[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7APWTFQ79SVQKEDMWRC91MW":3,"skill-same:01M7APWTFQ79SVQKEDMWRC91MW":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},"01M7APWTFQ79SVQKEDMWRC91MW","gilgamesh-attest",null,"Phase A (Attest) result emission — finalizes the TaskState audit record with evidence-anchored claims, emits the mission result via ECL PROPOSE, and PROPOSEs any typed handoff-request UPWARD (never dispatches). Use when Grind reaches a terminal stop_state; load at the end of a GILGAMESH cycle. Do NOT use during Gauge\u002FInventory\u002FLock\u002FGrind.","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\u002Fgilgamesh\u002Fskills\u002Fattest\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: gilgamesh-attest\ndescription: Phase A (Attest) result emission — finalizes the TaskState audit record with evidence-anchored claims, emits the mission result via ECL PROPOSE, and PROPOSEs any typed handoff-request UPWARD (never dispatches). Use when Grind reaches a terminal stop_state; load at the end of a GILGAMESH cycle. Do NOT use during Gauge\u002FInventory\u002FLock\u002FGrind.\nmetadata:\n  methodology: Gilgamesh\n  phase: A\n---\n\n# Attest Skill — Gilgamesh (Phase A result)\n\n## When to use\n\nLoad when Grind reaches a terminal `stop_state` (`terminate` or `escalate`). Attest\nturns the mission into an audit record and an ECL PROPOSE. Never invoked in Gauge,\nInventory, Lock, or Grind.\n\nThe wanderer leaves with no weapons: everything collected during the mission is either\nreturned here in the Attest record or discarded. Nothing persists (`security.persists:\n[]`).\n\n---\n\n## Step 1 — Finalize the TaskState (the audit record)\n\nComplete `schemas\u002Ftaskstate.v1.json`. Each entry in `claims[]` MUST carry ≥1 external\n**evidence** anchor drawn from `verification_outcomes[]` (an oracle result, a\n`path:line`, or a diff). A claim with no external anchor is **inadmissible** — the\nExcalipoor rule: a proud assertion is worthless if no oracle confirmed the blade.\n\nRecord: final `stop_state`, `verification_outcomes`, `changed_artifacts` (sandbox\npaths), `unresolved_risks`, and the spent `budget`. This is the mission's single audit\nartefact; ship it verbatim.\n\n---\n\n## Step 1a — The report is the attestation (mission report protocol)\n\nWhen the inbound mission enumerates required labeled report lines, your final\nhuman-readable message is itself part of the audit record, not a separate courtesy\nsummary. A report missing any required line — or one that skips enumeration — is an\n**inadmissible attestation**, the same Excalipoor rule an anchor-less claim fails.\n\n**1. Enumerate first.** The FIRST line of the final report is `REQUIRED-LABELS:`\nfollowed by every required label copied from the mission. RE-READ the mission and\nbuild this line before drafting any answer — a report that skips enumeration is\ninvalid regardless of what follows. Do this even under budget pressure.\n\n**2. Label discipline.** Then one line per label, `LABEL: value`. Reproduce each\nlabel **exactly** as the mission gives it, VERBATIM but WITHOUT any parenthetical\nhint: in `EVIDENCE-x (path:line)` the `(path:line)` describes the **value's shape**\nand is never part of the label. Write `EVIDENCE-x: \u003Cpath>:\u003Cline>`. Folding the\nhint into the label turns a matched line into an unmatched one under mechanical\ngrading.\n\n**3. Value format.** The value's FIRST whitespace-delimited token IS the answer —\na number, `pass`\u002F`fail`, or a `path:line` — with explanatory annotation trailing\nafter a space. A grader reading the first token should never have to parse prose to\nfind the answer.\n\n**4. Never omit a line.** If a verification is blocked, its line is still emitted\nwith value `fail` plus the blocker as annotation — never a missing line, and never\na `pass` you did not actually observe.\n\n**Quoted-anchor rule (Excalipoor applied to citations).** Every `path:line` anchor\nyou emit must be followed by a space and a short double-quoted verbatim fragment\n(3–6 words) of that exact line — copied AFTER Reading the line, never from memory.