[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7BJKHY3763SN5RT63PYV3MB":3,"skill-same:01M7BJKHY3763SN5RT63PYV3MB":63},{"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":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":6,"ownerHtmlUrl":29,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":30,"install":31,"resources":44},"01M7BJKHY3763SN5RT63PYV3MB","d3-visualization",null,"Build offline, deterministic D3.js **v6** web-app visualizations (HTML+CSS+JS) from local datasets, including force-layout bubble charts, tooltips, legends, and **two-way linked** chart↔table selection (with label overlays that don’t break clicking).","linyouxue\u002Fskill-repair-benchmark","linyouxue","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F216151464?v=4","01M7BJEVCXKD74KH6FG9CBVSQB","林宥学","01M7BJEVE02NP217V93BKZFC0J",0,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Flinyouxue\u002Fskill-repair-benchmark\u002Fblob\u002Fmain\u002Fcontrolled-skill-repair-experiments\u002Fresult\u002Fmmg2skill-gpt5.2-xhigh\u002Fcandidates\u002Flocation-data-to-d3\u002Fround-3\u002Fskills\u002Fd3-visualization\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: d3-visualization\ndescription: Build offline, deterministic D3.js **v6** web-app visualizations (HTML+CSS+JS)\n  from local datasets, including force-layout bubble charts, tooltips, legends, and\n  **two-way linked** chart↔table selection (with label overlays that don’t break clicking).\n---\n\n## Steps\n1. **Lock requirements + acceptance checks up front (write them into code comments and re-check at the end)**\n   - Confirm required **D3 version (v6)**, required output paths, and required data sources (main CSV + `indiv-stock\u002F` folder).\n   - Create an acceptance checklist that explicitly includes:\n     - Required artifacts exist **on disk** and are referenced locally: `index.html`, `css\u002Fstyle.css`, `js\u002Fd3.v6.min.js`, `js\u002Fvisualization.js`, and `data\u002F` copies.\n     - Bubble **click works even when clicking the ticker text label** (labels must not steal pointer events; click handler must be on the node container\u002Fcircle).\n     - Tooltip shows **ticker + name + sector**, and is **suppressed for ETFs** (ETF rows have missing `marketCap\u002Fcountry\u002Fwebsite`; show nothing for them).\n     - **Two-way linking**: click bubble highlights table row, click row highlights bubble using **one shared selection state** (use the same `.selected` class on both).\n\n2. **Inspect data using only built-in tools (do not assume pandas is installed)**\n   - Use Python’s built-in `csv` module (or `head`, `wc`, `ls`) to confirm:\n     - `stock-descriptions.csv` columns + row count (**expect 50 rows for this dataset**) and which fields are missing for ETFs.\n     - Sector domain (**expect 5 sectors including `ETF`**) and deterministic ordering (e.g., sort sectors alphabetically for stable colors\u002Flegend).\n     - ETF rows (**expect ~10**; spot-check tickers like `SPY`, `VOO`, `QQQ`, `GLD`).\n     - `indiv-stock\u002F` naming convention (`TICKER.csv`) and file count (**expect 50 files**) and one sample file’s columns (e.g., `Date`, `Open\u002FHigh\u002FLow\u002FClose`, `Volume`, `Adjusted Close`).\n   - Identify ETFs deterministically (e.g., missing `marketCap\u002Fcountry\u002Fwebsite`, not just a label) so tooltip suppression and sizing are correct.\n\n3. **Create the `\u002Froot\u002Foutput\u002F` tree and required files early, and prove it with terminal output**\n   - Execute filesystem-writing steps via the terminal tool (don’t just paste commands), and immediately follow them with checks that show up in the trace:\n     - Create required directories: `\u002Froot\u002Foutput\u002Fjs`, `\u002Froot\u002Foutput\u002Fcss`, `\u002Froot\u002Foutput\u002Fdata`, then `ls -ld` them.\n     - Copy input data into `\u002Froot\u002Foutput\u002Fdata\u002F` (including the full `indiv-stock\u002F` directory), then verify with:\n       - `test -f \u002Froot\u002Foutput\u002Fdata\u002Fstock-descriptions.csv`\n       - `test -d \u002Froot\u002Foutput\u002Fdata\u002Findiv-stock`\n       - `ls \u002Froot\u002Foutput\u002Fdata\u002Findiv-stock | wc -l` (should be 50)\n     - Vendor **D3 v6** to `\u002Froot\u002Foutput\u002Fjs\u002Fd3.v6.min.js` (local copy, not CDN at runtime). Prefer copying from an installed `d3` package if available (e.g., `node -p \"require.resolve('d3\u002Fdist\u002Fd3.min.js')\"`) otherwise download it; then verify:\n       - `test -s \u002Froot\u002Foutput\u002Fjs\u002Fd3.v6.min.js` and `wc -c` shows a non-trivial size\n       - The file corresponds to v6 (e.g., search for a `v6.