[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6MP5GEY6TH4712QQ3NNSGCE":3,"skill-same:01M6MP5GEY6TH4712QQ3NNSGCE":87},{"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":23,"publishedAt":45,"linkOnly":46,"markdownContent":47,"markdownBody":48,"frontMatter":49,"refName":51,"commitSha":52,"skillDirectory":53,"forksCount":54,"repositoryHtmlUrl":55,"repositoryHomepageUrl":56,"ownerHtmlUrl":57,"ownerBlogUrl":58,"ownerDescription":59,"updatedAt":60,"install":61,"resources":74},"01M6MP5GEY6TH4712QQ3NNSGCE","visual-companion",null,"Browser-based visual brainstorming companion for showing mockups, diagrams, and visual options. Use when brainstorm topics involve UI\u002FUX, layout, architecture diagrams, or any content better understood visually.","hashgraph-online\u002Fawesome-codex-plugins","hashgraph-online","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F160371962?v=4","01M6CNB6NRJVNNGN14TR01Q6D3","HOL (Hashgraph Online)","01M6JT1HSKKG9V68KQAQGBA7XP",1575,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fyagizdo\u002Fquiver\u002Fskills\u002Fvisual-companion\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000032","设计师","PROFESSION","适用职业",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44],"visual companion","companion","visual","use","when","for","layout","options","me","show","diagrams","visualize","brainstorm","show me","open","ui","ux","browser","architecture diagrams","diagram","architecture","2026-11-10 10:12:30",false,"---\nname: visual-companion\ndescription: Browser-based visual brainstorming companion for showing mockups, diagrams, and visual options. Use when brainstorm topics involve UI\u002FUX, layout, architecture diagrams, or any content better understood visually.\nwhen-to-use: \"user wants visual mockups, UI diagrams, or architecture sketches -- '\u002Fvisual-companion', 'show me a diagram', 'sketch this UI', 'visualize this', 'open visual companion'\"\n---\n\n# Visual Companion\n\nA browser-based companion for displaying mockups, wireframes, architecture diagrams, and side-by-side visual comparisons during brainstorm sessions.\n\n## 1. When to Use\n\nDecide **per question** whether to show content in the browser or keep it in the terminal.\n\n**Use the browser for:**\n- UI mockups and wireframes\n- Architecture diagrams and system maps\n- Side-by-side visual comparisons (layout A vs. layout B)\n- Spatial relationships (grid layouts, navigation flows, screen transitions)\n- Color palettes, typography samples, component galleries\n\n**Use the terminal for:**\n- Requirements questions and conceptual choices\n- Tradeoff lists and technical decisions\n- Clarifying questions about scope or constraints\n- API design, data models, algorithm selection\n\nA question about a UI topic is not automatically a visual question. \"Should we use tabs or accordion?\" is a terminal question. \"Here are two tab layouts -- which one?\" is a browser question.\n\n## 2. Starting a Session\n\n1. Create a temporary directory for HTML files:\n   ```\n   mktemp -d \u002Ftmp\u002Fvisual-companion-XXXXXX\n   ```\n\n2. Start the visual companion server in the background:\n   ```\n   python3 \u003Cskill-dir>\u002Fserver.py --dir \u003Ctemp-dir> &\n   ```\n   `\u003Cskill-dir>` is resolved by the invoking agent to the absolute path of `skills\u002Fvisual-companion\u002F`.\n   Do NOT pass `--owner-pid` -- in the Bash tool context, `$$` resolves to the ephemeral shell PID that dies immediately, causing the server to self-terminate within seconds. The server already has idle timeout (30 min) and max lifetime (8h) for cleanup.\n\n3. **Wait for the server to become ready before announcing its URL.** The `&` in step 2 returns immediately; the Python process still needs to import modules, bind the port, and write `server-info.json`. Announcing the URL before this finishes is the #1 cause of \"localhost opened but link unreachable\" failures. Probe until both `server-info.json` exists and the port accepts TCP connections:\n   ```\n   for i in $(seq 1 30); do\n     [ -f \u003Ctemp-dir>\u002F.vc-meta\u002Fserver-info.json ] && \\\n       python3 -c \"import json,socket; info=json.load(open('\u003Ctemp-dir>\u002F.vc-meta\u002Fserver-info.json')); s=socket.socket(); s.settimeout(0.5); s.connect(('127.0.0.1', info['port'])); s.close(); print(info['url'])\" 2>\u002Fdev\u002Fnull && break\n     sleep 0.2\n   done\n   ```\n   - If the loop prints a URL, the server is ready. Use that URL.