[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M730EDS2C9PGT2FAMGGHAZE6":3,"skill-same:01M730EDS2C9PGT2FAMGGHAZE6":48},{"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":25,"commitSha":26,"skillDirectory":27,"forksCount":28,"repositoryHtmlUrl":29,"repositoryHomepageUrl":6,"ownerHtmlUrl":30,"ownerBlogUrl":31,"ownerDescription":32,"updatedAt":33,"install":34,"resources":47},"01M730EDS2C9PGT2FAMGGHAZE6","ecc-guide",null,"Guide users through ECC's current agents, skills, commands, hooks, rules, install profiles, and project onboarding by reading the live repository surface before answering.","SriramGandhiS\u002FSkills","SriramGandhiS","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F211849986?v=4","01M72WQCW12BYX71C6WN584TTA","Sriram S","01M72WQCWTJ2RD0ET1X31AF1RC",1,"MIT","https:\u002F\u002Fgithub.com\u002FSriramGandhiS\u002FSkills\u002Fblob\u002Fmaster\u002Fskills\u002Feverything-claude-code\u002Fskills\u002Fecc-guide\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: ecc-guide\ndescription: Guide users through ECC's current agents, skills, commands, hooks, rules, install profiles, and project onboarding by reading the live repository surface before answering.\norigin: community\n---\n\n# ECC Guide\n\nUse this skill when a user needs help understanding, navigating, installing, or choosing parts of Everything Claude Code.\n\n## When To Use\n\nUse this skill when the user:\n\n- asks what ECC includes\n- wants help finding a skill, command, agent, hook, rule, or install profile\n- is new to the repository and needs a guided path\n- asks \"how do I do X with ECC?\"\n- asks which ECC components fit a project\n- needs a lightweight explanation of how commands, skills, agents, hooks, and rules relate\n- is confused by install paths, duplicate installs, reset\u002Funinstall, or selective install options\n\n## Core Principle\n\nAnswer from current files, not memory. ECC changes quickly, so hard-coded catalog counts, feature lists, and install instructions go stale.\n\nWhen the ECC repository is available, inspect the relevant files before giving a concrete answer:\n\n```bash\nnode scripts\u002Fci\u002Fcatalog.js --json\nfind skills -maxdepth 2 -name SKILL.md | sort\nfind commands -maxdepth 1 -name '*.md' | sort\nfind agents -maxdepth 1 -name '*.md' | sort\nnode scripts\u002Finstall-plan.js --list-profiles\nnode scripts\u002Finstall-plan.js --list-components --json\n```\n\nUse the smallest set of reads needed for the user's question.\n\n## Repository Map\n\n- `README.md`: install paths, uninstall\u002Freset guidance, public positioning, FAQs\n- `AGENTS.md`: contributor guidance and project structure\n- `agent.yaml`: exported gitagent surface and command list\n- `commands\u002F`: maintained slash-command compatibility shims\n- `skills\u002F*\u002FSKILL.md`: reusable workflows and domain playbooks\n- `agents\u002F*.md`: delegated subagent role prompts\n- `rules\u002F`: language and harness rules\n- `hooks\u002FREADME.md`, `hooks\u002Fhooks.json`, `scripts\u002Fhooks\u002F`: hook behavior and safety gates\n- `manifests\u002Finstall-*.json`: selective install modules, components, profiles, and target support\n- `docs\u002F`: harness guides, architecture notes, translated docs, release docs\n\n## Response Style\n\nLead with the answer, then give the next action. Most users do not need a full catalog dump.\n\nGood first response shape:\n\n1. what to use\n2. why it fits\n3. exact file or command to inspect\n4. one next command or question\n\nAvoid:\n\n- listing every skill or command by default\n- repeating large README sections\n- recommending retired command shims when a skill-first path exists\n- claiming a component exists without checking the filesystem\n- replacing install guidance with manual copy commands when the managed installer supports the target\n\n## Common Tasks\n\n### New User Onboarding\n\nGive a short menu:\n\n- install or reset ECC\n- pick skills for a project\n- understand commands vs skills\n- inspect hooks and safety behavior\n- run a harness audit\n- find a specific workflow\n\nPoint to `README.md` for install\u002Freset and `\u002Fproject-init` for project-specific onboarding.