\nIf you cannot quote it, you have not read it; do not cite it. Example:\n`EVIDENCE-enum_count: schemas\u002Froster-entry.schema.json:11 \"scout, planner, coder\"`.\nPrefer a single line over a range.\n\n**Pre-emit anchor re-read rule (mechanical, not exhortative).** Before writing ANY\n`path:line` anchor into the final report, Read that exact line number in that file\nand confirm the line's text contains the verbatim fragment being quoted. If the\nline does not contain the fragment (or is empty\u002Fout of range), the anchor is\nWRONG — re-locate the true line with Grep on the fragment, and cite the corrected\nline number. Never emit an anchor you have not re-read at that exact line in this\nsame mission; the quoted fragment must be present on the cited line. A drifted\nanchor is an inadmissible attestation — the Excalipoor rule applied to line\nnumbers: a citation you cannot re-read is a fake blade. This closes the gap a\nquoted fragment alone does not: a fragment copied once at write-time can still\ndrift onto the wrong line by the time the report is assembled — the re-read\nhappens immediately before the anchor is emitted, not earlier in the mission.\n\n**Repo-only anchor rule.** Evidence and proposal-target anchors MUST point at a\nrepo-relative path that exists in the working checkout (a committed source file).\nNEVER cite an ephemeral, temp, sandbox-scratch, or command-output path (`\u002Ftmp\u002F*`,\nredirected stdout, etc.). If a fact is produced by RUNNING a command, the\ncommand's result belongs in the `VERIFY-\u003Cname>` line; the `EVIDENCE-\u003Ckey>` anchor\npoints at the repo file or script the fact derives from (e.g. cite the script's\nsource line, not its runtime output file).\n\n**Verify-routing ladder.** (1) If the verification command is directly allowed by\nyour tool list (`make`, `bats`, `shellcheck`, `pytest`, `go test`, `jest`, `rspec`,\n`shasum`, `wc`) — run it directly. (2) Otherwise route it through the delegated\nsandbox: `eidolons sandbox run --allow-unsafe-host -- \u003Ccmd>` (see `skills\u002Fgrind\u002FSKILL.md`\n— externalized verification; the sandbox captures pass\u002Ffail). (3) Only if both\nrungs are unavailable, emit `VERIFY-\u003Cx>: fail` immediately followed by the\nblocker. Never skip a rung, never omit the line, never hand-derive a result you\ncould execute.\n\n---\n\n## Step 2 — Emit the result (ECL PROPOSE)\n\nOn `terminate` (success), emit the mission **result** to the orchestrator:\n\n1. Write the result artefact + compute its `sha256` and `size_bytes`.\n2. Compose the ECL v2.0 envelope sidecar (validate against\n   `schemas\u002Fecl-envelope.v2.json`):\n\n   ```json\n   {\n     \"envelope_version\": \"2.0\",\n     \"message_id\": \"\u003CUUIDv7>\",\n     \"thread_id\": \"\u003Cfrom inbound envelope>\",\n     \"from\": { \"eidolon\": \"gilgamesh\", \"version\": \"\u003Cversion>\" },\n     \"to\": { \"eidolon\": \"orchestrator\" },\n     \"performative\": \"PROPOSE\",\n     \"objective\": \"\u003C=240-char summary of the result>\",\n     \"artifact\": { \"kind\": \"\u003Cresult-kind>\", \"schema_version\": \"1\", \"path\": \"\u003Crel>\", \"sha256\": \"\u003Chex>\", \"size_bytes\": \u003CN> },\n     \"ise\": {\n       \"assertion_grade\": \"validated\",\n       \"provenance\": { \"methodology_version\": \"gilgamesh-\u003Cversion>\", \"tool_surface\": [\"Read\",\"Grep\",\"Glob\",\"Bash(eidolons sandbox:*)\"], \"lateral_consults\": [] },\n       \"receiver_authorization\": { \"auto_route\": true, \"auto_merge\": false, \"auto_deploy\": false }\n     },\n     \"integrity\": { \"method\": \"sha256\", \"value\": \"\u003Chex>\" }\n   }\n   ```\n\n   **`assertion_grade: \"validated\"`** is earned by construction (§4 pre-completion\n   gate), never self-report. **`auto_merge: false`** is load-bearing: the parent\n   applies and commits (PROPOSE-only). **`auto_deploy: false`** mirrors the\n   never-grantable deploy row. `lateral_consults` records a `forge` consult if one\n   informed the result; otherwise empty.\n\nOn `escalate`, emit `ESCALATE` instead, carrying the last oracle output.