[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7CS8M3GRQ6XP0KFDTV04H69":3,"skill-same:01M7CS8M3GRQ6XP0KFDTV04H69":54},{"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":26,"commitSha":27,"skillDirectory":28,"forksCount":14,"repositoryHtmlUrl":29,"repositoryHomepageUrl":6,"ownerHtmlUrl":30,"ownerBlogUrl":31,"ownerDescription":32,"updatedAt":33,"install":34,"resources":47},"01M7CS8M3GRQ6XP0KFDTV04H69","plan-canvas",null,"Open plans and HTML artifacts in a local browser canvas where the human annotates elements, chats, and approves or requests changes without leaving the page. Use when presenting a plan for review, or when feedback like \"move this, change that\" is easier pointed at than typed.","Henrique1601\u002FSkiilsToIAs","Henrique1601","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F92006691?v=4","01M7CRXVT0GVXVK80JT1GR687S","Henrique Bezerra Dos Santos","01M7CRXVTN5Y8TMWJ1MDSKCQ1T",0,"MIT","https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs\u002Fblob\u002Fmain\u002Fai-agents\u002Fplan-canvas\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: plan-canvas\ndescription: Open plans and HTML artifacts in a local browser canvas where the human annotates elements, chats, and approves or requests changes without leaving the page. Use when presenting a plan for review, or when feedback like \"move this, change that\" is easier pointed at than typed.\nmetadata:\n  origin: ECC\n---\n\n# Plan Canvas\n\nReview loop for plans and visual artifacts: you write the artifact, the human\nreviews it in the browser — annotating the exact element they mean, chatting,\nand delivering an **Approve plan \u002F Request changes** verdict — while you block\non a single CLI call that returns their feedback as JSON.\n\nInspired by [lavish-axi](https:\u002F\u002Fgithub.com\u002Fkunchenguid\u002Flavish-axi); rebuilt\nECC-native around the `\u002Fplan` confirmation gate, with zero dependencies.\n\n## When to Use\n\n- You just wrote a plan artifact (`.claude\u002Fplans\u002F*.plan.md` from `\u002Fplan`) and\n  need the CONFIRM\u002Fapprove decision — the canvas verdict replaces a typed\n  \"yes\u002Fproceed\".\n- The user should *point at* what to change: reviewing designs, comparisons,\n  reports, or any local `.md` \u002F `.html` artifact.\n- The user asks for `\u002Fplan-canvas`, a visual review, or \"open it in the browser\".\n\nDo NOT use for: code review of diffs (`\u002Fcode-review`), running web apps, or\nremote URLs. The canvas serves local artifact files only.\n\n## How It Works\n\nInvoke the CLI as `ecc-plan-canvas` — the bin shipped by the `ecc-universal`\npackage (on PATH after a global\u002Fplugin install; `node \"$CLAUDE_PLUGIN_ROOT\u002Fscripts\u002Fplan-canvas.js\"`\nalso works for plugin installs). Run it from the project you are reviewing in;\nit works from any working directory. It manages a detached loopback server\n(`127.0.0.1:4517`) shared by all sessions, keyed by artifact path — no session\nids to track.\n\nThe workflow is a plain CLI-plus-JSON loop, so it is model- and harness-agnostic:\nany agent that can run a shell command and read stdout drives it the same way\n(Claude Code, Codex, Cursor, Gemini, OpenCode, Copilot). Trigger it however your\nharness surfaces skills — e.g. `\u002Fplan-canvas` in Claude Code, `$plan-canvas` in\nCodex — or just run the `ecc-plan-canvas` commands directly.\n\n```bash\n# 1. Open the artifact in the user's browser (returns immediately)\necc-plan-canvas open .claude\u002Fplans\u002Ffeature.plan.md\n\n# 2. Block until the human responds. Leave running; re-run if interrupted —\n#    queued feedback is never lost. Run in the background if your harness\n#    time-limits foreground commands.