\n   - If the loop completes with no output, the server failed to launch. Do NOT announce a URL. Inspect `\u003Ctemp-dir>\u002F.vc-meta\u002F` and the background-process output, fix the underlying issue, and retry step 2.\n\n4. Tell the user (only after step 3 prints a URL):\n   > Visual companion running at {url}. Open it in your browser.\n\n5. **Push an initial HTML page immediately.** Do NOT enter the question flow while the browser shows the \"waiting\" page -- the user sees a broken-looking screen and loses confidence. Write a context-setting HTML fragment to `\u003Ctemp-dir>` right now, before any `AskUserQuestion` call. The content depends on the session:\n   - For brainstorm sessions: a brief \"session overview\" card showing the topic and what is coming next.\n   - For other sessions: a simple title card with the session purpose.\n   The server's SSE auto-reload will push this to the browser. Confirm the browser shows your content before proceeding.\n\n## 3. The Loop\n\nFor each visual step in the brainstorm:\n\n1. **Write an HTML fragment** to `\u003Ctemp-dir>` with a semantic filename (e.g., `layout-options.html`). Write body content only -- the server wraps fragments automatically.\n2. **Never reuse filenames.** Each screen gets a fresh file. For iterations, append a version suffix: `layout-options-v2.html`. Older files stay on disk so the agent can copy them out at the end of the session.\n3. **Browser stays on `\u002F` and auto-shows the newest file.** The server routes the root URL to the most recently modified `.html` file in the temp dir; SSE reload triggers whenever any HTML file changes. The user opens the URL once and never has to navigate manually -- each new file replaces the previous view automatically.\n\n### Pick ONE input mode per step\n\nA step is either **browser-answered** or **terminal-answered**. Do not do both in the same step. Mixing them produces the common failure: agent renders clickable cards, user clicks them, agent is actually blocked on `AskUserQuestion` -- clicks land in `events.jsonl` that the agent never reads, and the user sees their clicks \"do nothing.\"\n\n**Mode A -- Browser-answered (the cards ARE the question):**\n\nUse when the whole point is \"pick one of these visual options.\"\n\n**Pre-write checklist (mandatory before every Mode A HTML write):**\n- Every selectable visual element MUST have a `data-choice=\"\u003Cvalue>\"` attribute. The client JS ignores elements without it -- styled cards that look clickable but lack `data-choice` are a silent bug (clicks vanish, user sees nothing happen).\n- Do NOT use `AskUserQuestion` in Mode A. The browser click IS the answer.\n\n1. Clear stale selections first so old clicks do not leak into the new question:\n   ```\n   python3 -c \"import urllib.request; req=urllib.request.Request('http:\u002F\u002Flocalhost:{port}\u002Fevents', method='DELETE'); urllib.request.urlopen(req)\"\n   ```\n2. Write HTML with `[data-choice]` elements. The client JS highlights the clicked element and POSTs to `\u002Fevent`, which appends a line to `.vc-meta\u002Fevents.jsonl`.\n3. Tell the user explicitly: `> Click one of the cards in the browser to select your choice.`\n4. Poll `events.jsonl` until a new line arrives (up to ~60s):\n   ```\n   for i in $(seq 1 300); do\n     line=$(tail -n 1 \u003Ctemp-dir>\u002F.vc-meta\u002Fevents.jsonl 2>\u002Fdev\u002Fnull)\n     [ -n \"$line\" ] && echo \"$line\" && break\n     sleep 0.2\n   done\n   ```\n5. Parse the JSON line and use the `choice` field as the answer.\n6. If the poll times out with no click, fall back to `AskUserQuestion` and treat the step as Mode B from this point on.