[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7APVF0PJ3E3XKXYWQQ8HVGQ":3,"skill-same:01M7APVF0PJ3E3XKXYWQQ8HVGQ":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},"01M7APVF0PJ3E3XKXYWQQ8HVGQ","atlas-traverse",null,"Phase T (Traverse) — deterministic structural mapping of a codebase. Zero LLM calls during retrieval; only symbol index, AST, ripgrep, and git log. Emits map.md with entrypoints, modules, call graph, and heatmap. Use after mission.md is valid and before any meaning-based search. Trigger phrases — \"map the repo\", \"what are the entrypoints\", \"build the call graph\", \"list all routes\u002Fworkers\u002FCLIs\".","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\u002Ftraverse\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: atlas-traverse\ndescription: Phase T (Traverse) — deterministic structural mapping of a codebase. Zero LLM calls during retrieval; only symbol index, AST, ripgrep, and git log. Emits map.md with entrypoints, modules, call graph, and heatmap. Use after mission.md is valid and before any meaning-based search. Trigger phrases — \"map the repo\", \"what are the entrypoints\", \"build the call graph\", \"list all routes\u002Fworkers\u002FCLIs\".\nallowed-tools: view_file list_dir search_text search_symbol graph_query\nmetadata:\n  methodology: ATLAS\n  phase: T\n---\n\n# SKILL: Traverse — structural mapping (Phase T)\n\n## When to use\n\n**Load when:** Phase A (Assess) has produced a valid `mission.md` and you are\nabout to emit `map.md`.\n\n**Unload when:** `map.md` passes exit criteria and you enter Phase L (Locate).\n\n> **Memory pre-flight:** `recall` MUST have fired in Phase A (see `PERSONA.md`\n> §\"Memory pre-flight\") before Phase T begins. If it hasn't — e.g. this skill\n> was loaded directly — call it now with the mission objective and target paths\n> before any structural mapping. Fold relevant prior maps and known traps into\n> your mission context. If `mcp__crystalium__*` tools are unavailable, proceed\n> without memory — never hard-fail.\n\n---\n\n## Contract\n\n| Field | Value |\n|-------|-------|\n| LLM calls permitted | **Zero** during retrieval. LLM used only to author the final `map.md` summary. |\n| Tool budget | ≤ 20% of mission `max_tool_calls` |\n| Output | `map.md` conforming to `templates\u002Ftraversal-map.md` |\n\nIf you find yourself reasoning about *meaning*, stop — that's Phase L.\nTraverse is about *structure*.\n\n---\n\n## Deterministic retrieval ladder\n\nTry in order. Stop at the first that works for the mission scope.\n\n### 1. Code-graph MCP server (preferred)\n\nIf the host provides a code-graph server (e.g. Sourcegraph, a Tree-sitter\nindex over MCP, a Prism-based graph for Ruby):\n\n```\ngraph.roots(scope=\u003Cglobs>)                 # entrypoints\ngraph.modules(scope=\u003Cglobs>, top_n=20)     # centrality-ranked\ngraph.edges(scope=\u003Cglobs>, kind=call|import|inherit)\n```\n\nThese are O(1) lookups into an indexed structure. No file reads.\n\n### 2. Language-native AST\n\nFor single-language repos without a graph server:\n\n- **Ruby** → `prism` (`Prism.parse_file`, walk `CallNode` \u002F `DefNode`)\n- **Python** → stdlib `ast`\n- **TypeScript\u002FJavaScript** → `@typescript-eslint\u002Fparser` or `tree-sitter-typescript`\n- **Go** → `go\u002Fast` + `go\u002Ftypes`\n- **Anything else** → Tree-sitter with the appropriate grammar\n\nEmit a small script via `execute_read_only_script` (if the harness allows it)\nor delegate to a deterministic MCP tool. **Never paste file contents into the\nLLM to \"parse\" them.** That's the Inference Trap.\n\n### 3. `rg` (ripgrep) for coarse structural signals\n\nWhen AST is unavailable or the scope crosses languages:\n\n```\nrg --files \u003Cscope>                 # file enumeration\nrg -l '^class |^module ' \u003Cscope>   # class\u002Fmodule surface\nrg -l 'Rails.application.routes'   # routing entrypoints\n```\n\nAlways use `--files` or `-l` (filenames only) at this stage. You are not\nreading content yet.\n\n### 4. `git log` for heatmap\n\n```\ngit log --since='90 days' --name-only --pretty=format: \u003Cscope> | sort | uniq -c | sort -rn | head -30\ngit log --follow --format='%an' \u003Cfile> | sort | uniq -c | sort -rn\n```\n\nProduces `MAP-HEATMAP` entries: churn + primary contributors. Optional but\nhigh-signal for risk assessment.