[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7APTX7CD3DH1B08T0A1HZF5":3,"skill-same:01M7APTX7CD3DH1B08T0A1HZF5":51},{"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":28,"commitSha":29,"skillDirectory":30,"forksCount":31,"repositoryHtmlUrl":32,"repositoryHomepageUrl":6,"ownerHtmlUrl":33,"ownerBlogUrl":34,"ownerDescription":35,"updatedAt":36,"install":37,"resources":50},"01M7APTX7CD3DH1B08T0A1HZF5","atlas-rescout",null,"Incremental delta re-scout (Phase A\u002FT mode) — a READ-ONLY, evidence-anchored re-run that reuses a prior scout-report + its Memex store + a git-diff range to re-probe ONLY the changed surface, carrying unchanged findings forward verbatim. Narrows (does NOT close) the always-on-live-index staleness gap. Use at Phase A intake when a prior scout-report.md + Memex store exist for the same surface and the question is \"what changed since the last scout\" or \"re-verify the prior map against HEAD\". Do NOT use for a first-time scout (run the full A→T→L→A→S cycle instead).","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\u002Fatlas\u002Fskills\u002Frescout\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: atlas-rescout\ndescription: Incremental delta re-scout (Phase A\u002FT mode) — a READ-ONLY, evidence-anchored re-run that reuses a prior scout-report + its Memex store + a git-diff range to re-probe ONLY the changed surface, carrying unchanged findings forward verbatim. Narrows (does NOT close) the always-on-live-index staleness gap. Use at Phase A intake when a prior scout-report.md + Memex store exist for the same surface and the question is \"what changed since the last scout\" or \"re-verify the prior map against HEAD\". Do NOT use for a first-time scout (run the full A→T→L→A→S cycle instead).\nallowed-tools: search_symbol graph_query search_text view_file memex_read\nmetadata:\n  methodology: ATLAS\n  phase: A\n---\n\n# SKILL: Delta re-scout (incremental mode)\n\n## When to use\n\n**Load when:** a prior `scout-report.md` + its Memex excerpt store exist for\nthis surface, and you need to re-establish currency against a newer commit\nwithout re-running the full mission.\n\n**Unload when:** the delta-scout-report is emitted with every prior finding\nre-labelled FRESH \u002F UNCHANGED \u002F RE-VERIFIED \u002F NEWLY-STALE.\n\n**Honest scope (read this first).** This is a *faster evidence-anchored\nre-run*, **not** an always-on live index. ATLAS-as-a-separate-step is intrinsic\nto its read-only-by-construction design; a true always-on index is an\natlas-aci runtime \u002F nexus integration concern. The delta re-scout **narrows\nthe staleness penalty** by re-probing only changed surfaces — it does **not\nclose** the live-index gap. Do not over-claim it.\n\nThis mode is read-only (I-1). It reads `git diff` \u002F `git log` via the existing\ndeterministic Traverse ladder (`rg` \u002F `git log` in `skills\u002Ftraverse\u002FSKILL.md`), never\na write tool. Memory recall and Memex reads are permitted under I-1.\n\n---\n\n## Contract\n\n| Field | Value |\n|-------|-------|\n| LLM calls permitted | At the synthesis edge only; the changed-surface computation is deterministic. |\n| Tool budget | Bounded by the changed-surface size, not the full repo — this is the whole point. |\n| Output | `delta-scout-report.md` — same class as `scout-report.md`, with a section-3 finding-status label per finding. |\n\n---\n\n## Inputs\n\n1. **Prior `scout-report.md`** (surfaced by `mcp__crystalium__recall` at Phase A\n   intake, or supplied by the parent) — its `FINDING-XXX` records with\n   `path:line` anchors and the originating commit.\n2. **Prior Memex store** — the byte-exact excerpts those findings cited.