\n\n### Feature Discovery\n\nFor \"what should I use for X?\":\n\n1. Search `skills\u002F`, `commands\u002F`, and `agents\u002F`.\n2. Prefer skills as the primary workflow surface.\n3. Use commands only when they are a maintained compatibility shim or a user explicitly wants slash-command behavior.\n4. Mention agents when delegation is useful.\n\nUseful searches:\n\n```bash\nrg -n \"\u003Cquery>\" skills commands agents docs\nfind skills -maxdepth 2 -name SKILL.md | sort\n```\n\n### Install Guidance\n\nUse managed install paths:\n\n```bash\nnode scripts\u002Finstall-plan.js --list-profiles\nnode scripts\u002Finstall-plan.js --profile minimal --target claude --json\nnode scripts\u002Finstall-apply.js --profile minimal --target claude --dry-run\n```\n\nFor specific skill installs:\n\n```bash\nnode scripts\u002Finstall-plan.js --skills \u003Cskill-id> --target claude --json\nnode scripts\u002Finstall-apply.js --skills \u003Cskill-id> --target claude --dry-run\n```\n\nWarn users not to stack plugin installs and full manual\u002Fprofile installs unless they intentionally want duplicate surfaces.\n\n### Project Onboarding\n\nUse `\u002Fproject-init` when the user wants ECC configured for a target repo. The expected sequence is:\n\n1. detect the stack from project files\n2. resolve a dry-run install plan\n3. inspect existing `CLAUDE.md` and settings files\n4. ask before applying changes\n5. keep generated guidance minimal and repo-specific\n\n### Troubleshooting\n\nAsk for the target harness and install path first, then inspect:\n\n- plugin install metadata\n- `.claude\u002F`, `.cursor\u002F`, `.codex\u002F`, `.gemini\u002F`, `.opencode\u002F`, `.codebuddy\u002F`, `.joycode\u002F`, or `.qwen\u002F`\n- `hooks\u002Fhooks.json`\n- install-state files\n- relevant command\u002Fskill files\n\nFor repo health, suggest:\n\n```bash\nnpm run harness:audit -- --format text\nnpm run observability:ready\nnpm test\n```\n\n## Output Templates\n\n### Short Recommendation\n\n```text\nUse \u003Cskill-or-command>. It fits because \u003Creason>.\n\nCanonical file: \u003Cpath>\nVerify with: \u003Ccommand>\nNext: \u003Cone concrete action>\n```\n\n### Search Results\n\n```text\nBest matches:\n- \u003Cpath>: \u003Cwhy it matters>\n- \u003Cpath>: \u003Cwhy it matters>\n\nRecommendation: \u003Cwhich one to use first and why>\n```\n\n### Install Plan Summary\n\n```text\nDetected: \u003Cstack evidence>\nTarget: \u003Charness>\nPlan: \u003Cprofile\u002Fmodules\u002Fskills>\nDry run: \u003Ccommand>\nWould change: \u003Cpaths>\nNeeds approval before apply: \u003Cyes\u002Fno>\n```\n\n## Related Surfaces\n\n- `\u002Fproject-init`: stack-aware onboarding plan for a target repo\n- `\u002Fharness-audit`: deterministic readiness scorecard\n- `\u002Fskill-health`: skill quality review\n- `\u002Fskill-create`: generate a new skill from local git history\n- `\u002Fsecurity-scan`: inspect Claude\u002FOpenCode configuration security\n","# ECC Guide\n\nUse this skill when a user needs help understanding, navigating, installing, or choosing parts of Everything Claude Code.\n\n## When To Use\n\nUse this skill when the user:\n\n- asks what ECC includes\n- wants help finding a skill, command, agent, hook, rule, or install profile\n- is new to the repository and needs a guided path\n- asks \"how do I do X with ECC?\"\n- asks which ECC components fit a project\n- needs a lightweight explanation of how commands, skills, agents, hooks, and rules relate\n- is confused by install paths, duplicate installs, reset\u002Funinstall, or selective install options\n\n## Core Principle\n\nAnswer from current files, not memory. ECC changes quickly, so hard-coded catalog counts, feature lists, and install instructions go stale.\n\nWhen the ECC repository is available, inspect the relevant files before giving a concrete answer:\n\n```bash\nnode scripts\u002Fci\u002Fcatalog.js --json\nfind skills -maxdepth 2 -name SKILL.md | sort\nfind commands -maxdepth 1 -name '*.md' | sort\nfind agents -maxdepth 1 -name '*.md' | sort\nnode scripts\u002Finstall-plan.js --list-profiles\nnode scripts\u002Finstall-plan.js --list-components --json\n```\n\nUse the smallest set of reads needed for the user's question.