\n\n**Mode B -- Terminal-answered (browser is visual aid only):**\n\nUse when the browser shows a diagram, mockup, or reference and the real answer is a conceptual choice or free text.\n\n1. Write the HTML WITHOUT `[data-choice]` attributes. Clickable styling with no listener on the agent side is the bug that bit us before -- if you are not going to poll `events.jsonl`, do not ship clickable targets.\n2. Ask the question with `AskUserQuestion`. The browser is decoration; the button click is the answer.\n\n**Terminal-only steps (no browser):** No HTML update needed. Optionally push a placeholder page:\n   ```html\n   \u003Cdiv style=\"display:flex;align-items:center;justify-content:center;height:100vh;font-family:system-ui;color:#666\">\n     \u003Cp>Continuing in terminal...\u003C\u002Fp>\n   \u003C\u002Fdiv>\n   ```\n\n## 4. HTML Content Guide\n\nWrite body content only. The server wraps fragments with DOCTYPE, CSS, and client JS automatically.\n\nA file is treated as a fragment if its first 256 bytes (stripped, case-insensitive) do not start with `\u003C!DOCTYPE` or `\u003Chtml>`. Full HTML documents are served as-is, with client JS injected before `\u003C\u002Fbody>`.\n\n### Layout Patterns\n\n- **Options grid:** Use `.options` + `.option` for comparing 2-3 approaches visually. Mark the recommended option with `.recommended`.\n- **Cards:** Use `.cards` + `.card` for component galleries or feature inventories.\n- **Mockup:** Use `.mockup` with `.mock-nav`, `.mock-sidebar`, `.mock-content` for wireframes.\n- **Split view:** Use `.split` for before\u002Fafter or A\u002FB comparisons.\n- **Pros\u002Fcons:** Use `.pros-cons` for tradeoff visualization.\n- **Mock UI:** `.mock-button`, `.mock-input` for wireframe form elements.\n\n### Clickable Options with `data-choice`\n\nAdd `data-choice` attributes to elements that users can click to make selections:\n\n```html\n\u003Cdiv class=\"options\">\n  \u003Cdiv class=\"option\" data-choice=\"grid\">\n    \u003Ch3>Grid Layout\u003C\u002Fh3>\n    \u003Cp>Content arranged in a responsive grid\u003C\u002Fp>\n  \u003C\u002Fdiv>\n  \u003Cdiv class=\"option\" data-choice=\"list\">\n    \u003Ch3>List Layout\u003C\u002Fh3>\n    \u003Cp>Content in a vertical list\u003C\u002Fp>\n  \u003C\u002Fdiv>\n\u003C\u002Fdiv>\n```\n\nWhen a user clicks a `[data-choice]` element:\n- The `.selected` class is added (blue border + light blue background)\n- Previous selections within the same parent are deselected\n- A JSON event is appended to `.vc-meta\u002Fevents.jsonl`:\n  ```\n  {\"type\":\"choice\",\"choice\":\"grid\",\"text\":\"Grid Layout Content arranged in a responsive grid\",\"timestamp\":\"2026-04-09T14:30:00.000Z\"}\n  ```\n\n### events.jsonl Format\n\nEach line is a JSON object appended by the server. The agent reads this file to see what the user clicked:\n```\n{\"type\":\"choice\",\"choice\":\"option-a\",\"text\":\"Option A\",\"timestamp\":\"...\"}\n{\"type\":\"choice\",\"choice\":\"option-b\",\"text\":\"Option B\",\"timestamp\":\"...\"}\n```\n\n## 5. Cleaning Up\n\nThe server self-terminates in two cases:\n- **Idle timeout:** No real HTTP activity (page loads, click events, agent updates) for 30 minutes. SSE keepalives and auto-reconnects do NOT reset this timer -- if they did, an open browser tab would keep the server alive forever through any network blip.\n- **Max lifetime:** 8 hours since startup, regardless of activity. Override with `--max-lifetime \u003Cseconds>`; set to 0 to disable.\n\nNote: `--owner-pid` exists in server.py but is NOT used in the startup template above. In the Bash tool context, `$$` resolves to an ephemeral shell PID that dies immediately, making the owner-PID mechanism unreliable. The idle timeout and max lifetime are sufficient.\n\nTo stop manually:\n```\nkill $(cat \u003Ctemp-dir>\u002F.vc-meta\u002Fserver-info.json | python3 -c \"import sys,json; print(json.load(sys.stdin)['pid'])\") 2>\u002Fdev\u002Fnull\n```\n\nHTML files remain in the temp directory for reference. Optionally copy key mockups to `.claude\u002Fspecs\u002F` alongside the spec:\n```\ncp \u003Ctemp-dir>\u002Ffinal-layout.html .claude\u002Fspecs\u002FYYYY-MM-DD-\u003Cname>-mockups\u002F\n```\n","# Visual Companion\n\nA browser-based companion for displaying mockups, wireframes, architecture diagrams, and side-by-side visual comparisons during brainstorm sessions.