\n3. **A git-diff range** — `\u003Cprior_mission_commit>..HEAD` (the prior commit is\n   recorded in the prior scout-report telemetry; if absent, fall back to the\n   prior report's git heatmap base).\n\n---\n\n## Procedure\n\n### Step 1 — Compute the changed surface (deterministic)\n\n```\ngit diff --name-only \u003Cprior_mission_commit>..HEAD\n```\n\nIntersect the changed file set with the prior `map.md` `MAP-MODULES`:\n\n```\nCHANGED-SURFACE = diff_files ∩ prior MAP-MODULES (and their MAP-GRAPH neighbours)\n```\n\nFiles that changed but lie outside the prior scope are noted in `MAP-GAPS`\n(they may warrant a full scout, not a delta) but are not re-probed here.\n\n### Step 2 — Re-run Phase T over the changed surface ONLY\n\nRe-map structure (entrypoints, modules, call-graph edges) **only** for\n`CHANGED-SURFACE`. Deterministic and cheap — Tree-sitter \u002F `rg` \u002F `git log`,\nno LLM calls (Phase T rule). Unchanged regions reuse the prior `map.md` slice\nverbatim.\n\n### Step 3 — Mark prior findings STALE by anchor intersection\n\nA prior `FINDING-XXX` is **STALE** iff its anchored `path:line_start-line_end`\nrange intersects a changed hunk in the diff. Findings whose anchors are\nuntouched are **not** re-probed.\n\n### Step 4 — Re-probe ONLY the stale findings\n\nFor each STALE finding, run the `skills\u002Flocate\u002FSKILL.md` Tier 1–5 probe ladder over\nits anchor, producing an updated finding (new anchor, new confidence). This is\nthe only LLM-synthesis-edge work in the mode.\n\n### Step 5 — Carry forward UNCHANGED findings verbatim\n\nFindings whose anchors were untouched are copied **verbatim from Memex** —\nclaim, anchor, confidence, and `excerpt_ref` unchanged. **Provenance is\npreserved**; this is ATLAS's differentiator (read-only + evidence-anchored +\nauditable lineage). Do not re-author what did not change.\n\n---\n\n## Output — delta-scout-report.md\n\nSame class and section layout as `scout-report.md` (reuse the existing\n`templates\u002Fscout-report.md` and `schemas\u002Fscout-report.v1.json`). Section 3 of\nthe delta report labels **every** finding with its delta status:\n\n| Label | Meaning |\n|-------|---------|\n| `FRESH` | New finding, no prior counterpart (surfaced by the changed surface). |\n| `UNCHANGED` | Carried forward verbatim from Memex; anchor untouched by the diff. |\n| `RE-VERIFIED` | Prior finding whose anchor was touched, re-probed, claim still holds (possibly new line range). |\n| `NEWLY-STALE` | Prior finding whose anchor was touched and the claim no longer holds; superseded or dropped to a `GAP`. |\n\nEach label records the **originating commit** (the prior commit for\nUNCHANGED\u002Fcarried-forward, `HEAD` for FRESH\u002FRE-VERIFIED) so the lineage is\nauditable.\n\n---\n\n## Stop condition\n\nThe delta re-scout completes when **every prior finding has a delta label**\nand **every changed-surface region** has either a FRESH finding or a `GAP`.\nNo re-scatter beyond `PERSONA.md` P0 rule 9 (max recursion = 1).\n\n---\n\n## Telemetry\n\n```\ndelta-rescout | changed_files: \u003Cn> | stale_findings: \u003Cn> | unchanged_carried: \u003Cn>\n              | fresh: \u003Cn> | reverified: \u003Cn> | newly_stale: \u003Cn>\n              | reprobe_tool_calls: \u003Cn vs full-scout estimate>\n```\n\nThe `reprobe_tool_calls vs full-scout estimate` ratio is the staleness-saving\nsignal — it quantifies how much of the live-index gap the delta narrowed.\n\n---\n\n## Exit gate\n\n- [ ] Changed surface computed deterministically (`git diff` ∩ prior MAP-MODULES).\n- [ ] Phase T re-ran over the changed surface ONLY; unchanged map reused verbatim.\n- [ ] Every prior finding labelled FRESH \u002F UNCHANGED \u002F RE-VERIFIED \u002F NEWLY-STALE\n      with an originating commit.\n- [ ] UNCHANGED findings carried verbatim from Memex (provenance preserved).