\necc-plan-canvas await .claude\u002Fplans\u002Ffeature.plan.md\n```\n\n`await` prints JSON when the human acts:\n\n```json\n{\n  \"status\": \"feedback\",\n  \"items\": [\n    { \"kind\": \"annotation\", \"text\": \"Split this into two phases\",\n      \"anchor\": { \"selector\": \"h2:nth-of-type(3)\", \"tag\": \"h2\", \"snippet\": \"Phase 2: Migration\" } },\n    { \"kind\": \"verdict\", \"verdict\": \"request-changes\" }\n  ]\n}\n```\n\n- `kind: \"chat\"` — freeform message; answer in the canvas, not the terminal.\n- `kind: \"annotation\"` — feedback anchored to an element (`anchor.selector`,\n  `anchor.snippet` show what they pointed at; `anchor.textRange.text` when\n  they highlighted a passage).\n- `kind: \"verdict\"` — `approve` means the plan is CONFIRMED: stop polling,\n  end the session, and start implementing. `request-changes` means revise the\n  artifact (the canvas live-reloads it) and keep the loop going.\n\n**3. Respond in the canvas**, then keep listening — one command does both:\n\n```bash\necc-plan-canvas await \u003Cfile> --reply \"Split Phase 2 as requested — take a look.\"\n```\n\n**4. End** when review concludes: `ecc-plan-canvas end \u003Cfile>`.\n\n## Diagrams (Mermaid)\n\nWhen part of the plan is a flow, architecture, sequence, state machine, ER\nmodel, or dependency graph, author it as a fenced ` ```mermaid ` block instead\nof ASCII art or a wall of prose — the canvas renders it as a themed diagram the\nhuman can point at. Reach for it when a picture reads faster than a paragraph;\nskip it for simple lists or tables.\n\n````markdown\n```mermaid\nflowchart LR\n  A[Market resolves] --> B{Watchers?}\n  B -->|yes| C[Enqueue jobs] --> D[Fan-out worker]\n```\n````\n\nDiagrams render in the ECC dark theme with the accent palette. Mermaid loads in\nthe browser from a pinned CDN; if that is unavailable (offline), the block\ndegrades to showing its source, so the review is never blocked. Point a local\nmirror at `ECC_PLAN_CANVAS_MERMAID_URL` for air-gapped use.\n\n## Rules\n\n- Markdown artifacts render in ECC's plan template (including Mermaid blocks);\n  `.html` artifacts render as-is with the annotation layer injected. For HTML\n  authoring guidance use the `frontend-design-direction` and `artifact-design`\n  skills.\n- Edit the artifact file to revise — the canvas live-reloads on save. Never\n  re-run `open` to refresh.\n- `{\"status\": \"ended\", \"endedBy\": \"user\"}` (or `sessionEnded: true` on a\n  feedback batch) means the user closed the review: stop polling, deliver\n  remaining updates in chat, and do not reopen. A plain `open` on that\n  session is refused; pass `--reopen` only when the user asks to resume.\n- Sibling assets (images, CSS) must sit next to the artifact and be\n  referenced by relative path.\n- The server is loopback-only and exits after 30 idle minutes\n  (`ECC_PLAN_CANVAS_IDLE_MS`); `stop` shuts it down explicitly. State lives\n  in `~\u002F.claude\u002Fplan-canvas\u002F` (`ECC_PLAN_CANVAS_STATE_DIR`).\n\n## Examples\n\n**Plan approval flow** — `\u002Fplan` writes\n`.claude\u002Fplans\u002Fnotifications.plan.md` and must WAIT for confirmation:\n\n```bash\necc-plan-canvas open .claude\u002Fplans\u002Fnotifications.plan.md\necc-plan-canvas await .claude\u002Fplans\u002Fnotifications.plan.md\n# → {\"status\":\"feedback\",\"items\":[{\"kind\":\"verdict\",\"verdict\":\"approve\"}]}\necc-plan-canvas end .claude\u002Fplans\u002Fnotifications.plan.md\n# plan is confirmed — begin implementation\n```\n\n**Revision loop** — feedback arrives, you edit the file, reply, keep listening:\n\n```bash\n# await returned annotations → edit the .plan.md (canvas live-reloads)\necc-plan-canvas await \u003Cfile> --reply \"Reworked the risk table.