` marker if present, or verify `d3.version` in-browser during manual check).\n     - Create the three app files **right away** (even minimal placeholders first): `\u002Froot\u002Foutput\u002Findex.html`, `\u002Froot\u002Foutput\u002Fjs\u002Fvisualization.js`, `\u002Froot\u002Foutput\u002Fcss\u002Fstyle.css`, then verify they exist and are non-empty with `test -s` and `ls -l`.\n   - When writing files:\n     - Use quoted heredocs: `cat > file \u003C\u003C'EOF' ... EOF` (prevents JS template strings\u002Fbackticks from breaking the shell).\n\n4. **Create an HTML skeleton that supports the required layout and interactivity**\n   - Use a two-column layout (flex\u002Fgrid) for “bubble chart” (left) and “table” (right).\n   - Include:\n     - A chart container (SVG or a div into which the SVG is appended).\n     - A legend container.\n     - A table container.\n     - A tooltip `\u003Cdiv id=\"tooltip\" class=\"tooltip\">\u003C\u002Fdiv>` (CSS toggles `.visible`).\n   - Reference only local assets (no CDN): `css\u002Fstyle.css`, then `js\u002Fd3.v6.min.js`, then `js\u002Fvisualization.js` (use `defer` on the app script if needed).\n\n5. **Load\u002Fprepare data deterministically and offline-friendly**\n   - Prefer approaches that work when opened locally:\n     - If `file:\u002F\u002F` loading is a concern, embed the CSV content at build time and parse via `d3.csvParse(...)`.\n     - If you rely on runtime loading, use relative paths under the output tree (e.g., `data\u002Fstock-descriptions.csv`).\n   - Normalize fields:\n     - `marketCap`: number or `null`\n     - `isETF`: derived from missing `marketCap\u002Fcountry\u002Fwebsite` (drives uniform sizing + tooltip suppression).\n   - Keep ordering stable (e.g., sort by sector then ticker) before binding to marks.\n\n6. **Bubble chart: force clusters by sector, no overlaps, centered clusters, clickable even with labels**\n   - Scales:\n     - Radius: `d3.scaleSqrt` on `marketCap` (ETFs get a uniform radius).\n     - Color: `d3.scaleOrdinal` with **sorted sector domain** and a fixed scheme.\n   - Force simulation:\n     - Use `forceCenter(width\u002F2, height\u002F2)`.\n     - Compute sector target positions **near the center** (compact circle\u002Fgrid), then cluster via `forceX\u002FforceY` so sector groups don’t drift far away.\n     - Use `forceCollide(d => d.r + padding)` to prevent overlaps.\n     - For determinism: set initial `(x,y)` deterministically; run a fixed number of ticks and stop if you don’t need animation.\n   - Rendering pattern that guarantees “clicking text still clicks bubble”:\n     - Create one `\u003Cg class=\"node\">` per stock; append `\u003Ccircle>` then `\u003Ctext>` inside it; on each tick, move the **group** via `transform: translate(x,y)` so circle+label stay aligned.\n     - Attach hover\u002Fclick handlers to the **`g.node` (or the circle)**, never to the text.\n     - Ensure the label never captures clicks: `text.attr('pointer-events', 'none')` (or CSS `.node text{pointer-events:none}`).\n   - Legend:\n     - Build legend entries from `colorScale.domain()` so every sector appears exactly once with its color swatch + name.\n   - Tooltip:\n     - Tooltip element must be `pointer-events: none`.\n     - On hover, if `isETF` then hide\u002Fkeep hidden and do not show anything; otherwise show ticker + full name + sector.\n\n7. **(If required by the task) visibly use `indiv-stock\u002F` data**\n   - On hover or selection (non-ETF only), optionally render a lightweight mini line chart \u002F sparkline for that ticker using `data\u002Findiv-stock\u002FTICKER.csv` (embed or lazy-load + cache).\n   - Keep it small and robust: if a file is missing\u002Funparseable, fail gracefully without breaking the page.\n\n8. **Data table + formatting + true two-way linking**\n   - Render all 50 rows with required columns: **Ticker symbol**, **Full company name**, **Sector**, **Market cap** (formatted `T\u002FB\u002FM\u002FK`; ETFs should display `-` or similar).