicity\":6,\"risk\":7,\"innovation\":5}' \\\n  | ramza-score --rubric explore --state \u003Cstate> --label \"\u003Ccandidate-perspective>\"\n```\n\nThe 7-dimension weighted rubric (Alignment 25% + Correctness 20% +\nMaintainability 15% + Performance 15% + Simplicity 10% + Risk 10% + Innovation\n5%, see `docs\u002Fmethodology\u002Fscoring.md`) is arithmetic done by `ramza-score`, not\nthe evaluator — the evaluator's job is producing honest per-dimension inputs\nwhile applying EXPLICIT LLM-as-judge bias mitigations (R3-09):\n\n- **Strip authoring-branch identity\u002Flabel** from each candidate before scoring\n  (counters self-preference \u002F identity bias).\n- **Randomize \u002F rotate candidate presentation order** across the comparison\n  (counters position bias).\n- **Length-normalize** — judge on rubric-dimension content, not verbosity\n  (counters verbosity bias).\n- **Anchor on deterministic checks** — prefer `ramza-lint` \u002F `ramza-ears-lint`\n  and the dependency\u002Fconstraint layers already in the Test (T) phase as the\n  trust anchor over pure LLM judgment.\n\nRecord the per-candidate `ramza-score` results (each call appends to the state\nfile's `gates[]` and the calibration log) and the bias mitigations applied, so\nthe evaluation is auditable in the final spec.\n\n### 3. JUDGE-MERGE (mandatory aggregation)\n\nSynthesize ONE spec by taking the **highest-scoring approach per dimension**:\n\n- Record which candidate won each dimension and why, via `[DECISION]` markers\n  (per-dimension provenance table).\n- Carry every rejected candidate's rationale into the **Rejected Alternatives**\n  section (a full-tier-required section, see `docs\u002Fmethodology\u002Ftiers.md`) —\n  never silently discard a losing branch.\n\nThe result is one synthesized dual-format spec (Markdown + YAML\u002FJSON) that\nstill passes through the normal Assemble exit gates — `ramza-freeze`, then\n`ramza-verify-emit` before any envelope is emitted. Downstream sees exactly one\nspec + one validated ECL envelope, identical to the standard cycle. The\nparallel mode is invisible at the hand-off boundary.\n\n### 4. TERMINATE (bounded)\n\nStop when the merged-spec confidence **≥85%** (`ramza-score --rubric\nconfidence` at the Assemble gate) OR the iteration count reaches the **hard cap\nof 3** — whichever comes first. The cap is inviolable (inherited unchanged from\nSPECTRA, `DESIGN-RATIONALE.md` D2; the nexus trance-matrix R4 refusal gate). On\nnon-convergence, emit a `[GAP]`\u002F`[BLOCKED]` gap report and escalate to the\nhuman — **do not loop past the cap**.\n\n## Hard constraints (P0)\n\n1. TRANCE-only — never the default; standard tier runs the single-pass cycle.\n2. READ-ONLY; no worktree isolation needed (read-only ⇒ safe parallel).\n3. Cap branches at 4 (default 3); cap iterations at 3.\n4. Evaluator MUST apply identity-strip + order-rotate + length-normalize +\n   deterministic-anchor and record them auditably; scoring arithmetic always\n   runs through `ramza-score`, never hand-computed.\n5. JUDGE-MERGE produces ONE spec with per-dimension `[DECISION]` provenance,\n   and still passes through `ramza-freeze` + `ramza-verify-emit` before\n   emission.\n6. Non-convergence → `[GAP]` escalation, never an unbounded loop.\n\nSee `SPEC.md` \"## Parallel spec mode (TRANCE-gated)\" for the\nfull methodology section and `DESIGN-RATIONALE.md` for the succession's\nresearch basis.\n\n---\n\n*RAMZA — Parallel Spec Mode (TRANCE \u002F G3)*\n",{"name":5,"metadata":24,"description":7},{"phase":25,"methodology":26},"TRANCE","RAMZA","main","38c3a82583abf9806de764f89ac0099ad690933a",".eidolons\u002Framza\u002Fskills\u002Fparallel-spec",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 ramza-parallel-spec",{"tool":42,"command":43},"bunx","bunx skills add Rynaro\u002Fmagicite --skill ramza-parallel-spec",{"tool":45,"command":46},"pnpm","pnpm dlx skills add Rynaro\u002Fmagicite --skill ramza-parallel-spec","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FRynaro\u002Fmagicite\u002Fblob\u002Fmain\u002F.eidolons\u002Framza\u002Fskills\u002Fparallel-spec\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",[],[]]