\n\n---\n\n## Step 3 — Emit handoff-request(s) UPWARD (never dispatch)\n\nFor any work that crossed an **information \u002F authority \u002F modality** boundary, emit a\ntyped `handoff-request` (`schemas\u002Fhandoff-request.v1.json`) as a **PROPOSE to the\norchestrator** — a proposal to route, **not** a dispatch (AC-E09, HC8):\n\n```json\n{\n  \"schema_version\": \"1\",\n  \"kind\": \"handoff-request\",\n  \"objective\": \"\u003Csub-mission goal>\",\n  \"scope\": { \"paths\": [\"...\"], \"mode\": \"read-write\" },\n  \"deliverables\": [\"...\"],\n  \"evidence_required\": [\"\u003Coracle output that will prove it>\"],\n  \"stop_conditions\": [\"...\"],\n  \"suggested_specialist\": \"\u003Catlas|kupo|vigil|idg|forge|...>\",\n  \"evidence_of_boundary\": {\n    \"boundary_kind\": \"authority\",\n    \"rationale\": \"requires deploy authority Gilgamesh's table denies (never-grantable)\"\n  }\n}\n```\n\n**`evidence_of_boundary` is REQUIRED.** Delegation is never justified by \"it looks\ncomplex\" (digest §5) — it must name the boundary: a **separable information context**, an\n**authority Gilgamesh cannot grant itself**, or a **distinct modality Gilgamesh cannot\nverify externally**.\n\n**Cross-check the worker-never-router invariant:** `handoffs.downstream: []`. Gilgamesh\ninvokes **no spawn primitive** and calls no subagent. The orchestrator owns routing;\nGilgamesh only proposes it.\n\n---\n\n## Step 4 — Memory + session end (graceful skip)\n\nAfter emitting PROPOSE:\n\n- `mcp__crystalium__ingest(envelope, payload)` — record the outbound spine for\n  provenance. There is **no post-flight `commit`**: unlike a specialist, Gilgamesh\n  grows no durable pattern library (R-032).\n- `mcp__crystalium__session_end()` on the terminal exit → Dream consolidation.\n\nAll `mcp__crystalium__*` calls are skipped silently when CRYSTALIUM is absent.\n\n---\n\n## Notes\n\n- **Evidence or it did not happen.** Every claim resolves to an oracle result. No\n  anchor → drop the claim; it was never real.\n- **Result PROPOSE, never commit.** The parent applies and commits with its own\n  authority; Gilgamesh holds none.\n- **Handoff is a proposal, not a dispatch.** You return the typed request; the\n  orchestrator routes it. You never spawn.\n\n---\n\n*Attest Skill — Gilgamesh Phase A: audit record + evidence-anchored PROPOSE + upward handoff-request*\n","# Attest Skill — Gilgamesh (Phase A result)\n\n## When to use\n\nLoad when Grind reaches a terminal `stop_state` (`terminate` or `escalate`). Attest\nturns the mission into an audit record and an ECL PROPOSE. Never invoked in Gauge,\nInventory, Lock, or Grind.\n\nThe wanderer leaves with no weapons: everything collected during the mission is either\nreturned here in the Attest record or discarded. Nothing persists (`security.persists:\n[]`).\n\n---\n\n## Step 1 — Finalize the TaskState (the audit record)\n\nComplete `schemas\u002Ftaskstate.v1.json`. Each entry in `claims[]` MUST carry ≥1 external\n**evidence** anchor drawn from `verification_outcomes[]` (an oracle result, a\n`path:line`, or a diff). A claim with no external anchor is **inadmissible** — the\nExcalipoor rule: a proud assertion is worthless if no oracle confirmed the blade.\n\nRecord: final `stop_state`, `verification_outcomes`, `changed_artifacts` (sandbox\npaths), `unresolved_risks`, and the spent `budget`. This is the mission's single audit\nartefact; ship it verbatim.\n\n---\n\n## Step 1a — The report is the attestation (mission report protocol)\n\nWhen the inbound mission enumerates required labeled report lines, your final\nhuman-readable message is itself part of the audit record, not a separate courtesy\nsummary. A report missing any required line — or one that skips enumeration — is an\n**inadmissible attestation**, the same Excalipoor rule an anchor-less claim fails.\n\n**1. Enumerate first.** The FIRST line of the final report is `REQUIRED-LABELS:`\nfollowed by every required label copied from the mission. RE-READ the mission and\nbuild this line before drafting any answer — a report that skips enumeration is\ninvalid regardless of what follows. Do this even under budget pressure.\n\n**2. Label discipline.