\"\n# → blocks again until the next response\n```\n\n## Anti-Patterns\n\n- Polling with `--timeout-ms` in a loop — it exists for tests. Leave the\n  plain `await` running instead.\n- Reopening after a user-initiated end \"just to show\" something.\n- Pasting the whole plan into chat *and* opening a canvas — pick the canvas\n  and keep the terminal summary to one line.\n- Parsing the canvas chat from state files — everything you need arrives via\n  `await`.\n","# Plan Canvas\n\nReview loop for plans and visual artifacts: you write the artifact, the human\nreviews it in the browser — annotating the exact element they mean, chatting,\nand delivering an **Approve plan \u002F Request changes** verdict — while you block\non a single CLI call that returns their feedback as JSON.\n\nInspired by [lavish-axi](https:\u002F\u002Fgithub.com\u002Fkunchenguid\u002Flavish-axi); rebuilt\nECC-native around the `\u002Fplan` confirmation gate, with zero dependencies.\n\n## When to Use\n\n- You just wrote a plan artifact (`.claude\u002Fplans\u002F*.plan.md` from `\u002Fplan`) and\n  need the CONFIRM\u002Fapprove decision — the canvas verdict replaces a typed\n  \"yes\u002Fproceed\".\n- The user should *point at* what to change: reviewing designs, comparisons,\n  reports, or any local `.md` \u002F `.html` artifact.\n- The user asks for `\u002Fplan-canvas`, a visual review, or \"open it in the browser\".\n\nDo NOT use for: code review of diffs (`\u002Fcode-review`), running web apps, or\nremote URLs. The canvas serves local artifact files only.\n\n## How It Works\n\nInvoke the CLI as `ecc-plan-canvas` — the bin shipped by the `ecc-universal`\npackage (on PATH after a global\u002Fplugin install; `node \"$CLAUDE_PLUGIN_ROOT\u002Fscripts\u002Fplan-canvas.js\"`\nalso works for plugin installs). Run it from the project you are reviewing in;\nit works from any working directory. It manages a detached loopback server\n(`127.0.0.1:4517`) shared by all sessions, keyed by artifact path — no session\nids to track.\n\nThe workflow is a plain CLI-plus-JSON loop, so it is model- and harness-agnostic:\nany agent that can run a shell command and read stdout drives it the same way\n(Claude Code, Codex, Cursor, Gemini, OpenCode, Copilot). Trigger it however your\nharness surfaces skills — e.g. `\u002Fplan-canvas` in Claude Code, `$plan-canvas` in\nCodex — or just run the `ecc-plan-canvas` commands directly.\n\n```bash\n# 1. Open the artifact in the user's browser (returns immediately)\necc-plan-canvas open .claude\u002Fplans\u002Ffeature.plan.md\n\n# 2. Block until the human responds. Leave running; re-run if interrupted —\n#    queued feedback is never lost. Run in the background if your harness\n#    time-limits foreground commands.\necc-plan-canvas await .claude\u002Fplans\u002Ffeature.plan.md\n```\n\n`await` prints JSON when the human acts:\n\n```json\n{\n  \"status\": \"feedback\",\n  \"items\": [\n    { \"kind\": \"annotation\", \"text\": \"Split this into two phases\",\n      \"anchor\": { \"selector\": \"h2:nth-of-type(3)\", \"tag\": \"h2\", \"snippet\": \"Phase 2: Migration\" } },\n    { \"kind\": \"verdict\", \"verdict\": \"request-changes\" }\n  ]\n}\n```\n\n- `kind: \"chat\"` — freeform message; answer in the canvas, not the terminal.\n- `kind: \"annotation\"` — feedback anchored to an element (`anchor.selector`,\n  `anchor.snippet` show what they pointed at; `anchor.textRange.text` when\n  they highlighted a passage).\n- `kind: \"verdict\"` — `approve` means the plan is CONFIRMED: stop polling,\n  end the session, and start implementing. `request-changes` means revise the\n  artifact (the canvas live-reloads it) and keep the loop going.\n\n**3. Respond in the canvas**, then keep listening — one command does both:\n\n```bash\necc-plan-canvas await \u003Cfile> --reply \"Split Phase 2 as requested — take a look.