[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DBA0W2YD87ANMDJX7YBTX2":3,"skill-same:01M6DBA0W2YD87ANMDJX7YBTX2":80},{"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":28,"publishedAt":49,"linkOnly":50,"markdownContent":51,"markdownBody":52,"frontMatter":53,"refName":54,"commitSha":55,"skillDirectory":56,"forksCount":14,"repositoryHtmlUrl":57,"repositoryHomepageUrl":6,"ownerHtmlUrl":58,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":59,"install":60,"resources":73},"01M6DBA0W2YD87ANMDJX7YBTX2","design-studio-session",null,"The interactive-modify capability behind `design-studio session` mode. Use when the owner wants to point at a LIVE element in a running app (Reframe, momentstudio, WebCoder, bilbo) and iteratively restyle it with Claude and Codex — preview candidates as injected style overlays FIRST, resolve the clicked element back to its source file:line, apply ONE scoped micro-commit, incrementally re-audit only the changed screen, and auto-decide KEEP or REVERT through the SAME revert-gate as the batch design-review loop. Do NOT use for a whole-app batch audit (use design-studio \u002F ui-audit) or for driving the app without modifying it (use ui-drive).","Prekzursil\u002Fagent-skills-toolchain","Prekzursil","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F54636077?v=4","01M6DACZ1PCQHD99SCR1YXG28B","Andrei Mihai Visalon","01M6DACZ670WZF535V3WYYSS4Z",0,"MIT","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fdesign-studio-session\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000015","视觉设计","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":26,"taxonomyTypeDesc":27},"01JBSEEDCAT000000000000032","设计师","PROFESSION","适用职业",[29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48],"session","design studio session","design","use","review","app","as","preview","back","do","only","auto","commit","codex","interactive","decide","loop","first","file","batch","2026-11-10 10:12:30",false,"---\nname: design-studio-session\ndescription: The interactive-modify capability behind `design-studio session` mode. Use when the owner wants to point at a LIVE element in a running app (Reframe, momentstudio, WebCoder, bilbo) and iteratively restyle it with Claude and Codex — preview candidates as injected style overlays FIRST, resolve the clicked element back to its source file:line, apply ONE scoped micro-commit, incrementally re-audit only the changed screen, and auto-decide KEEP or REVERT through the SAME revert-gate as the batch design-review loop. Do NOT use for a whole-app batch audit (use design-studio \u002F ui-audit) or for driving the app without modifying it (use ui-drive).\n---\n\n# design-studio session — interactive-modify (gem N.2)\n\nThe **interactive twin** of the batch `design-studio`. Where the batch loop audits a\nwhole flow G0→G7, `session` runs ONE tight modify cycle per element, with the owner in the\nloop and Claude + Codex as rival suggesters. It is deliberately a **consolidation, not a new\nruntime**: it reuses the **same revert-gate**, the **same ui-audit summary shape**, and the\n**same `loop-state.json` scope** as the batch loop, so it kills the overlap instead of\nre-creating it (UIUX N.2 §89).\n\n> Routed to by the `design-studio` meta-skill's `session` mode. Standalone entry:\n> `node session.mjs \u003Csubcommand>`. No new deps, no new runtime.\n\n## The cycle (UIUX N.2 §2.2)\n\n```\nDRIVE (ui-drive) → AUDIT baseline (ui-audit, cached)\n  → PICK      owner clicks a live element → element→source picker resolves {selector, file:line, rect, computedStyle}\n  → SUGGEST   Claude + Codex register N candidates, each a LIVE injected-style overlay FIRST (by:claude|codex)\n  → OVERLAY   preview every candidate BEFORE any source edit (reload = gone → reversible by construction)\n  → SELECT    Artifact side-by-side gallery + one AskUserQuestion → owner picks (or \"keep as-is\")\n  → APPLY     ONE scoped micro-commit on a design\u002Flive-\u003Cid> branch — the picked file ONLY\n  → REAUDIT   incremental: changed screen only → delta from the ui-audit summary\n  → REVERT-GATE  shared revertDecision(): KEEP or REVERT → loop\n  → batch Figma-mirror every K accepts (hand off to design-studio mirror)\n```\n\n**Why overlay-first:** each candidate is an injected `style` tag (`data-candidate`) on the\nrunning app **before any source edit** — instant (\u003C1s vs edit+HMR) and reversible-by-reload, so\nthe revert-gate only ever arbitrates changes the owner already **accepted** (UIUX N.2 §91).