\n- [ ] Changed-surface files outside prior scope noted in `MAP-GAPS`, not silently dropped.\n- [ ] Report does NOT claim to be an always-on index — staleness narrowed, not closed.\n","# SKILL: Delta re-scout (incremental mode)\n\n## When to use\n\n**Load when:** a prior `scout-report.md` + its Memex excerpt store exist for\nthis surface, and you need to re-establish currency against a newer commit\nwithout re-running the full mission.\n\n**Unload when:** the delta-scout-report is emitted with every prior finding\nre-labelled FRESH \u002F UNCHANGED \u002F RE-VERIFIED \u002F NEWLY-STALE.\n\n**Honest scope (read this first).** This is a *faster evidence-anchored\nre-run*, **not** an always-on live index. ATLAS-as-a-separate-step is intrinsic\nto its read-only-by-construction design; a true always-on index is an\natlas-aci runtime \u002F nexus integration concern. The delta re-scout **narrows\nthe staleness penalty** by re-probing only changed surfaces — it does **not\nclose** the live-index gap. Do not over-claim it.\n\nThis mode is read-only (I-1). It reads `git diff` \u002F `git log` via the existing\ndeterministic Traverse ladder (`rg` \u002F `git log` in `skills\u002Ftraverse\u002FSKILL.md`), never\na write tool. Memory recall and Memex reads are permitted under I-1.\n\n---\n\n## Contract\n\n| Field | Value |\n|-------|-------|\n| LLM calls permitted | At the synthesis edge only; the changed-surface computation is deterministic. |\n| Tool budget | Bounded by the changed-surface size, not the full repo — this is the whole point. |\n| Output | `delta-scout-report.md` — same class as `scout-report.md`, with a section-3 finding-status label per finding. |\n\n---\n\n## Inputs\n\n1. **Prior `scout-report.md`** (surfaced by `mcp__crystalium__recall` at Phase A\n   intake, or supplied by the parent) — its `FINDING-XXX` records with\n   `path:line` anchors and the originating commit.\n2. **Prior Memex store** — the byte-exact excerpts those findings cited.\n3. **A git-diff range** — `\u003Cprior_mission_commit>..HEAD` (the prior commit is\n   recorded in the prior scout-report telemetry; if absent, fall back to the\n   prior report's git heatmap base).\n\n---\n\n## Procedure\n\n### Step 1 — Compute the changed surface (deterministic)\n\n```\ngit diff --name-only \u003Cprior_mission_commit>..HEAD\n```\n\nIntersect the changed file set with the prior `map.md` `MAP-MODULES`:\n\n```\nCHANGED-SURFACE = diff_files ∩ prior MAP-MODULES (and their MAP-GRAPH neighbours)\n```\n\nFiles that changed but lie outside the prior scope are noted in `MAP-GAPS`\n(they may warrant a full scout, not a delta) but are not re-probed here.\n\n### Step 2 — Re-run Phase T over the changed surface ONLY\n\nRe-map structure (entrypoints, modules, call-graph edges) **only** for\n`CHANGED-SURFACE`. Deterministic and cheap — Tree-sitter \u002F `rg` \u002F `git log`,\nno LLM calls (Phase T rule). Unchanged regions reuse the prior `map.md` slice\nverbatim.\n\n### Step 3 — Mark prior findings STALE by anchor intersection\n\nA prior `FINDING-XXX` is **STALE** iff its anchored `path:line_start-line_end`\nrange intersects a changed hunk in the diff. Findings whose anchors are\nuntouched are **not** re-probed.\n\n### Step 4 — Re-probe ONLY the stale findings\n\nFor each STALE finding, run the `skills\u002Flocate\u002FSKILL.md` Tier 1–5 probe ladder over\nits anchor, producing an updated finding (new anchor, new confidence). This is\nthe only LLM-synthesis-edge work in the mode.\n\n### Step 5 — Carry forward UNCHANGED findings verbatim\n\nFindings whose anchors were untouched are copied **verbatim from Memex** —\nclaim, anchor, confidence, and `excerpt_ref` unchanged. **Provenance is\npreserved**; this is ATLAS's differentiator (read-only + evidence-anchored +\nauditable lineage). Do not re-author what did not change.