\n\n## 1. When to Use\n\nDecide **per question** whether to show content in the browser or keep it in the terminal.\n\n**Use the browser for:**\n- UI mockups and wireframes\n- Architecture diagrams and system maps\n- Side-by-side visual comparisons (layout A vs. layout B)\n- Spatial relationships (grid layouts, navigation flows, screen transitions)\n- Color palettes, typography samples, component galleries\n\n**Use the terminal for:**\n- Requirements questions and conceptual choices\n- Tradeoff lists and technical decisions\n- Clarifying questions about scope or constraints\n- API design, data models, algorithm selection\n\nA question about a UI topic is not automatically a visual question. \"Should we use tabs or accordion?\" is a terminal question. \"Here are two tab layouts -- which one?\" is a browser question.\n\n## 2. Starting a Session\n\n1. Create a temporary directory for HTML files:\n   ```\n   mktemp -d \u002Ftmp\u002Fvisual-companion-XXXXXX\n   ```\n\n2. Start the visual companion server in the background:\n   ```\n   python3 \u003Cskill-dir>\u002Fserver.py --dir \u003Ctemp-dir> &\n   ```\n   `\u003Cskill-dir>` is resolved by the invoking agent to the absolute path of `skills\u002Fvisual-companion\u002F`.\n   Do NOT pass `--owner-pid` -- in the Bash tool context, `$$` resolves to the ephemeral shell PID that dies immediately, causing the server to self-terminate within seconds. The server already has idle timeout (30 min) and max lifetime (8h) for cleanup.\n\n3. **Wait for the server to become ready before announcing its URL.** The `&` in step 2 returns immediately; the Python process still needs to import modules, bind the port, and write `server-info.json`. Announcing the URL before this finishes is the #1 cause of \"localhost opened but link unreachable\" failures. Probe until both `server-info.json` exists and the port accepts TCP connections:\n   ```\n   for i in $(seq 1 30); do\n     [ -f \u003Ctemp-dir>\u002F.vc-meta\u002Fserver-info.json ] && \\\n       python3 -c \"import json,socket; info=json.load(open('\u003Ctemp-dir>\u002F.vc-meta\u002Fserver-info.json')); s=socket.socket(); s.settimeout(0.5); s.connect(('127.0.0.1', info['port'])); s.close(); print(info['url'])\" 2>\u002Fdev\u002Fnull && break\n     sleep 0.2\n   done\n   ```\n   - If the loop prints a URL, the server is ready. Use that URL.\n   - If the loop completes with no output, the server failed to launch. Do NOT announce a URL. Inspect `\u003Ctemp-dir>\u002F.vc-meta\u002F` and the background-process output, fix the underlying issue, and retry step 2.\n\n4. Tell the user (only after step 3 prints a URL):\n   > Visual companion running at {url}. Open it in your browser.\n\n5. **Push an initial HTML page immediately.** Do NOT enter the question flow while the browser shows the \"waiting\" page -- the user sees a broken-looking screen and loses confidence. Write a context-setting HTML fragment to `\u003Ctemp-dir>` right now, before any `AskUserQuestion` call. The content depends on the session:\n   - For brainstorm sessions: a brief \"session overview\" card showing the topic and what is coming next.\n   - For other sessions: a simple title card with the session purpose.\n   The server's SSE auto-reload will push this to the browser. Confirm the browser shows your content before proceeding.\n\n## 3. The Loop\n\nFor each visual step in the brainstorm:\n\n1. **Write an HTML fragment** to `\u003Ctemp-dir>` with a semantic filename (e.g., `layout-options.html`). Write body content only -- the server wraps fragments automatically.\n2. **Never reuse filenames.** Each screen gets a fresh file. For iterations, append a version suffix: `layout-options-v2.html`. Older files stay on disk so the agent can copy them out at the end of the session.\n3. **Browser stays on `\u002F` and auto-shows the newest file.