\n\n---\n\n## Entrypoint taxonomy (`MAP-ROOTS`)\n\nThe mission `DECISION_TARGET` almost always traces back to one of:\n\n- **HTTP routes** (Rails routes, Express\u002FKoa handlers, FastAPI, gRPC services)\n- **Background workers** (Sidekiq, Celery, RQ, Temporal workflows)\n- **CLI entrypoints** (`bin\u002F`, `rake` tasks, `click`\u002F`cobra` commands)\n- **Public library API** (gem top-level, `__init__.py` re-exports, package `main`)\n- **Event handlers** (webhooks, message consumers, scheduled jobs)\n- **Test surfaces** (integration tests as executable specs of behavior)\n\nIdentify the root category relevant to the mission and enumerate exhaustively\nwithin scope. Ignore others.\n\n---\n\n## What to skip by default\n\nHardcoded skip list (override only when mission explicitly requires):\n\n```\nnode_modules\u002F   vendor\u002Fbundle\u002F    vendor\u002Fcache\u002F\ntmp\u002F            log\u002F              .git\u002F\ndist\u002F           build\u002F            public\u002Fassets\u002F\ncoverage\u002F       .bundle\u002F          __pycache__\u002F\n*.min.js        *.map             *.lock\n```\n\nGenerated code and vendored dependencies are noise at this phase.\n\n---\n\n## Ambiguity handling\n\n- **Monorepo?** Ask which package(s) the mission applies to. Don't guess.\n- **Multi-language?** Build `MAP-MODULES` per language; edges only within language.\n- **Un-parseable file?** Record in `MAP-GAPS`, don't retry with different parsers.\n\n---\n\n## Exit gate\n\nBefore emitting `map.md`, check:\n\n- [ ] `MAP-ROOTS` is non-empty and every entry is a real file.\n- [ ] `MAP-MODULES` top-N is ranked by a deterministic metric, not by LLM guess.\n- [ ] `MAP-GRAPH` edges are all AST-derived or graph-server-derived, never\n      LLM-inferred.\n- [ ] `MAP-GAPS` lists every region the index couldn't parse.\n- [ ] Total token cost for Phase T ≤ 20% of mission budget.\n\nIf any fails, the mission is likely out of scope or the toolchain is\ninsufficient — halt and report.\n\n---\n\n## Common anti-patterns\n\n| Anti-pattern | Why it's wrong | Fix |\n|--------------|----------------|-----|\n| \"Let me read `app\u002Fcontrollers\u002F*.rb` to understand routing\" | Wastes thousands of tokens on content the router already knows | Query `Rails.application.routes.routes` or parse `config\u002Froutes.rb` with Prism |\n| \"I'll grep for `class.*Service`\" | Captures junk, misses the real hierarchy | Use AST to get every `class` declaration with its superclass |\n| \"Give me a summary of this module\" | That's interpretation, i.e. Phase L | Traverse answers *what exists*, not *what it means* |\n| Loading AST of every file \"just in case\" | Blows the budget before Locate starts | Build the map from *structural* signals; let Locate zoom in |\n","# SKILL: Traverse — structural mapping (Phase T)\n\n## When to use\n\n**Load when:** Phase A (Assess) has produced a valid `mission.md` and you are\nabout to emit `map.md`.\n\n**Unload when:** `map.md` passes exit criteria and you enter Phase L (Locate).\n\n> **Memory pre-flight:** `recall` MUST have fired in Phase A (see `PERSONA.md`\n> §\"Memory pre-flight\") before Phase T begins. If it hasn't — e.g. this skill\n> was loaded directly — call it now with the mission objective and target paths\n> before any structural mapping. Fold relevant prior maps and known traps into\n> your mission context. If `mcp__crystalium__*` tools are unavailable, proceed\n> without memory — never hard-fail.\n\n---\n\n## Contract\n\n| Field | Value |\n|-------|-------|\n| LLM calls permitted | **Zero** during retrieval. LLM used only to author the final `map.md` summary. |\n| Tool budget | ≤ 20% of mission `max_tool_calls` |\n| Output | `map.md` conforming to `templates\u002Ftraversal-map.md` |\n\nIf you find yourself reasoning about *meaning*, stop — that's Phase L.\nTraverse is about *structure*.\n\n---\n\n## Deterministic retrieval ladder\n\nTry in order. Stop at the first that works for the mission scope.\n\n### 1. Code-graph MCP server (preferred)\n\nIf the host provides a code-graph server (e.g. Sourcegraph, a Tree-sitter\nindex over MCP, a Prism-based graph for Ruby):\n\n```\ngraph.roots(scope=\u003Cglobs>)                 # entrypoints\ngraph.modules(scope=\u003Cglobs>, top_n=20)     # centrality-ranked\ngraph.edges(scope=\u003Cglobs>, kind=call|import|inherit)\n```\n\nThese are O(1) lookups into an indexed structure. No file reads.\n\n### 2. Language-native AST\n\nFor single-language repos without a graph server:\n\n- **Ruby** → `prism` (`Prism.parse_file`, walk `CallNode` \u002F `DefNode`)\n- **Python** → stdlib `ast`\n- **TypeScript\u002FJavaScript** → `@typescript-eslint\u002Fparser` or `tree-sitter-typescript`\n- **Go** → `go\u002Fast` + `go\u002Ftypes`\n- **Anything else** → Tree-sitter with the appropriate grammar\n\nEmit a small script via `execute_read_only_script` (if the harness allows it)\nor delegate to a deterministic MCP tool. **Never paste file contents into the\nLLM to \"parse\" them.