** Then one line per label, `LABEL: value`. Reproduce each\nlabel **exactly** as the mission gives it, VERBATIM but WITHOUT any parenthetical\nhint: in `EVIDENCE-x (path:line)` the `(path:line)` describes the **value's shape**\nand is never part of the label. Write `EVIDENCE-x: \u003Cpath>:\u003Cline>`. Folding the\nhint into the label turns a matched line into an unmatched one under mechanical\ngrading.\n\n**3. Value format.** The value's FIRST whitespace-delimited token IS the answer —\na number, `pass`\u002F`fail`, or a `path:line` — with explanatory annotation trailing\nafter a space. A grader reading the first token should never have to parse prose to\nfind the answer.\n\n**4. Never omit a line.** If a verification is blocked, its line is still emitted\nwith value `fail` plus the blocker as annotation — never a missing line, and never\na `pass` you did not actually observe.\n\n**Quoted-anchor rule (Excalipoor applied to citations).** Every `path:line` anchor\nyou emit must be followed by a space and a short double-quoted verbatim fragment\n(3–6 words) of that exact line — copied AFTER Reading the line, never from memory.\nIf you cannot quote it, you have not read it; do not cite it. Example:\n`EVIDENCE-enum_count: schemas\u002Froster-entry.schema.json:11 \"scout, planner, coder\"`.\nPrefer a single line over a range.\n\n**Pre-emit anchor re-read rule (mechanical, not exhortative).** Before writing ANY\n`path:line` anchor into the final report, Read that exact line number in that file\nand confirm the line's text contains the verbatim fragment being quoted. If the\nline does not contain the fragment (or is empty\u002Fout of range), the anchor is\nWRONG — re-locate the true line with Grep on the fragment, and cite the corrected\nline number. Never emit an anchor you have not re-read at that exact line in this\nsame mission; the quoted fragment must be present on the cited line. A drifted\nanchor is an inadmissible attestation — the Excalipoor rule applied to line\nnumbers: a citation you cannot re-read is a fake blade. This closes the gap a\nquoted fragment alone does not: a fragment copied once at write-time can still\ndrift onto the wrong line by the time the report is assembled — the re-read\nhappens immediately before the anchor is emitted, not earlier in the mission.\n\n**Repo-only anchor rule.** Evidence and proposal-target anchors MUST point at a\nrepo-relative path that exists in the working checkout (a committed source file).\nNEVER cite an ephemeral, temp, sandbox-scratch, or command-output path (`\u002Ftmp\u002F*`,\nredirected stdout, etc.). If a fact is produced by RUNNING a command, the\ncommand's result belongs in the `VERIFY-\u003Cname>` line; the `EVIDENCE-\u003Ckey>` anchor\npoints at the repo file or script the fact derives from (e.g. cite the script's\nsource line, not its runtime output file).\n\n**Verify-routing ladder.** (1) If the verification command is directly allowed by\nyour tool list (`make`, `bats`, `shellcheck`, `pytest`, `go test`, `jest`, `rspec`,\n`shasum`, `wc`) — run it directly. (2) Otherwise route it through the delegated\nsandbox: `eidolons sandbox run --allow-unsafe-host -- \u003Ccmd>` (see `skills\u002Fgrind\u002FSKILL.md`\n— externalized verification; the sandbox captures pass\u002Ffail). (3) Only if both\nrungs are unavailable, emit `VERIFY-\u003Cx>: fail` immediately followed by the\nblocker. Never skip a rung, never omit the line, never hand-derive a result you\ncould execute.\n\n---\n\n## Step 2 — Emit the result (ECL PROPOSE)\n\nOn `terminate` (success), emit the mission **result** to the orchestrator:\n\n1. Write the result artefact + compute its `sha256` and `size_bytes`.