** The server routes the root URL to the most recently modified `.html` file in the temp dir; SSE reload triggers whenever any HTML file changes. The user opens the URL once and never has to navigate manually -- each new file replaces the previous view automatically.\n\n### Pick ONE input mode per step\n\nA step is either **browser-answered** or **terminal-answered**. Do not do both in the same step. Mixing them produces the common failure: agent renders clickable cards, user clicks them, agent is actually blocked on `AskUserQuestion` -- clicks land in `events.jsonl` that the agent never reads, and the user sees their clicks \"do nothing.\"\n\n**Mode A -- Browser-answered (the cards ARE the question):**\n\nUse when the whole point is \"pick one of these visual options.\"\n\n**Pre-write checklist (mandatory before every Mode A HTML write):**\n- Every selectable visual element MUST have a `data-choice=\"\u003Cvalue>\"` attribute. The client JS ignores elements without it -- styled cards that look clickable but lack `data-choice` are a silent bug (clicks vanish, user sees nothing happen).\n- Do NOT use `AskUserQuestion` in Mode A. The browser click IS the answer.\n\n1. Clear stale selections first so old clicks do not leak into the new question:\n   ```\n   python3 -c \"import urllib.request; req=urllib.request.Request('http:\u002F\u002Flocalhost:{port}\u002Fevents', method='DELETE'); urllib.request.urlopen(req)\"\n   ```\n2. Write HTML with `[data-choice]` elements. The client JS highlights the clicked element and POSTs to `\u002Fevent`, which appends a line to `.vc-meta\u002Fevents.jsonl`.\n3. Tell the user explicitly: `> Click one of the cards in the browser to select your choice.`\n4. Poll `events.jsonl` until a new line arrives (up to ~60s):\n   ```\n   for i in $(seq 1 300); do\n     line=$(tail -n 1 \u003Ctemp-dir>\u002F.vc-meta\u002Fevents.jsonl 2>\u002Fdev\u002Fnull)\n     [ -n \"$line\" ] && echo \"$line\" && break\n     sleep 0.2\n   done\n   ```\n5. Parse the JSON line and use the `choice` field as the answer.\n6. If the poll times out with no click, fall back to `AskUserQuestion` and treat the step as Mode B from this point on.\n\n**Mode B -- Terminal-answered (browser is visual aid only):**\n\nUse when the browser shows a diagram, mockup, or reference and the real answer is a conceptual choice or free text.\n\n1. Write the HTML WITHOUT `[data-choice]` attributes. Clickable styling with no listener on the agent side is the bug that bit us before -- if you are not going to poll `events.jsonl`, do not ship clickable targets.\n2. Ask the question with `AskUserQuestion`. The browser is decoration; the button click is the answer.\n\n**Terminal-only steps (no browser):** No HTML update needed. Optionally push a placeholder page:\n   ```html\n   \u003Cdiv style=\"display:flex;align-items:center;justify-content:center;height:100vh;font-family:system-ui;color:#666\">\n     \u003Cp>Continuing in terminal...\u003C\u002Fp>\n   \u003C\u002Fdiv>\n   ```\n\n## 4. HTML Content Guide\n\nWrite body content only. The server wraps fragments with DOCTYPE, CSS, and client JS automatically.\n\nA file is treated as a fragment if its first 256 bytes (stripped, case-insensitive) do not start with `\u003C!DOCTYPE` or `\u003Chtml>`. Full HTML documents are served as-is, with client JS injected before `\u003C\u002Fbody>`.\n\n### Layout Patterns\n\n- **Options grid:** Use `.options` + `.option` for comparing 2-3 approaches visually. Mark the recommended option with `.recommended`.\n- **Cards:** Use `.cards` + `.card` for component galleries or feature inventories.\n- **Mockup:** Use `.mockup` with `.mock-nav`, `.mock-sidebar`, `.mock-content` for wireframes.\n- **Split view:** Use `.split` for before\u002Fafter or A\u002FB comparisons.\n- **Pros\u002Fcons:** Use `.pros-cons` for tradeoff visualization.\n- **Mock UI:** `.mock-button`, `.mock-input` for wireframe form elements.