\n   - Implement **one shared selection function** used by both chart and table:\n     - `setSelected(ticker)` stores a single `selectedTicker` and updates:\n       - bubble node class (e.g., `g.node.selected`)\n       - table row class (e.g., `tr.selected`)\n     - Call `setSelected(d.ticker)` from both bubble click and row click (do not maintain separate “highlight” vs “selected” pathways).\n\n9. **Verification (must be executed before considering the build “done”)**\n   - Filesystem (show results in terminal):\n     - `find \u002Froot\u002Foutput -maxdepth 3 -type f` includes `index.html`, `js\u002Fd3.v6.min.js`, `js\u002Fvisualization.js`, `css\u002Fstyle.css`, plus `data\u002Fstock-descriptions.csv`.\n     - `find \u002Froot\u002Foutput\u002Fdata\u002Findiv-stock -maxdepth 1 -type f | wc -l` is 50.\n   - JS sanity:\n     - Run `node --check` on generated JS files.\n   - Interaction checks (manual or scripted):\n     - 50 bubbles + 50 table rows render; legend includes every sector.\n     - Clicking the **bubble OR its ticker label** selects it (label does not block clicks).\n     - Bubble click highlights the matching table row; table row click highlights the matching bubble (single shared selection state).\n     - Tooltip appears only for non-ETFs; ETFs show no tooltip.\n     - Sector clusters are compact\u002Fcentered; collisions prevent overlap.\n\n## Expected Result\nA reproducible, offline-capable D3 **v6** single-page app with the required `\u002Froot\u002Foutput\u002F` file tree populated, where the bubble chart (non-overlapping sector clusters, labels, legends, conditional tooltips) and the 50-row data table are **bidirectionally linked**, and the text labels do not block bubble clicking.\n","## Steps\n1. **Lock requirements + acceptance checks up front (write them into code comments and re-check at the end)**\n   - Confirm required **D3 version (v6)**, required output paths, and required data sources (main CSV + `indiv-stock\u002F` folder).\n   - Create an acceptance checklist that explicitly includes:\n     - Required artifacts exist **on disk** and are referenced locally: `index.html`, `css\u002Fstyle.css`, `js\u002Fd3.v6.min.js`, `js\u002Fvisualization.js`, and `data\u002F` copies.\n     - Bubble **click works even when clicking the ticker text label** (labels must not steal pointer events; click handler must be on the node container\u002Fcircle).\n     - Tooltip shows **ticker + name + sector**, and is **suppressed for ETFs** (ETF rows have missing `marketCap\u002Fcountry\u002Fwebsite`; show nothing for them).\n     - **Two-way linking**: click bubble highlights table row, click row highlights bubble using **one shared selection state** (use the same `.selected` class on both).\n\n2. **Inspect data using only built-in tools (do not assume pandas is installed)**\n   - Use Python’s built-in `csv` module (or `head`, `wc`, `ls`) to confirm:\n     - `stock-descriptions.csv` columns + row count (**expect 50 rows for this dataset**) and which fields are missing for ETFs.\n     - Sector domain (**expect 5 sectors including `ETF`**) and deterministic ordering (e.g., sort sectors alphabetically for stable colors\u002Flegend).\n     - ETF rows (**expect ~10**; spot-check tickers like `SPY`, `VOO`, `QQQ`, `GLD`).\n     - `indiv-stock\u002F` naming convention (`TICKER.csv`) and file count (**expect 50 files**) and one sample file’s columns (e.g., `Date`, `Open\u002FHigh\u002FLow\u002FClose`, `Volume`, `Adjusted Close`).\n   - Identify ETFs deterministically (e.g., missing `marketCap\u002Fcountry\u002Fwebsite`, not just a label) so tooltip suppression and sizing are correct.\n\n3. **Create the `\u002Froot\u002Foutput\u002F` tree and required files early, and prove it with terminal output**\n   - Execute filesystem-writing steps via the terminal tool (don’t just paste commands), and immediately follow them with checks that show up in the trace:\n     - Create required directories: `\u002Froot\u002Foutput\u002Fjs`, `\u002Froot\u002Foutput\u002Fcss`, `\u002Froot\u002Foutput\u002Fdata`, then `ls -ld` them.