[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6DBB3X1MA4TVQSE62X3MRWS":3,"skill-same:01M6DBB3X1MA4TVQSE62X3MRWS":65},{"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":39,"linkOnly":40,"markdownContent":41,"markdownBody":42,"frontMatter":43,"refName":45,"commitSha":46,"skillDirectory":47,"forksCount":14,"repositoryHtmlUrl":48,"repositoryHomepageUrl":6,"ownerHtmlUrl":49,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":50,"install":51,"resources":64},"01M6DBB3X1MA4TVQSE62X3MRWS","dmux-workflows",null,"Multi-agent orchestration using dmux (tmux pane manager for AI agents). Patterns for parallel agent workflows across Claude Code, Codex, OpenCode, and other harnesses. Use when running multiple agent sessions in parallel or coordinating multi-agent development workflows.","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\u002Fdmux-workflows\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38],"workflows","dmux workflows","multi-agent","agent workflows","development workflows","across","agent sessions","patterns","agent orchestration","opencode","use","parallel","ai agents","agent development","code","development","sessions","orchestration","codex","tmux","2026-11-10 10:12:30",false,"---\nname: dmux-workflows\ndescription: Multi-agent orchestration using dmux (tmux pane manager for AI agents). Patterns for parallel agent workflows across Claude Code, Codex, OpenCode, and other harnesses. Use when running multiple agent sessions in parallel or coordinating multi-agent development workflows.\norigin: ECC\n---\n\n# dmux Workflows\n\nOrchestrate parallel AI agent sessions using dmux, a tmux pane manager for agent harnesses.\n\n## When to Activate\n\n- Running multiple agent sessions in parallel\n- Coordinating work across Claude Code, Codex, and other harnesses\n- Complex tasks that benefit from divide-and-conquer parallelism\n- User says \"run in parallel\", \"split this work\", \"use dmux\", or \"multi-agent\"\n\n## What is dmux\n\ndmux is a tmux-based orchestration tool that manages AI agent panes:\n- Press `n` to create a new pane with a prompt\n- Press `m` to merge pane output back to the main session\n- Supports: Claude Code, Codex, OpenCode, Cline, Gemini, Qwen\n\n**Install:** `npm install -g dmux` or see [github.com\u002Fstandardagents\u002Fdmux](https:\u002F\u002Fgithub.com\u002Fstandardagents\u002Fdmux)\n\n## Quick Start\n\n```bash\n# Start dmux session\ndmux\n\n# Create agent panes (press 'n' in dmux, then type prompt)\n# Pane 1: \"Implement the auth middleware in src\u002Fauth\u002F\"\n# Pane 2: \"Write tests for the user service\"\n# Pane 3: \"Update API documentation\"\n\n# Each pane runs its own agent session\n# Press 'm' to merge results back\n```\n\n## Workflow Patterns\n\n### Pattern 1: Research + Implement\n\nSplit research and implementation into parallel tracks:\n\n```\nPane 1 (Research): \"Research best practices for rate limiting in Node.js.\n  Check current libraries, compare approaches, and write findings to\n  \u002Ftmp\u002Frate-limit-research.md\"\n\nPane 2 (Implement): \"Implement rate limiting middleware for our Express API.\n  Start with a basic token bucket, we'll refine after research completes.\"\n\n# After Pane 1 completes, merge findings into Pane 2's context\n```\n\n### Pattern 2: Multi-File Feature\n\nParallelize work across independent files:\n\n```\nPane 1: \"Create the database schema and migrations for the billing feature\"\nPane 2: \"Build the billing API endpoints in src\u002Fapi\u002Fbilling\u002F\"\nPane 3: \"Create the billing dashboard UI components\"\n\n# Merge all, then do integration in main pane\n```\n\n### Pattern 3: Test + Fix Loop\n\nRun tests in one pane, fix in another:\n\n```\nPane 1 (Watcher): \"Run the test suite in watch mode. When tests fail,\n  summarize the failures.\"\n\nPane 2 (Fixer): \"Fix failing tests based on the error output from pane 1\"\n```\n\n### Pattern 4: Cross-Harness\n\nUse different AI tools for different tasks:\n\n```\nPane 1 (Claude Code): \"Review the security of the auth module\"\nPane 2 (Codex): \"Refactor the utility functions for performance\"\nPane 3 (Claude Code): \"Write E2E tests for the checkout flow\"\n```\n\n### Pattern 5: Code Review Pipeline\n\nParallel review perspectives:\n\n```\nPane 1: \"Review src\u002Fapi\u002F for security vulnerabilities\"\nPane 2: \"Review src\u002Fapi\u002F for performance issues\"\nPane 3: \"Review src\u002Fapi\u002F for test coverage gaps\"\n\n# Merge all reviews into a single report\n```\n\n## Best Practices\n\n1. **Independent tasks only.