\n\n**Why element→source, not vision:** the picker rebuilds the react-dev-inspector \u002F\ncode-inspector-plugin pattern thin on `evaluate_script` — a click resolves the React fiber's\n`_debugSource` (or `data-insp-path` attrs) to a real `file:line`. Deterministic; beats VLM\nSet-of-Mark guessing (the Cursor-2.0 \u002F stagewise pattern; UIUX N.2 §90).\n\n**Why external audit at all:** LLMs cannot reliably self-correct without external feedback\n(ICLR-2024) — the incremental re-audit is what makes model-suggested edits trustworthy.\n\n## Dual-agent mingle (UIUX N.2 §92)\n\n| Role | Agent | Contract |\n|---|---|---|\n| **driver \u002F applier** | **Claude** | holds the `mcp_agent_mail` file-lease on the picked source; the ONLY writer of the apply-back micro-commit |\n| **rival-suggester + independent re-auditor** | **Codex** | posts candidates (`by:codex`) and its own KEEP\u002FREVERT verdict; **never edits the leased file** |\n\nCandidate pools merge **attributed**; agreement across vendors is the signal (independent\nfailures); disagreement **escalates to the owner** — never auto-resolves to consensus. Emit the\nlease\u002Frole card with `node session.mjs mingle`.\n\n## Subcommands\n\n| cmd | does |\n|---|---|\n| `start --app \u003Cn> --flow \u003C\u002Fpath> --url \u003Curl> [--repo \u003Cpath>]` | open a session; **inherits scope from `loop-state.json`** if present; records the `design\u002Flive-\u003Cid>` branch |\n| `pick --selector \u003Csel> --file \u003Cpath:line>` | record the picked element→source target. `pick --emit-script` prints the browser picker JS for `evaluate_script` |\n| `suggest --cid \u003Cid> --selector \u003Csel> --css \"\u003Cdecls>\" --by \u003Cclaude\\|codex> [--dims \"contrast:+1\"]` | register a candidate + print its overlay markup |\n| `overlay --cid \u003Cid>` | print the injectable style tag + the `evaluate_script` inject snippet (preview) |\n| `gallery` | write `gallery.json` (before + N candidates + predicted deltas) for an Artifact + one AskUserQuestion |\n| `select --cid \u003Cid\\|keep>` | owner's choice (`keep` = no change; the cycle still closes clean) |\n| `apply [--commit --repo \u003Cpath>]` | scoped micro-commit. **Default = SHADOW plan** (prints the exact scoped `git add \u003Cfile>` — never `git add -A`); `--commit` executes a single-file commit |\n| `reaudit --before \u003Caudit.json> --after \u003Caudit.json>` | incremental delta from the ui-audit `summary` → `delta.json` |\n| `revert [--enforce --repo \u003Cpath>]` | the **shared** G6 revert-gate over the delta. **SHADOW by default**: logs the decision + emits the scoped rollback command, never mutates the repo |\n| `mingle` \u002F `status` | print the mingle card \u002F the session ledger |\n\n## Safety \u002F SHADOW (council C5)\n\n- The **revert-gate is SHADOW by default** — it decides + logs + emits the recommended scoped\n  rollback but **never mutates the repo**. Enforcement is opt-in (`revert --enforce`) and only\n  ever runs a scoped `git revert --no-edit \u003Csha>` on the candidate commit.\n- `apply` is scoped to the **picked file only** (execFile array args, no shell) — it can never\n  `git add -A`. Every apply-back is one reversible commit; the revert-gate arbitrates it.\n- Overlay previews touch only the DOM of the running app (a `data-candidate` style tag) — they\n  never write to disk and vanish on reload.\n\n## Consolidation ledger (what it reuses, not rebuilds)\n\n- **revert-gate:** dynamically imports `revertDecision()` from the sibling\n  `design-studio` `gates.mjs`; a byte-identical `inlineRevert`\n  fallback keeps it standalone. Same KEEP\u002FREVERT law as the batch loop.