\n     - Copy input data into `\u002Froot\u002Foutput\u002Fdata\u002F` (including the full `indiv-stock\u002F` directory), then verify with:\n       - `test -f \u002Froot\u002Foutput\u002Fdata\u002Fstock-descriptions.csv`\n       - `test -d \u002Froot\u002Foutput\u002Fdata\u002Findiv-stock`\n       - `ls \u002Froot\u002Foutput\u002Fdata\u002Findiv-stock | wc -l` (should be 50)\n     - Vendor **D3 v6** to `\u002Froot\u002Foutput\u002Fjs\u002Fd3.v6.min.js` (local copy, not CDN at runtime). Prefer copying from an installed `d3` package if available (e.g., `node -p \"require.resolve('d3\u002Fdist\u002Fd3.min.js')\"`) otherwise download it; then verify:\n       - `test -s \u002Froot\u002Foutput\u002Fjs\u002Fd3.v6.min.js` and `wc -c` shows a non-trivial size\n       - The file corresponds to v6 (e.g., search for a `v6.` marker if present, or verify `d3.version` in-browser during manual check).\n     - Create the three app files **right away** (even minimal placeholders first): `\u002Froot\u002Foutput\u002Findex.html`, `\u002Froot\u002Foutput\u002Fjs\u002Fvisualization.js`, `\u002Froot\u002Foutput\u002Fcss\u002Fstyle.css`, then verify they exist and are non-empty with `test -s` and `ls -l`.\n   - When writing files:\n     - Use quoted heredocs: `cat > file \u003C\u003C'EOF' ... EOF` (prevents JS template strings\u002Fbackticks from breaking the shell).\n\n4. **Create an HTML skeleton that supports the required layout and interactivity**\n   - Use a two-column layout (flex\u002Fgrid) for “bubble chart” (left) and “table” (right).\n   - Include:\n     - A chart container (SVG or a div into which the SVG is appended).\n     - A legend container.\n     - A table container.\n     - A tooltip `\u003Cdiv id=\"tooltip\" class=\"tooltip\">\u003C\u002Fdiv>` (CSS toggles `.visible`).\n   - Reference only local assets (no CDN): `css\u002Fstyle.css`, then `js\u002Fd3.v6.min.js`, then `js\u002Fvisualization.js` (use `defer` on the app script if needed).\n\n5. **Load\u002Fprepare data deterministically and offline-friendly**\n   - Prefer approaches that work when opened locally:\n     - If `file:\u002F\u002F` loading is a concern, embed the CSV content at build time and parse via `d3.csvParse(...)`.\n     - If you rely on runtime loading, use relative paths under the output tree (e.g., `data\u002Fstock-descriptions.csv`).\n   - Normalize fields:\n     - `marketCap`: number or `null`\n     - `isETF`: derived from missing `marketCap\u002Fcountry\u002Fwebsite` (drives uniform sizing + tooltip suppression).\n   - Keep ordering stable (e.g., sort by sector then ticker) before binding to marks.\n\n6. **Bubble chart: force clusters by sector, no overlaps, centered clusters, clickable even with labels**\n   - Scales:\n     - Radius: `d3.scaleSqrt` on `marketCap` (ETFs get a uniform radius).\n     - Color: `d3.scaleOrdinal` with **sorted sector domain** and a fixed scheme.\n   - Force simulation:\n     - Use `forceCenter(width\u002F2, height\u002F2)`.\n     - Compute sector target positions **near the center** (compact circle\u002Fgrid), then cluster via `forceX\u002FforceY` so sector groups don’t drift far away.\n     - Use `forceCollide(d => d.r + padding)` to prevent overlaps.\n     - For determinism: set initial `(x,y)` deterministically; run a fixed number of ticks and stop if you don’t need animation.\n   - Rendering pattern that guarantees “clicking text still clicks bubble”:\n     - Create one `\u003Cg class=\"node\">` per stock; append `\u003Ccircle>` then `\u003Ctext>` inside it; on each tick, move the **group** via `transform: translate(x,y)` so circle+label stay aligned.\n     - Attach hover\u002Fclick handlers to the **`g.node` (or the circle)**, never to the text.\n     - Ensure the label never captures clicks: `text.attr('pointer-events', 'none')` (or CSS `.node text{pointer-events:none}`).\n   - Legend:\n     - Build legend entries from `colorScale.domain()` so every sector appears exactly once with its color swatch + name.\n   - Tooltip:\n     - Tooltip element must be `pointer-events: none`.\n     - On hover, if `isETF` then hide\u002Fkeep hidden and do not show anything; otherwise show ticker + full name + sector.\n\n7. **(If required by the task) visibly use `indiv-stock\u002F` data**\n   - On hover or selection (non-ETF only), optionally render a lightweight mini line chart \u002F sparkline for that ticker using `data\u002Findiv-stock\u002FTICKER.csv` (embed or lazy-load + cache).