** That's the Inference Trap.\n\n### 3. `rg` (ripgrep) for coarse structural signals\n\nWhen AST is unavailable or the scope crosses languages:\n\n```\nrg --files \u003Cscope>                 # file enumeration\nrg -l '^class |^module ' \u003Cscope>   # class\u002Fmodule surface\nrg -l 'Rails.application.routes'   # routing entrypoints\n```\n\nAlways use `--files` or `-l` (filenames only) at this stage. You are not\nreading content yet.\n\n### 4. `git log` for heatmap\n\n```\ngit log --since='90 days' --name-only --pretty=format: \u003Cscope> | sort | uniq -c | sort -rn | head -30\ngit log --follow --format='%an' \u003Cfile> | sort | uniq -c | sort -rn\n```\n\nProduces `MAP-HEATMAP` entries: churn + primary contributors. Optional but\nhigh-signal for risk assessment.\n\n---\n\n## Entrypoint taxonomy (`MAP-ROOTS`)\n\nThe mission `DECISION_TARGET` almost always traces back to one of:\n\n- **HTTP routes** (Rails routes, Express\u002FKoa handlers, FastAPI, gRPC services)\n- **Background workers** (Sidekiq, Celery, RQ, Temporal workflows)\n- **CLI entrypoints** (`bin\u002F`, `rake` tasks, `click`\u002F`cobra` commands)\n- **Public library API** (gem top-level, `__init__.py` re-exports, package `main`)\n- **Event handlers** (webhooks, message consumers, scheduled jobs)\n- **Test surfaces** (integration tests as executable specs of behavior)\n\nIdentify the root category relevant to the mission and enumerate exhaustively\nwithin scope. Ignore others.\n\n---\n\n## What to skip by default\n\nHardcoded skip list (override only when mission explicitly requires):\n\n```\nnode_modules\u002F   vendor\u002Fbundle\u002F    vendor\u002Fcache\u002F\ntmp\u002F            log\u002F              .git\u002F\ndist\u002F           build\u002F            public\u002Fassets\u002F\ncoverage\u002F       .bundle\u002F          __pycache__\u002F\n*.min.js        *.map             *.lock\n```\n\nGenerated code and vendored dependencies are noise at this phase.\n\n---\n\n## Ambiguity handling\n\n- **Monorepo?** Ask which package(s) the mission applies to. Don't guess.\n- **Multi-language?** Build `MAP-MODULES` per language; edges only within language.\n- **Un-parseable file?** Record in `MAP-GAPS`, don't retry with different parsers.\n\n---\n\n## Exit gate\n\nBefore emitting `map.md`, check:\n\n- [ ] `MAP-ROOTS` is non-empty and every entry is a real file.\n- [ ] `MAP-MODULES` top-N is ranked by a deterministic metric, not by LLM guess.\n- [ ] `MAP-GRAPH` edges are all AST-derived or graph-server-derived, never\n      LLM-inferred.\n- [ ] `MAP-GAPS` lists every region the index couldn't parse.\n- [ ] Total token cost for Phase T ≤ 20% of mission budget.\n\nIf any fails, the mission is likely out of scope or the toolchain is\ninsufficient — halt and report.\n\n---\n\n## Common anti-patterns\n\n| Anti-pattern | Why it's wrong | Fix |\n|--------------|----------------|-----|\n| \"Let me read `app\u002Fcontrollers\u002F*.rb` to understand routing\" | Wastes thousands of tokens on content the router already knows | Query `Rails.application.routes.routes` or parse `config\u002Froutes.rb` with Prism |\n| \"I'll grep for `class.*Service`\" | Captures junk, misses the real hierarchy | Use AST to get every `class` declaration with its superclass |\n| \"Give me a summary of this module\" | That's interpretation, i.e. Phase L | Traverse answers *what exists*, not *what it means* |\n| Loading AST of every file \"just in case\" | Blows the budget before Locate starts | Build the map from *structural* signals; let Locate zoom in |\n",{"name":5,"metadata":24,"description":7,"allowed-tools":27},{"phase":25,"methodology":26},"T","ATLAS","view_file list_dir search_text search_symbol graph_query","main","38c3a82583abf9806de764f89ac0099ad690933a",".eidolons\u002Fatlas\u002Fskills\u002Ftraverse",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-traverse",{"tool":43,"command":44},"bunx","bunx skills add Rynaro\u002Fmagicite --skill atlas-traverse",{"tool":46,"command":47},"pnpm","pnpm dlx skills add Rynaro\u002Fmagicite --skill atlas-traverse","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FRynaro\u002Fmagicite\u002Fblob\u002Fmain\u002F.eidolons\u002Fatlas\u002Fskills\u002Ftraverse\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",[],[]]