\n- **audit summary:** `scoreSummary()` reads ui-audit's `run_audit.mjs` `aggregate().summary`\n  (pageErrors, clickErrors, deadControls, axe, spacing, affordance, motion) — no new metric.\n- **state:** `session-state.json` carries `loopStateRef` and inherits `app\u002Fflow\u002FsourceOfTruth`\n  from `loop-state.json`; the session is the interactive specialization of the batch G5↔G6.\n\nEvidence: MASTER §N.2 · UIUX-CONSOLIDATION-DECISION-QUEUE §2.2, §89–95, N.2, K.5.\n","# design-studio session — interactive-modify (gem N.2)\n\nThe **interactive twin** of the batch `design-studio`. Where the batch loop audits a\nwhole flow G0→G7, `session` runs ONE tight modify cycle per element, with the owner in the\nloop and Claude + Codex as rival suggesters. It is deliberately a **consolidation, not a new\nruntime**: it reuses the **same revert-gate**, the **same ui-audit summary shape**, and the\n**same `loop-state.json` scope** as the batch loop, so it kills the overlap instead of\nre-creating it (UIUX N.2 §89).\n\n> Routed to by the `design-studio` meta-skill's `session` mode. Standalone entry:\n> `node session.mjs \u003Csubcommand>`. No new deps, no new runtime.\n\n## The cycle (UIUX N.2 §2.2)\n\n```\nDRIVE (ui-drive) → AUDIT baseline (ui-audit, cached)\n  → PICK      owner clicks a live element → element→source picker resolves {selector, file:line, rect, computedStyle}\n  → SUGGEST   Claude + Codex register N candidates, each a LIVE injected-style overlay FIRST (by:claude|codex)\n  → OVERLAY   preview every candidate BEFORE any source edit (reload = gone → reversible by construction)\n  → SELECT    Artifact side-by-side gallery + one AskUserQuestion → owner picks (or \"keep as-is\")\n  → APPLY     ONE scoped micro-commit on a design\u002Flive-\u003Cid> branch — the picked file ONLY\n  → REAUDIT   incremental: changed screen only → delta from the ui-audit summary\n  → REVERT-GATE  shared revertDecision(): KEEP or REVERT → loop\n  → batch Figma-mirror every K accepts (hand off to design-studio mirror)\n```\n\n**Why overlay-first:** each candidate is an injected `style` tag (`data-candidate`) on the\nrunning app **before any source edit** — instant (\u003C1s vs edit+HMR) and reversible-by-reload, so\nthe revert-gate only ever arbitrates changes the owner already **accepted** (UIUX N.2 §91).\n\n**Why element→source, not vision:** the picker rebuilds the react-dev-inspector \u002F\ncode-inspector-plugin pattern thin on `evaluate_script` — a click resolves the React fiber's\n`_debugSource` (or `data-insp-path` attrs) to a real `file:line`. Deterministic; beats VLM\nSet-of-Mark guessing (the Cursor-2.0 \u002F stagewise pattern; UIUX N.2 §90).\n\n**Why external audit at all:** LLMs cannot reliably self-correct without external feedback\n(ICLR-2024) — the incremental re-audit is what makes model-suggested edits trustworthy.\n\n## Dual-agent mingle (UIUX N.2 §92)\n\n| Role | Agent | Contract |\n|---|---|---|\n| **driver \u002F applier** | **Claude** | holds the `mcp_agent_mail` file-lease on the picked source; the ONLY writer of the apply-back micro-commit |\n| **rival-suggester + independent re-auditor** | **Codex** | posts candidates (`by:codex`) and its own KEEP\u002FREVERT verdict; **never edits the leased file** |\n\nCandidate pools merge **attributed**; agreement across vendors is the signal (independent\nfailures); disagreement **escalates to the owner** — never auto-resolves to consensus. Emit the\nlease\u002Frole card with `node session.mjs mingle`.