\n\n---\n\n## Output — delta-scout-report.md\n\nSame class and section layout as `scout-report.md` (reuse the existing\n`templates\u002Fscout-report.md` and `schemas\u002Fscout-report.v1.json`). Section 3 of\nthe delta report labels **every** finding with its delta status:\n\n| Label | Meaning |\n|-------|---------|\n| `FRESH` | New finding, no prior counterpart (surfaced by the changed surface). |\n| `UNCHANGED` | Carried forward verbatim from Memex; anchor untouched by the diff. |\n| `RE-VERIFIED` | Prior finding whose anchor was touched, re-probed, claim still holds (possibly new line range). |\n| `NEWLY-STALE` | Prior finding whose anchor was touched and the claim no longer holds; superseded or dropped to a `GAP`. |\n\nEach label records the **originating commit** (the prior commit for\nUNCHANGED\u002Fcarried-forward, `HEAD` for FRESH\u002FRE-VERIFIED) so the lineage is\nauditable.\n\n---\n\n## Stop condition\n\nThe delta re-scout completes when **every prior finding has a delta label**\nand **every changed-surface region** has either a FRESH finding or a `GAP`.\nNo re-scatter beyond `PERSONA.md` P0 rule 9 (max recursion = 1).\n\n---\n\n## Telemetry\n\n```\ndelta-rescout | changed_files: \u003Cn> | stale_findings: \u003Cn> | unchanged_carried: \u003Cn>\n              | fresh: \u003Cn> | reverified: \u003Cn> | newly_stale: \u003Cn>\n              | reprobe_tool_calls: \u003Cn vs full-scout estimate>\n```\n\nThe `reprobe_tool_calls vs full-scout estimate` ratio is the staleness-saving\nsignal — it quantifies how much of the live-index gap the delta narrowed.\n\n---\n\n## Exit gate\n\n- [ ] Changed surface computed deterministically (`git diff` ∩ prior MAP-MODULES).\n- [ ] Phase T re-ran over the changed surface ONLY; unchanged map reused verbatim.\n- [ ] Every prior finding labelled FRESH \u002F UNCHANGED \u002F RE-VERIFIED \u002F NEWLY-STALE\n      with an originating commit.\n- [ ] UNCHANGED findings carried verbatim from Memex (provenance preserved).\n- [ ] Changed-surface files outside prior scope noted in `MAP-GAPS`, not silently dropped.\n- [ ] Report does NOT claim to be an always-on index — staleness narrowed, not closed.\n",{"name":5,"metadata":24,"description":7,"allowed-tools":27},{"phase":25,"methodology":26},"A","ATLAS","search_symbol graph_query search_text view_file memex_read","main","38c3a82583abf9806de764f89ac0099ad690933a",".eidolons\u002Fatlas\u002Fskills\u002Frescout",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":38,"prompt":48,"zipAvailable":49},[39,42,45],{"tool":40,"command":41},"npx","npx skills add Rynaro\u002Fmagicite --skill atlas-rescout",{"tool":43,"command":44},"bunx","bunx skills add Rynaro\u002Fmagicite --skill atlas-rescout",{"tool":46,"command":47},"pnpm","pnpm dlx skills add Rynaro\u002Fmagicite --skill atlas-rescout","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FRynaro\u002Fmagicite\u002Fblob\u002Fmain\u002F.eidolons\u002Fatlas\u002Fskills\u002Frescout\u002FSKILL.md",true,[],[52,59,66,73,80,87],{"skillNo":53,"name":54,"nameZh":6,"description":55,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":56,"categories":57,"keywords":58,"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":60,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":65,"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":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"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":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"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":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"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":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"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",[],[]]