\n2. Compose the ECL v2.0 envelope sidecar (validate against\n   `schemas\u002Fecl-envelope.v2.json`):\n\n   ```json\n   {\n     \"envelope_version\": \"2.0\",\n     \"message_id\": \"\u003CUUIDv7>\",\n     \"thread_id\": \"\u003Cfrom inbound envelope>\",\n     \"from\": { \"eidolon\": \"gilgamesh\", \"version\": \"\u003Cversion>\" },\n     \"to\": { \"eidolon\": \"orchestrator\" },\n     \"performative\": \"PROPOSE\",\n     \"objective\": \"\u003C=240-char summary of the result>\",\n     \"artifact\": { \"kind\": \"\u003Cresult-kind>\", \"schema_version\": \"1\", \"path\": \"\u003Crel>\", \"sha256\": \"\u003Chex>\", \"size_bytes\": \u003CN> },\n     \"ise\": {\n       \"assertion_grade\": \"validated\",\n       \"provenance\": { \"methodology_version\": \"gilgamesh-\u003Cversion>\", \"tool_surface\": [\"Read\",\"Grep\",\"Glob\",\"Bash(eidolons sandbox:*)\"], \"lateral_consults\": [] },\n       \"receiver_authorization\": { \"auto_route\": true, \"auto_merge\": false, \"auto_deploy\": false }\n     },\n     \"integrity\": { \"method\": \"sha256\", \"value\": \"\u003Chex>\" }\n   }\n   ```\n\n   **`assertion_grade: \"validated\"`** is earned by construction (§4 pre-completion\n   gate), never self-report. **`auto_merge: false`** is load-bearing: the parent\n   applies and commits (PROPOSE-only). **`auto_deploy: false`** mirrors the\n   never-grantable deploy row. `lateral_consults` records a `forge` consult if one\n   informed the result; otherwise empty.\n\nOn `escalate`, emit `ESCALATE` instead, carrying the last oracle output.\n\n---\n\n## Step 3 — Emit handoff-request(s) UPWARD (never dispatch)\n\nFor any work that crossed an **information \u002F authority \u002F modality** boundary, emit a\ntyped `handoff-request` (`schemas\u002Fhandoff-request.v1.json`) as a **PROPOSE to the\norchestrator** — a proposal to route, **not** a dispatch (AC-E09, HC8):\n\n```json\n{\n  \"schema_version\": \"1\",\n  \"kind\": \"handoff-request\",\n  \"objective\": \"\u003Csub-mission goal>\",\n  \"scope\": { \"paths\": [\"...\"], \"mode\": \"read-write\" },\n  \"deliverables\": [\"...\"],\n  \"evidence_required\": [\"\u003Coracle output that will prove it>\"],\n  \"stop_conditions\": [\"...\"],\n  \"suggested_specialist\": \"\u003Catlas|kupo|vigil|idg|forge|...>\",\n  \"evidence_of_boundary\": {\n    \"boundary_kind\": \"authority\",\n    \"rationale\": \"requires deploy authority Gilgamesh's table denies (never-grantable)\"\n  }\n}\n```\n\n**`evidence_of_boundary` is REQUIRED.** Delegation is never justified by \"it looks\ncomplex\" (digest §5) — it must name the boundary: a **separable information context**, an\n**authority Gilgamesh cannot grant itself**, or a **distinct modality Gilgamesh cannot\nverify externally**.\n\n**Cross-check the worker-never-router invariant:** `handoffs.downstream: []`. Gilgamesh\ninvokes **no spawn primitive** and calls no subagent. The orchestrator owns routing;\nGilgamesh only proposes it.\n\n---\n\n## Step 4 — Memory + session end (graceful skip)\n\nAfter emitting PROPOSE:\n\n- `mcp__crystalium__ingest(envelope, payload)` — record the outbound spine for\n  provenance. There is **no post-flight `commit`**: unlike a specialist, Gilgamesh\n  grows no durable pattern library (R-032).\n- `mcp__crystalium__session_end()` on the terminal exit → Dream consolidation.\n\nAll `mcp__crystalium__*` calls are skipped silently when CRYSTALIUM is absent.\n\n---\n\n## Notes\n\n- **Evidence or it did not happen.** Every claim resolves to an oracle result. No\n  anchor → drop the claim; it was never real.\n- **Result PROPOSE, never commit.** The parent applies and commits with its own\n  authority; Gilgamesh holds none.\n- **Handoff is a proposal, not a dispatch.** You return the typed request; the\n  orchestrator routes it. You never spawn.\n\n---\n\n*Attest Skill — Gilgamesh Phase A: audit record + evidence-anchored PROPOSE + upward handoff-request*\n",{"name":5,"metadata":24,"description":7},{"phase":25,"methodology":26},"A","Gilgamesh","main","38c3a82583abf9806de764f89ac0099ad690933a",".eidolons\u002Fgilgamesh\u002Fskills\u002Fattest",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 gilgamesh-attest",{"tool":42,"command":43},"bunx","bunx skills add Rynaro\u002Fmagicite --skill gilgamesh-attest",{"tool":45,"command":46},"pnpm","pnpm dlx skills add Rynaro\u002Fmagicite --skill gilgamesh-attest","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FRynaro\u002Fmagicite\u002Fblob\u002Fmain\u002F.eidolons\u002Fgilgamesh\u002Fskills\u002Fattest\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",[],[]]