\n\n### Clickable Options with `data-choice`\n\nAdd `data-choice` attributes to elements that users can click to make selections:\n\n```html\n\u003Cdiv class=\"options\">\n  \u003Cdiv class=\"option\" data-choice=\"grid\">\n    \u003Ch3>Grid Layout\u003C\u002Fh3>\n    \u003Cp>Content arranged in a responsive grid\u003C\u002Fp>\n  \u003C\u002Fdiv>\n  \u003Cdiv class=\"option\" data-choice=\"list\">\n    \u003Ch3>List Layout\u003C\u002Fh3>\n    \u003Cp>Content in a vertical list\u003C\u002Fp>\n  \u003C\u002Fdiv>\n\u003C\u002Fdiv>\n```\n\nWhen a user clicks a `[data-choice]` element:\n- The `.selected` class is added (blue border + light blue background)\n- Previous selections within the same parent are deselected\n- A JSON event is appended to `.vc-meta\u002Fevents.jsonl`:\n  ```\n  {\"type\":\"choice\",\"choice\":\"grid\",\"text\":\"Grid Layout Content arranged in a responsive grid\",\"timestamp\":\"2026-04-09T14:30:00.000Z\"}\n  ```\n\n### events.jsonl Format\n\nEach line is a JSON object appended by the server. The agent reads this file to see what the user clicked:\n```\n{\"type\":\"choice\",\"choice\":\"option-a\",\"text\":\"Option A\",\"timestamp\":\"...\"}\n{\"type\":\"choice\",\"choice\":\"option-b\",\"text\":\"Option B\",\"timestamp\":\"...\"}\n```\n\n## 5. Cleaning Up\n\nThe server self-terminates in two cases:\n- **Idle timeout:** No real HTTP activity (page loads, click events, agent updates) for 30 minutes. SSE keepalives and auto-reconnects do NOT reset this timer -- if they did, an open browser tab would keep the server alive forever through any network blip.\n- **Max lifetime:** 8 hours since startup, regardless of activity. Override with `--max-lifetime \u003Cseconds>`; set to 0 to disable.\n\nNote: `--owner-pid` exists in server.py but is NOT used in the startup template above. In the Bash tool context, `$$` resolves to an ephemeral shell PID that dies immediately, making the owner-PID mechanism unreliable. The idle timeout and max lifetime are sufficient.\n\nTo stop manually:\n```\nkill $(cat \u003Ctemp-dir>\u002F.vc-meta\u002Fserver-info.json | python3 -c \"import sys,json; print(json.load(sys.stdin)['pid'])\") 2>\u002Fdev\u002Fnull\n```\n\nHTML files remain in the temp directory for reference. Optionally copy key mockups to `.claude\u002Fspecs\u002F` alongside the spec:\n```\ncp \u003Ctemp-dir>\u002Ffinal-layout.html .claude\u002Fspecs\u002FYYYY-MM-DD-\u003Cname>-mockups\u002F\n```\n",{"name":5,"description":7,"when-to-use":50},"user wants visual mockups, UI diagrams, or architecture sketches -- '\u002Fvisual-companion', 'show me a diagram', 'sketch this UI', 'visualize this', 'open visual companion'","main","2b63f856ce19c2a797929cacabd9e0fc936812fa","plugins\u002Fyagizdo\u002Fquiver\u002Fskills\u002Fvisual-companion",491,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins","https:\u002F\u002Fhol.org\u002Fplugins\u002Fbest-codex-plugins","https:\u002F\u002Fgithub.com\u002Fhashgraph-online","https:\u002F\u002Fhol.org","Open-source standards and developer tools for interoperable AI agents: discovery, identity, communication, payments, privacy and security.","2026-11-14 14:06:13",{"source":8,"skillName":5,"commands":62,"prompt":72,"zipAvailable":73},[63,66,69],{"tool":64,"command":65},"npx","npx skills add hashgraph-online\u002Fawesome-codex-plugins --skill visual-companion",{"tool":67,"command":68},"bunx","bunx skills add hashgraph-online\u002Fawesome-codex-plugins --skill visual-companion",{"tool":70,"command":71},"pnpm","pnpm dlx skills add hashgraph-online\u002Fawesome-codex-plugins --skill visual-companion","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fyagizdo\u002Fquiver\u002Fskills\u002Fvisual-companion\u002FSKILL.md",true,[75,81],{"path":76,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":79,"sourceHtmlUrl":80},"server.py","SCRIPT","脚本",19036,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fyagizdo\u002Fquiver\u002Fskills\u002Fvisual-companion\u002Fserver.py",{"path":82,"resourceType":83,"resourceTypeDesc":84,"sizeBytes":85,"sourceHtmlUrl":86},"TEST-PLAN.md","REFERENCE","参考文档",2249,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fyagizdo\u002Fquiver\u002Fskills\u002Fvisual-companion\u002FTEST-PLAN.md",[88,98,106,114,122,130],{"skillNo":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":92,"licenseFileUrl":93,"sourceHtmlUrl":94,"categories":95,"keywords":96,"publishedAt":97},"01M7DV332YQMGD8WTRJ9DZQXTB","worktable-review-with-annotations","Create, inspect, reply