\n\n## Repository Map\n\n- `README.md`: install paths, uninstall\u002Freset guidance, public positioning, FAQs\n- `AGENTS.md`: contributor guidance and project structure\n- `agent.yaml`: exported gitagent surface and command list\n- `commands\u002F`: maintained slash-command compatibility shims\n- `skills\u002F*\u002FSKILL.md`: reusable workflows and domain playbooks\n- `agents\u002F*.md`: delegated subagent role prompts\n- `rules\u002F`: language and harness rules\n- `hooks\u002FREADME.md`, `hooks\u002Fhooks.json`, `scripts\u002Fhooks\u002F`: hook behavior and safety gates\n- `manifests\u002Finstall-*.json`: selective install modules, components, profiles, and target support\n- `docs\u002F`: harness guides, architecture notes, translated docs, release docs\n\n## Response Style\n\nLead with the answer, then give the next action. Most users do not need a full catalog dump.\n\nGood first response shape:\n\n1. what to use\n2. why it fits\n3. exact file or command to inspect\n4. one next command or question\n\nAvoid:\n\n- listing every skill or command by default\n- repeating large README sections\n- recommending retired command shims when a skill-first path exists\n- claiming a component exists without checking the filesystem\n- replacing install guidance with manual copy commands when the managed installer supports the target\n\n## Common Tasks\n\n### New User Onboarding\n\nGive a short menu:\n\n- install or reset ECC\n- pick skills for a project\n- understand commands vs skills\n- inspect hooks and safety behavior\n- run a harness audit\n- find a specific workflow\n\nPoint to `README.md` for install\u002Freset and `\u002Fproject-init` for project-specific onboarding.\n\n### Feature Discovery\n\nFor \"what should I use for X?\":\n\n1. Search `skills\u002F`, `commands\u002F`, and `agents\u002F`.\n2. Prefer skills as the primary workflow surface.\n3. Use commands only when they are a maintained compatibility shim or a user explicitly wants slash-command behavior.\n4. Mention agents when delegation is useful.\n\nUseful searches:\n\n```bash\nrg -n \"\u003Cquery>\" skills commands agents docs\nfind skills -maxdepth 2 -name SKILL.md | sort\n```\n\n### Install Guidance\n\nUse managed install paths:\n\n```bash\nnode scripts\u002Finstall-plan.js --list-profiles\nnode scripts\u002Finstall-plan.js --profile minimal --target claude --json\nnode scripts\u002Finstall-apply.js --profile minimal --target claude --dry-run\n```\n\nFor specific skill installs:\n\n```bash\nnode scripts\u002Finstall-plan.js --skills \u003Cskill-id> --target claude --json\nnode scripts\u002Finstall-apply.js --skills \u003Cskill-id> --target claude --dry-run\n```\n\nWarn users not to stack plugin installs and full manual\u002Fprofile installs unless they intentionally want duplicate surfaces.\n\n### Project Onboarding\n\nUse `\u002Fproject-init` when the user wants ECC configured for a target repo. The expected sequence is:\n\n1. detect the stack from project files\n2. resolve a dry-run install plan\n3. inspect existing `CLAUDE.md` and settings files\n4. ask before applying changes\n5. keep generated guidance minimal and repo-specific\n\n### Troubleshooting\n\nAsk for the target harness and install path first, then inspect:\n\n- plugin install metadata\n- `.claude\u002F`, `.cursor\u002F`, `.codex\u002F`, `.gemini\u002F`, `.opencode\u002F`, `.codebuddy\u002F`, `.joycode\u002F`, or `.qwen\u002F`\n- `hooks\u002Fhooks.json`\n- install-state files\n- relevant command\u002Fskill files\n\nFor repo health, suggest:\n\n```bash\nnpm run harness:audit -- --format text\nnpm run observability:ready\nnpm test\n```\n\n## Output Templates\n\n### Short Recommendation\n\n```text\nUse \u003Cskill-or-command>. It fits because \u003Creason>.