\"\n```\n\n**4. End** when review concludes: `ecc-plan-canvas end \u003Cfile>`.\n\n## Diagrams (Mermaid)\n\nWhen part of the plan is a flow, architecture, sequence, state machine, ER\nmodel, or dependency graph, author it as a fenced ` ```mermaid ` block instead\nof ASCII art or a wall of prose — the canvas renders it as a themed diagram the\nhuman can point at. Reach for it when a picture reads faster than a paragraph;\nskip it for simple lists or tables.\n\n````markdown\n```mermaid\nflowchart LR\n  A[Market resolves] --> B{Watchers?}\n  B -->|yes| C[Enqueue jobs] --> D[Fan-out worker]\n```\n````\n\nDiagrams render in the ECC dark theme with the accent palette. Mermaid loads in\nthe browser from a pinned CDN; if that is unavailable (offline), the block\ndegrades to showing its source, so the review is never blocked. Point a local\nmirror at `ECC_PLAN_CANVAS_MERMAID_URL` for air-gapped use.\n\n## Rules\n\n- Markdown artifacts render in ECC's plan template (including Mermaid blocks);\n  `.html` artifacts render as-is with the annotation layer injected. For HTML\n  authoring guidance use the `frontend-design-direction` and `artifact-design`\n  skills.\n- Edit the artifact file to revise — the canvas live-reloads on save. Never\n  re-run `open` to refresh.\n- `{\"status\": \"ended\", \"endedBy\": \"user\"}` (or `sessionEnded: true` on a\n  feedback batch) means the user closed the review: stop polling, deliver\n  remaining updates in chat, and do not reopen. A plain `open` on that\n  session is refused; pass `--reopen` only when the user asks to resume.\n- Sibling assets (images, CSS) must sit next to the artifact and be\n  referenced by relative path.\n- The server is loopback-only and exits after 30 idle minutes\n  (`ECC_PLAN_CANVAS_IDLE_MS`); `stop` shuts it down explicitly. State lives\n  in `~\u002F.claude\u002Fplan-canvas\u002F` (`ECC_PLAN_CANVAS_STATE_DIR`).\n\n## Examples\n\n**Plan approval flow** — `\u002Fplan` writes\n`.claude\u002Fplans\u002Fnotifications.plan.md` and must WAIT for confirmation:\n\n```bash\necc-plan-canvas open .claude\u002Fplans\u002Fnotifications.plan.md\necc-plan-canvas await .claude\u002Fplans\u002Fnotifications.plan.md\n# → {\"status\":\"feedback\",\"items\":[{\"kind\":\"verdict\",\"verdict\":\"approve\"}]}\necc-plan-canvas end .claude\u002Fplans\u002Fnotifications.plan.md\n# plan is confirmed — begin implementation\n```\n\n**Revision loop** — feedback arrives, you edit the file, reply, keep listening:\n\n```bash\n# await returned annotations → edit the .plan.md (canvas live-reloads)\necc-plan-canvas await \u003Cfile> --reply \"Reworked the risk table.\"\n# → blocks again until the next response\n```\n\n## Anti-Patterns\n\n- Polling with `--timeout-ms` in a loop — it exists for tests. Leave the\n  plain `await` running instead.\n- Reopening after a user-initiated end \"just to show\" something.\n- Pasting the whole plan into chat *and* opening a canvas — pick the canvas\n  and keep the terminal summary to one line.\n- Parsing the canvas chat from state files — everything you need arrives via\n  `await`.\n",{"name":5,"metadata":24,"description":7},{"origin":25},"ECC","main","a73152352c0612252131e5cf84e91312a6cf17dc","ai-agents\u002Fplan-canvas","https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs","https:\u002F\u002Fgithub.com\u002FHenrique1601","https:\u002F\u002Fbezerraportifolio.netlify.app\u002F","Full Stack Developer | React, Next.js, TypeScript, Node.js & IA | Construindo produtos digitais e soluções SaaS","2026-11-15 02:56:04",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":46},[36,39,42],{"tool":37,"command":38},"npx","npx skills add Henrique1601\u002FSkiilsToIAs --skill plan-canvas",{"tool":40,"command":41},"bunx","bunx skills add Henrique1601\u002FSkiilsToIAs --skill plan-canvas",{"tool":43,"command":44},"pnpm","pnpm dlx skills add Henrique1601\u002FSkiilsToIAs --skill plan-canvas","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs\u002Fblob\u002Fmain\u002Fai-agents\u002Fplan-canvas\u002FSKILL.md",true,[48],{"path":49,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":52,"sourceHtmlUrl":53},"agents\u002Fopenai.yaml","REFERENCE","参考文档",286,"https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs\u002Fblob\u002Fmain\u002Fai-agents\u002Fplan-canvas\u002Fagents\u002Fopenai.yaml",[55,62,69,77,84,91],{"skillNo":56,"name":57,"nameZh":6,"description":58,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":59,"categories":60,"keywords":61,"publishedAt":19},"01M7E2ANBW9V6AVX5JXNCEAWF8","rag-architect-agent","Agente Arquiteto de RAG, Embeddings & Busca Vetorial. Especialista em design e implementação de pipelines de Retrieval-Augmented Generation de alta fidelidade: chunking semântico, modelagem pgvector no PostgreSQL (Neon\u002FSupabase), busca híbrida (cosseno + BM25), reranking, validação via TypeSafe AI e filosofia Ponytail (anti-overengineering).","https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs\u002Fblob\u002Fmain\u002Fcustom-agents\u002Frag-architect-agent\u002FSKILL.md",[],[],{"skillNo":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"publishedAt":19},"01M7E29KKF8R02ZRGYE2MJM67G","rag-architecture-patterns","Padrões arquiteturais e implementação de pipelines RAG (Retrieval-Augmented Generation) de alta fidelidade para qualquer projeto ou sistema. Cobre chunking semântico, embeddings, busca híbrida (pgvector + BM25), reranking, validação via TypeSafe AI e filosofia Ponytail (anti-overengineering).","https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs\u002Fblob\u002Fmain\u002Fai-agents\u002Frag-architecture-patterns\u002FSKILL.md",[],[],{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":73,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":19},"01M7CWRA8E3BJ7CPY8N8EG28J1","skill-repair","Use this to fix and re-install agent skills that have failed installation.\nThis skill provides the necessary context and permissions to surgically update\nthe `manifest.json` after a fix has been applied.","Apache-2.0","https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs\u002Fblob\u002Fmain\u002Futilities\u002Fskill-repair\u002FSKILL.md",[],[],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":19},"01M7CWR66FZP8FA47WVZ4Z2EXC","security-scan","Scan your Claude Code configuration (.claude\u002F directory) for security vulnerabilities, misconfigurations, and injection risks using AgentShield. Checks CLAUDE.md, settings.json, MCP servers, hooks, and agent definitions.","https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs\u002Fblob\u002Fmain\u002Futilities\u002Fsecurity-scan\u002FSKILL.md",[],[],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":19},"01M7CWR0QPY58QPTR1P759TFNG","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\u002FHenrique1601\u002FSkiilsToIAs\u002Fblob\u002Fmain\u002Futilities\u002Fsecurity-review\u002FSKILL.md",[],[],{"skillNo":92,"name":93,"nameZh":6,"description":94,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":95,"categories":96,"keywords":97,"publishedAt":19},"01M7CWQXCE40XWT4FZ3VWZFGDP","security-bounty-hunter","Hunt for exploitable, bounty-worthy security issues in repositories. Focuses on remotely reachable vulnerabilities that qualify for real reports instead of noisy local-only findings.","https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs\u002Fblob\u002Fmain\u002Futilities\u002Fsecurity-bounty-hunter\u002FSKILL.md",[],[]]