** Don't parallelize tasks that depend on each other's output.\n2. **Clear boundaries.** Each pane should work on distinct files or concerns.\n3. **Merge strategically.** Review pane output before merging to avoid conflicts.\n4. **Use git worktrees.** For file-conflict-prone work, use separate worktrees per pane.\n5. **Resource awareness.** Each pane uses API tokens — keep total panes under 5-6.\n\n## Git Worktree Integration\n\nFor tasks that touch overlapping files:\n\n```bash\n# Create worktrees for isolation\ngit worktree add -b feat\u002Fauth ..\u002Ffeature-auth HEAD\ngit worktree add -b feat\u002Fbilling ..\u002Ffeature-billing HEAD\n\n# Run agents in separate worktrees\n# Pane 1: cd ..\u002Ffeature-auth && claude\n# Pane 2: cd ..\u002Ffeature-billing && claude\n\n# Merge branches when done\ngit merge feat\u002Fauth\ngit merge feat\u002Fbilling\n```\n\n## Complementary Tools\n\n| Tool | What It Does | When to Use |\n|------|-------------|-------------|\n| **dmux** | tmux pane management for agents | Parallel agent sessions |\n| **Superset** | Terminal IDE for 10+ parallel agents | Large-scale orchestration |\n| **Claude Code Task tool** | In-process subagent spawning | Programmatic parallelism within a session |\n| **Codex multi-agent** | Built-in agent roles | Codex-specific parallel work |\n\n## ECC Helper\n\nECC now includes a helper for external tmux-pane orchestration with separate git worktrees:\n\n```bash\nnode scripts\u002Forchestrate-worktrees.js plan.json --execute\n```\n\nExample `plan.json`:\n\n```json\n{\n  \"sessionName\": \"skill-audit\",\n  \"baseRef\": \"HEAD\",\n  \"launcherCommand\": \"codex exec --cwd {worktree_path} --task-file {task_file}\",\n  \"workers\": [\n    { \"name\": \"docs-a\", \"task\": \"Fix skills 1-4 and write handoff notes.\" },\n    { \"name\": \"docs-b\", \"task\": \"Fix skills 5-8 and write handoff notes.\" }\n  ]\n}\n```\n\nThe helper:\n- Creates one branch-backed git worktree per worker\n- Optionally overlays selected `seedPaths` from the main checkout into each worker worktree\n- Writes per-worker `task.md`, `handoff.md`, and `status.md` files under `.orchestration\u002F\u003Csession>\u002F`\n- Starts a tmux session with one pane per worker\n- Launches each worker command in its own pane\n- Leaves the main pane free for the orchestrator\n\nUse `seedPaths` when workers need access to dirty or untracked local files that are not yet part of `HEAD`, such as local orchestration scripts, draft plans, or docs:\n\n```json\n{\n  \"sessionName\": \"workflow-e2e\",\n  \"seedPaths\": [\n    \"scripts\u002Forchestrate-worktrees.js\",\n    \"scripts\u002Flib\u002Ftmux-worktree-orchestrator.js\",\n    \".claude\u002Fplan\u002Fworkflow-e2e-test.json\"\n  ],\n  \"launcherCommand\": \"bash {repo_root}\u002Fscripts\u002Forchestrate-codex-worker.sh {task_file} {handoff_file} {status_file}\",\n  \"workers\": [\n    { \"name\": \"seed-check\", \"task\": \"Verify seeded files are present before starting work.\" }\n  ]\n}\n```\n\n## Troubleshooting\n\n- **Pane not responding:** Switch to the pane directly or inspect it with `tmux capture-pane -pt \u003Csession>:0.\u003Cpane-index>`.\n- **Merge conflicts:** Use git worktrees to isolate file changes per pane.\n- **High token usage:** Reduce number of parallel panes. Each pane is a full agent session.\n- **tmux not found:** Install with `brew install tmux` (macOS) or `apt install tmux` (Linux).\n","# dmux Workflows\n\nOrchestrate parallel AI agent sessions using dmux, a tmux pane manager for agent harnesses.\n\n## When to Activate\n\n- Running multiple agent sessions in parallel\n- Coordinating work across Claude Code, Codex, and other harnesses\n- Complex tasks that benefit from divide-and-conquer parallelism\n- User says \"run in parallel\", \"split this work\", \"use dmux\", or \"multi-agent\"\n\n## What is dmux\n\ndmux is a tmux-based orchestration tool that manages AI agent panes:\n- Press `n` to create a new pane with a prompt\n- Press `m` to merge pane output back to the main session\n- Supports: Claude Code, Codex, OpenCode, Cline, Gemini, Qwen\n\n**Install:** `npm install -g dmux` or see [github.com\u002Fstandardagents\u002Fdmux](https:\u002F\u002Fgithub.com\u002Fstandardagents\u002Fdmux)\n\n## Quick Start\n\n```bash\n# Start dmux session\ndmux\n\n# Create agent panes (press 'n' in dmux, then type prompt)\n# Pane 1: \"Implement the auth middleware in src\u002Fauth\u002F\"\n# Pane 2: \"Write tests for the user service\"\n# Pane 3: \"Update API documentation\"\n\n# Each pane runs its own agent session\n# Press 'm' to merge results back\n```\n\n## Workflow Patterns\n\n### Pattern 1: Research + Implement\n\nSplit research and implementation into parallel tracks:\n\n```\nPane 1 (Research): \"Research best practices for rate limiting in Node.js.