to, update, or resolve situated Worktable annotations. Use when feedback belongs to a Doc section, block, text range, or HTML Doc, or when the user asks to address existing review feedback and coordinate a requested artifact edit.","MIT","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-review-with-annotations\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-review-with-annotations\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"skillNo":99,"name":100,"nameZh":6,"description":101,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":92,"licenseFileUrl":102,"sourceHtmlUrl":103,"categories":104,"keywords":105,"publishedAt":97},"01M7DV2YGHCZVBEB1AHYB6CGHE","worktable-find-and-synthesize-context","Find, assess, and synthesize context from Worktable Docs and Records. Use when the user asks what a workspace contains, wants workspace-backed research, needs current facts reconciled across artifacts, or requests a cited synthesis without changing workspace state.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-find-and-synthesize-context\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-find-and-synthesize-context\u002FSKILL.md",[],[],{"skillNo":107,"name":108,"nameZh":6,"description":109,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":92,"licenseFileUrl":110,"sourceHtmlUrl":111,"categories":112,"keywords":113,"publishedAt":97},"01M7DV2TQN1H11ME2SAF9MXN7V","worktable-create-or-update-docs","Create, edit, rename, or maintain narrative Worktable Docs. Use for plans, decisions, briefs, notes, research syntheses, and other durable prose when the user requests a new artifact or a safe update to an existing one.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-update-docs\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-update-docs\u002FSKILL.md",[],[],{"skillNo":115,"name":116,"nameZh":6,"description":117,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":92,"licenseFileUrl":118,"sourceHtmlUrl":119,"categories":120,"keywords":121,"publishedAt":97},"01M7DV2NE452NEA8TXATKSNAJH","worktable-create-or-manage-records","Organize repeated structured information as durable Worktable Records. Use for research datasets, inventories, directories, pipelines, trackers, and other collections whose items need identity, fields, filtering, links, validation, or individual updates.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-records\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-records\u002FSKILL.md",[],[],{"skillNo":123,"name":124,"nameZh":6,"description":125,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":92,"licenseFileUrl":126,"sourceHtmlUrl":127,"categories":128,"keywords":129,"publishedAt":97},"01M7DV2HENRBR2KSCVM064WH0Y","worktable-create-or-manage-interactive-html","Create or improve durable visual and interactive artifacts in Worktable. Use for dashboards, trackers, calculators, mini apps, slide presentations, and other requests that benefit from a polished HTML Doc.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-interactive-html\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-interactive-html\u002FSKILL.md",[],[],{"skillNo":131,"name":132,"nameZh":6,"description":133,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":92,"licenseFileUrl":134,"sourceHtmlUrl":135,"categories":136,"keywords":137,"publishedAt":97},"01M7DV2CADR5R7RQFFYPNAGR9Y","worktable-collaborate-threads","Read, answer, and hand off messages through durable Worktable threads with users or other authenticated participants. Use when the user asks to check addressed messages, reply to a participant, continue a thread, request another agent's help, wait briefly for a response, or watch for comments and messages sent to the agent.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-collaborate-threads\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-collaborate-threads\u002FSKILL.md",[],[]]