\n\nCanonical file: \u003Cpath>\nVerify with: \u003Ccommand>\nNext: \u003Cone concrete action>\n```\n\n### Search Results\n\n```text\nBest matches:\n- \u003Cpath>: \u003Cwhy it matters>\n- \u003Cpath>: \u003Cwhy it matters>\n\nRecommendation: \u003Cwhich one to use first and why>\n```\n\n### Install Plan Summary\n\n```text\nDetected: \u003Cstack evidence>\nTarget: \u003Charness>\nPlan: \u003Cprofile\u002Fmodules\u002Fskills>\nDry run: \u003Ccommand>\nWould change: \u003Cpaths>\nNeeds approval before apply: \u003Cyes\u002Fno>\n```\n\n## Related Surfaces\n\n- `\u002Fproject-init`: stack-aware onboarding plan for a target repo\n- `\u002Fharness-audit`: deterministic readiness scorecard\n- `\u002Fskill-health`: skill quality review\n- `\u002Fskill-create`: generate a new skill from local git history\n- `\u002Fsecurity-scan`: inspect Claude\u002FOpenCode configuration security\n",{"name":5,"origin":24,"description":7},"community","master","d6ca01da0f24a3b0e26e4a8b7b66cbd25d429f5d","skills\u002Feverything-claude-code\u002Fskills\u002Fecc-guide",0,"https:\u002F\u002Fgithub.com\u002FSriramGandhiS\u002FSkills","https:\u002F\u002Fgithub.com\u002FSriramGandhiS","https:\u002F\u002Fsriram.website\u002F","Curious guy who keeps tinkering until something works","2026-05-20 16:21:34",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":46},[36,39,42],{"tool":37,"command":38},"npx","npx skills add SriramGandhiS\u002FSkills --skill ecc-guide",{"tool":40,"command":41},"bunx","bunx skills add SriramGandhiS\u002FSkills --skill ecc-guide",{"tool":43,"command":44},"pnpm","pnpm dlx skills add SriramGandhiS\u002FSkills --skill ecc-guide","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FSriramGandhiS\u002FSkills\u002Fblob\u002Fmaster\u002Fskills\u002Feverything-claude-code\u002Fskills\u002Fecc-guide\u002FSKILL.md",true,[],[49,56,61,67,74,81],{"skillNo":50,"name":51,"nameZh":6,"description":52,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":53,"categories":54,"keywords":55,"publishedAt":19},"01M732609EPJWV13PVTX3GT4TM","webgpu-threejs-tsl","Comprehensive guide for developing WebGPU-enabled Three.js applications using TSL (Three.js Shading Language). Covers WebGPU renderer setup, TSL syntax and node materials, compute shaders, post-processing effects, and WGSL integration. Use this skill when working with Three.js WebGPU, TSL shaders, node materials, or GPU compute in Three.js.","https:\u002F\u002Fgithub.com\u002FSriramGandhiS\u002FSkills\u002Fblob\u002Fmaster\u002Fwebgpu-threejs-tsl\u002Fskills\u002Fwebgpu-threejs-tsl\u002FSKILL.md",[],[],{"skillNo":57,"name":51,"nameZh":6,"description":52,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":58,"categories":59,"keywords":60,"publishedAt":19},"01M7325XM47AGWB6K6C4VXKE6B","https:\u002F\u002Fgithub.com\u002FSriramGandhiS\u002FSkills\u002Fblob\u002Fmaster\u002Fwebgpu-threejs-tsl\u002FSKILL.md",[],[],{"skillNo":62,"name":63,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":19},"01M7325WP6DES69JKC840VMFEP","verification-loop","https:\u002F\u002Fgithub.com\u002FSriramGandhiS\u002FSkills\u002Fblob\u002Fmaster\u002Fweb-assets\u002Fdocs\u002Fzh-TW\u002Fskills\u002Fverification-loop\u002FSKILL.md",[],[],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":19},"01M7325TFQF1DZTQ6J3WGQQ1VR","tdd-workflow","Use this skill when writing new features, fixing bugs, or refactoring code. Enforces test-driven development with 80%+ coverage including unit, integration, and E2E tests.","https:\u002F\u002Fgithub.com\u002FSriramGandhiS\u002FSkills\u002Fblob\u002Fmaster\u002Fweb-assets\u002Fdocs\u002Fzh-TW\u002Fskills\u002Ftdd-workflow\u002FSKILL.md",[],[],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":19},"01M7325RGV9AY9PK92D2V8KKPW","strategic-compact","Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.","https:\u002F\u002Fgithub.com\u002FSriramGandhiS\u002FSkills\u002Fblob\u002Fmaster\u002Fweb-assets\u002Fdocs\u002Fzh-TW\u002Fskills\u002Fstrategic-compact\u002FSKILL.md",[],[],{"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":19},"01M7325MZC28SE86E7NMCNEFS4","security-review","Use this skill when adding authentication, handling user input, working with secrets, creating API endpoints, or implementing payment\u002Fsensitive features. Provides comprehensive security checklist and patterns.","https:\u002F\u002Fgithub.com\u002FSriramGandhiS\u002FSkills\u002Fblob\u002Fmaster\u002Fweb-assets\u002Fdocs\u002Fzh-TW\u002Fskills\u002Fsecurity-review\u002FSKILL.md",[],[]]