\n\n## Subcommands\n\n| cmd | does |\n|---|---|\n| `start --app \u003Cn> --flow \u003C\u002Fpath> --url \u003Curl> [--repo \u003Cpath>]` | open a session; **inherits scope from `loop-state.json`** if present; records the `design\u002Flive-\u003Cid>` branch |\n| `pick --selector \u003Csel> --file \u003Cpath:line>` | record the picked element→source target. `pick --emit-script` prints the browser picker JS for `evaluate_script` |\n| `suggest --cid \u003Cid> --selector \u003Csel> --css \"\u003Cdecls>\" --by \u003Cclaude\\|codex> [--dims \"contrast:+1\"]` | register a candidate + print its overlay markup |\n| `overlay --cid \u003Cid>` | print the injectable style tag + the `evaluate_script` inject snippet (preview) |\n| `gallery` | write `gallery.json` (before + N candidates + predicted deltas) for an Artifact + one AskUserQuestion |\n| `select --cid \u003Cid\\|keep>` | owner's choice (`keep` = no change; the cycle still closes clean) |\n| `apply [--commit --repo \u003Cpath>]` | scoped micro-commit. **Default = SHADOW plan** (prints the exact scoped `git add \u003Cfile>` — never `git add -A`); `--commit` executes a single-file commit |\n| `reaudit --before \u003Caudit.json> --after \u003Caudit.json>` | incremental delta from the ui-audit `summary` → `delta.json` |\n| `revert [--enforce --repo \u003Cpath>]` | the **shared** G6 revert-gate over the delta. **SHADOW by default**: logs the decision + emits the scoped rollback command, never mutates the repo |\n| `mingle` \u002F `status` | print the mingle card \u002F the session ledger |\n\n## Safety \u002F SHADOW (council C5)\n\n- The **revert-gate is SHADOW by default** — it decides + logs + emits the recommended scoped\n  rollback but **never mutates the repo**. Enforcement is opt-in (`revert --enforce`) and only\n  ever runs a scoped `git revert --no-edit \u003Csha>` on the candidate commit.\n- `apply` is scoped to the **picked file only** (execFile array args, no shell) — it can never\n  `git add -A`. Every apply-back is one reversible commit; the revert-gate arbitrates it.\n- Overlay previews touch only the DOM of the running app (a `data-candidate` style tag) — they\n  never write to disk and vanish on reload.\n\n## Consolidation ledger (what it reuses, not rebuilds)\n\n- **revert-gate:** dynamically imports `revertDecision()` from the sibling\n  `design-studio` `gates.mjs`; a byte-identical `inlineRevert`\n  fallback keeps it standalone. Same KEEP\u002FREVERT law as the batch loop.\n- **audit summary:** `scoreSummary()` reads ui-audit's `run_audit.mjs` `aggregate().summary`\n  (pageErrors, clickErrors, deadControls, axe, spacing, affordance, motion) — no new metric.\n- **state:** `session-state.json` carries `loopStateRef` and inherits `app\u002Fflow\u002FsourceOfTruth`\n  from `loop-state.json`; the session is the interactive specialization of the batch G5↔G6.\n\nEvidence: MASTER §N.2 · UIUX-CONSOLIDATION-DECISION-QUEUE §2.2, §89–95, N.2, K.5.\n",{"name":5,"description":7},"main","a298c929b6cbd662e1fce54302ce520d5ceea1a5",".agents\u002Fskills\u002Fdesign-studio-session","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain","https:\u002F\u002Fgithub.com\u002FPrekzursil","2026-11-02 14:30:57",{"source":8,"skillName":5,"commands":61,"prompt":71,"zipAvailable":72},[62,65,68],{"tool":63,"command":64},"npx","npx skills add Prekzursil\u002Fagent-skills-toolchain --skill design-studio-session",{"tool":66,"command":67},"bunx","bunx skills add Prekzursil\u002Fagent-skills-toolchain --skill design-studio-session",{"tool":69,"command":70},"pnpm","pnpm dlx skills add Prekzursil\u002Fagent-skills-toolchain --skill design-studio-session","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fdesign-studio-session\u002FSKILL.md",true,[74],{"path":75,"resourceType":76,"resourceTypeDesc":77,"sizeBytes":78,"sourceHtmlUrl":79},"session.mjs","SCRIPT","脚本",29898,"https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fdesign-studio-session\u002Fsession.mjs",[81,101,129,155,169,185],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":49},"01M6DF7D7478R55P46REYH4QAC","clarify-requirements","Resolve genuine pre-execution ambiguity by scanning repo context, generating 1-6 grounded options, and asking 1-3 focused questions via AskUserQuestion. NOT for mid-task use (injection risk); NOT when the goal is already unambiguous; use to disambiguate vague prompts before any file