\n  Check current libraries, compare approaches, and write findings to\n  \u002Ftmp\u002Frate-limit-research.md\"\n\nPane 2 (Implement): \"Implement rate limiting middleware for our Express API.\n  Start with a basic token bucket, we'll refine after research completes.\"\n\n# After Pane 1 completes, merge findings into Pane 2's context\n```\n\n### Pattern 2: Multi-File Feature\n\nParallelize work across independent files:\n\n```\nPane 1: \"Create the database schema and migrations for the billing feature\"\nPane 2: \"Build the billing API endpoints in src\u002Fapi\u002Fbilling\u002F\"\nPane 3: \"Create the billing dashboard UI components\"\n\n# Merge all, then do integration in main pane\n```\n\n### Pattern 3: Test + Fix Loop\n\nRun tests in one pane, fix in another:\n\n```\nPane 1 (Watcher): \"Run the test suite in watch mode. When tests fail,\n  summarize the failures.\"\n\nPane 2 (Fixer): \"Fix failing tests based on the error output from pane 1\"\n```\n\n### Pattern 4: Cross-Harness\n\nUse different AI tools for different tasks:\n\n```\nPane 1 (Claude Code): \"Review the security of the auth module\"\nPane 2 (Codex): \"Refactor the utility functions for performance\"\nPane 3 (Claude Code): \"Write E2E tests for the checkout flow\"\n```\n\n### Pattern 5: Code Review Pipeline\n\nParallel review perspectives:\n\n```\nPane 1: \"Review src\u002Fapi\u002F for security vulnerabilities\"\nPane 2: \"Review src\u002Fapi\u002F for performance issues\"\nPane 3: \"Review src\u002Fapi\u002F for test coverage gaps\"\n\n# Merge all reviews into a single report\n```\n\n## Best Practices\n\n1. **Independent tasks only.** Don't parallelize tasks that depend on each other's output.\n2. **Clear boundaries.** Each pane should work on distinct files or concerns.\n3. **Merge strategically.** Review pane output before merging to avoid conflicts.\n4. **Use git worktrees.** For file-conflict-prone work, use separate worktrees per pane.\n5. **Resource awareness.** Each pane uses API tokens — keep total panes under 5-6.\n\n## Git Worktree Integration\n\nFor tasks that touch overlapping files:\n\n```bash\n# Create worktrees for isolation\ngit worktree add -b feat\u002Fauth ..\u002Ffeature-auth HEAD\ngit worktree add -b feat\u002Fbilling ..\u002Ffeature-billing HEAD\n\n# Run agents in separate worktrees\n# Pane 1: cd ..\u002Ffeature-auth && claude\n# Pane 2: cd ..\u002Ffeature-billing && claude\n\n# Merge branches when done\ngit merge feat\u002Fauth\ngit merge feat\u002Fbilling\n```\n\n## Complementary Tools\n\n| Tool | What It Does | When to Use |\n|------|-------------|-------------|\n| **dmux** | tmux pane management for agents | Parallel agent sessions |\n| **Superset** | Terminal IDE for 10+ parallel agents | Large-scale orchestration |\n| **Claude Code Task tool** | In-process subagent spawning | Programmatic parallelism within a session |\n| **Codex multi-agent** | Built-in agent roles | Codex-specific parallel work |\n\n## ECC Helper\n\nECC now includes a helper for external tmux-pane orchestration with separate git worktrees:\n\n```bash\nnode scripts\u002Forchestrate-worktrees.js plan.json --execute\n```\n\nExample `plan.json`:\n\n```json\n{\n  \"sessionName\": \"skill-audit\",\n  \"baseRef\": \"HEAD\",\n  \"launcherCommand\": \"codex exec --cwd {worktree_path} --task-file {task_file}\",\n  \"workers\": [\n    { \"name\": \"docs-a\", \"task\": \"Fix skills 1-4 and write handoff notes.\" },\n    { \"name\": \"docs-b\", \"task\": \"Fix skills 5-8 and write handoff notes.