edits.","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Fworkspace-hooks\u002Fskills\u002Fclarify-requirements\u002FSKILL.md",[],[88,89,90,91,92,93,94,95,96,32,97,98,99,100,47],"clarify requirements","clarify","requirements","risk","options","task","prompts","goal","scanning","context","repo","injection","execution",{"skillNo":102,"name":103,"nameZh":6,"description":104,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":105,"categories":106,"keywords":110,"publishedAt":49},"01M6DF79CA4BHJS66J8EZDBPWJ","openmm-md","Run FREE, open-source, Windows-native GPU molecular dynamics via the openmm-md MCP (OpenMM + CUDA on the local NVIDIA GPU). Use for protein \u002F protein-ligand MD when you want a free stack or are on Windows without a Schrodinger license. Covers the full workflow (prepare, solvate, minimize, equilibrate, production, analyze, mmgbsa) AND an honest decision guide vs Schrodinger Desmond, including how to run Desmond legitimately on Linux or a cloud GPU with a real license. This is a deliberately LESSER free alternative and does NOT replace the schrodinger MCP tools. Do NOT use it to pick a free tool when a validated FEP+, WaterMap, IFD-MD, or Prime MM-GBSA result is actually required.","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Fmcp\u002Fopenmm-md-mcp\u002Fskill\u002Fopenmm-md\u002FSKILL.md",[107],{"categoryNo":108,"categoryName":109,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[111,112,113,114,115,116,117,118,119,120,121,122,123,124,32,125,126,127,38,128],"openmm md","how","decision","pick","linux","analyze","tool","stack","open","NVIDIA","gpu","license","workflow","windows","free","molecular dynamics","local","MCP",{"skillNo":130,"name":131,"nameZh":6,"description":132,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":133,"categories":134,"keywords":141,"publishedAt":49},"01M6DF76C1MG85VEWP8VZCBNMN","visual-review","Take screenshots of web pages and UI using Playwright for visual review and iteration","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fvisual-review\u002FSKILL.md",[135,138],{"categoryNo":136,"categoryName":137,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000003","演示文稿",{"categoryNo":139,"categoryName":140,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量",[33,142,143,144,145,146,147,148,149,150,112,151,152,153,154],"visual","visual review","pages","web","false","iteration","take","check","slides","ui","screenshot","playwright","screenshots",{"skillNo":156,"name":157,"nameZh":6,"description":158,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":159,"categories":160,"keywords":161,"publishedAt":49},"01M6DF73AQVCBZKEN0YXEX9FXP","status","Diagnostic status report — shows metaswarm installation state, project setup, and potential issues","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fstatus\u002FSKILL.md",[],[157,162,163,164,165,166,167,168],"setup","report","project","installation","project setup","issues","state",{"skillNo":170,"name":171,"nameZh":6,"description":172,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":173,"categories":174,"keywords":176,"publishedAt":49},"01M6DF6X6C2XB0P6GX76P7TTYV","start","Use when starting work on any task, when the user mentions metaswarm, or when the user wants to begin tracked development work","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fstart\u002FSKILL.md",[175],{"categoryNo":108,"categoryName":109,"taxonomyType":21,"taxonomyTypeDesc":22},[171,177,93,178,179,180,32,181,182,183,184],"start issue","issue","ready","work on issue","user","work","work on","development",{"skillNo":186,"name":162,"nameZh":6,"description":187,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":188,"categories":189,"keywords":190,"publishedAt":49},"01M6DF6QMJ9AJKFKHHKRT005PQ","Interactive project setup — detects your project, configures metaswarm, writes project-local files","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002Ftools\u002Feditor\u002Fmetaswarm\u002Fskills\u002Fsetup\u002FSKILL.md",[],[162,164,127,191,166,43],"files"]