\" }\n  ]\n}\n```\n\nThe helper:\n- Creates one branch-backed git worktree per worker\n- Optionally overlays selected `seedPaths` from the main checkout into each worker worktree\n- Writes per-worker `task.md`, `handoff.md`, and `status.md` files under `.orchestration\u002F\u003Csession>\u002F`\n- Starts a tmux session with one pane per worker\n- Launches each worker command in its own pane\n- Leaves the main pane free for the orchestrator\n\nUse `seedPaths` when workers need access to dirty or untracked local files that are not yet part of `HEAD`, such as local orchestration scripts, draft plans, or docs:\n\n```json\n{\n  \"sessionName\": \"workflow-e2e\",\n  \"seedPaths\": [\n    \"scripts\u002Forchestrate-worktrees.js\",\n    \"scripts\u002Flib\u002Ftmux-worktree-orchestrator.js\",\n    \".claude\u002Fplan\u002Fworkflow-e2e-test.json\"\n  ],\n  \"launcherCommand\": \"bash {repo_root}\u002Fscripts\u002Forchestrate-codex-worker.sh {task_file} {handoff_file} {status_file}\",\n  \"workers\": [\n    { \"name\": \"seed-check\", \"task\": \"Verify seeded files are present before starting work.\" }\n  ]\n}\n```\n\n## Troubleshooting\n\n- **Pane not responding:** Switch to the pane directly or inspect it with `tmux capture-pane -pt \u003Csession>:0.\u003Cpane-index>`.\n- **Merge conflicts:** Use git worktrees to isolate file changes per pane.\n- **High token usage:** Reduce number of parallel panes. Each pane is a full agent session.\n- **tmux not found:** Install with `brew install tmux` (macOS) or `apt install tmux` (Linux).\n",{"name":5,"origin":44,"description":7},"ECC","main","a298c929b6cbd662e1fce54302ce520d5ceea1a5",".agents\u002Fskills\u002Fdmux-workflows","https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain","https:\u002F\u002Fgithub.com\u002FPrekzursil","2026-11-02 14:30:57",{"source":8,"skillName":5,"commands":52,"prompt":62,"zipAvailable":63},[53,56,59],{"tool":54,"command":55},"npx","npx skills add Prekzursil\u002Fagent-skills-toolchain --skill dmux-workflows",{"tool":57,"command":58},"bunx","bunx skills add Prekzursil\u002Fagent-skills-toolchain --skill dmux-workflows",{"tool":60,"command":61},"pnpm","pnpm dlx skills add Prekzursil\u002Fagent-skills-toolchain --skill dmux-workflows","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FPrekzursil\u002Fagent-skills-toolchain\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fdmux-workflows\u002FSKILL.md",true,[],[66,87,118,145,159,174],{"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":39},"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",[],[73,74,75,76,77,78,79,80,81,29,82,83,84,85,86],"clarify requirements","clarify","requirements","risk","options","task","prompts","goal","scanning","context","repo","injection","execution","file",{"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":98,"publishedAt":39},"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",[93],{"categoryNo":94,"categoryName":95,"taxonomyType":96,"taxonomyTypeDesc":97},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[99,100,101,102,103,104,105,106,107,108,109,110,111,112,29,113,114,115,116,117],"openmm md","how","decision","pick","linux","analyze","tool","stack","open","NVIDIA","gpu","license","workflow","windows","free","molecular dynamics","local","do","MCP",{"skillNo":119,"name":120,"nameZh":6,"description":121,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":122,"categories":123,"keywords":130,"publishedAt":39},"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",[124,127],{"categoryNo":125,"categoryName":126,"taxonomyType":96,"taxonomyTypeDesc":97},"01JBSEEDCAT000000000000003","演示文稿",{"categoryNo":128,"categoryName":129,"taxonomyType":96,"taxonomyTypeDesc":97},"01JBSEEDCAT000000000000008","测试与质量",[131,132,133,134,135,136,137,138,139,140,100,141,142,143,144],"review","visual","visual review","pages","web","false","iteration","take","check","slides","ui","screenshot","playwright","screenshots",{"skillNo":146,"name":147,"nameZh":6,"description":148,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":149,"categories":150,"keywords":151,"publishedAt":39},"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",[],[147,152,153,154,155,156,157,158],"setup","report","project","installation","project setup","issues","state",{"skillNo":160,"name":161,"nameZh":6,"description":162,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":163,"categories":164,"keywords":166,"publishedAt":39},"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",[165],{"categoryNo":94,"categoryName":95,"taxonomyType":96,"taxonomyTypeDesc":97},[161,167,78,168,169,170,29,171,172,173,34],"start issue","issue","ready","work on issue","user","work","work on",{"skillNo":175,"name":152,"nameZh":6,"description":176,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":177,"categories":178,"keywords":179,"publishedAt":39},"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",[],[152,154,115,180,156,181],"files","interactive"]