\n   - Keep it small and robust: if a file is missing\u002Funparseable, fail gracefully without breaking the page.\n\n8. **Data table + formatting + true two-way linking**\n   - Render all 50 rows with required columns: **Ticker symbol**, **Full company name**, **Sector**, **Market cap** (formatted `T\u002FB\u002FM\u002FK`; ETFs should display `-` or similar).\n   - Implement **one shared selection function** used by both chart and table:\n     - `setSelected(ticker)` stores a single `selectedTicker` and updates:\n       - bubble node class (e.g., `g.node.selected`)\n       - table row class (e.g., `tr.selected`)\n     - Call `setSelected(d.ticker)` from both bubble click and row click (do not maintain separate “highlight” vs “selected” pathways).\n\n9. **Verification (must be executed before considering the build “done”)**\n   - Filesystem (show results in terminal):\n     - `find \u002Froot\u002Foutput -maxdepth 3 -type f` includes `index.html`, `js\u002Fd3.v6.min.js`, `js\u002Fvisualization.js`, `css\u002Fstyle.css`, plus `data\u002Fstock-descriptions.csv`.\n     - `find \u002Froot\u002Foutput\u002Fdata\u002Findiv-stock -maxdepth 1 -type f | wc -l` is 50.\n   - JS sanity:\n     - Run `node --check` on generated JS files.\n   - Interaction checks (manual or scripted):\n     - 50 bubbles + 50 table rows render; legend includes every sector.\n     - Clicking the **bubble OR its ticker label** selects it (label does not block clicks).\n     - Bubble click highlights the matching table row; table row click highlights the matching bubble (single shared selection state).\n     - Tooltip appears only for non-ETFs; ETFs show no tooltip.\n     - Sector clusters are compact\u002Fcentered; collisions prevent overlap.\n\n## Expected Result\nA reproducible, offline-capable D3 **v6** single-page app with the required `\u002Froot\u002Foutput\u002F` file tree populated, where the bubble chart (non-overlapping sector clusters, labels, legends, conditional tooltips) and the 50-row data table are **bidirectionally linked**, and the text labels do not block bubble clicking.\n",{"name":5,"description":7},"main","cdcb6d230f3b15c3c33f8a2bdd16439f43602cbe","controlled-skill-repair-experiments\u002Fresult\u002Fmmg2skill-gpt5.2-xhigh\u002Fcandidates\u002Flocation-data-to-d3\u002Fround-3\u002Fskills\u002Fd3-visualization",1,"https:\u002F\u002Fgithub.com\u002Flinyouxue\u002Fskill-repair-benchmark","https:\u002F\u002Fgithub.com\u002Flinyouxue","2026-11-14 20:28:35",{"source":8,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add linyouxue\u002Fskill-repair-benchmark --skill d3-visualization",{"tool":37,"command":38},"bunx","bunx skills add linyouxue\u002Fskill-repair-benchmark --skill d3-visualization",{"tool":40,"command":41},"pnpm","pnpm dlx skills add linyouxue\u002Fskill-repair-benchmark --skill d3-visualization","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flinyouxue\u002Fskill-repair-benchmark\u002Fblob\u002Fmain\u002Fcontrolled-skill-repair-experiments\u002Fresult\u002Fmmg2skill-gpt5.2-xhigh\u002Fcandidates\u002Flocation-data-to-d3\u002Fround-3\u002Fskills\u002Fd3-visualization\u002FSKILL.md",true,[45,51,55,59],{"path":46,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":49,"sourceHtmlUrl":50},"scripts\u002Fbubble_chart_example.js","SCRIPT","脚本",3679,"https:\u002F\u002Fgithub.com\u002Flinyouxue\u002Fskill-repair-benchmark\u002Fblob\u002Fmain\u002Fcontrolled-skill-repair-experiments\u002Fresult\u002Fmmg2skill-gpt5.2-xhigh\u002Fcandidates\u002Flocation-data-to-d3\u002Fround-3\u002Fskills\u002Fd3-visualization\u002Fscripts\u002Fbubble_chart_example.js",{"path":52,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":53,"sourceHtmlUrl":54},"scripts\u002Fcheck_tooltip.js",1752,"https:\u002F\u002Fgithub.com\u002Flinyouxue\u002Fskill-repair-benchmark\u002Fblob\u002Fmain\u002Fcontrolled-skill-repair-experiments\u002Fresult\u002Fmmg2skill-gpt5.2-xhigh\u002Fcandidates\u002Flocation-data-to-d3\u002Fround-3\u002Fskills\u002Fd3-visualization\u002Fscripts\u002Fcheck_tooltip.js",{"path":56,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":57,"sourceHtmlUrl":58},"scripts\u002Finteractive_table_example.js",4439,"https:\u002F\u002Fgithub.com\u002Flinyouxue\u002Fskill-repair-benchmark\u002Fblob\u002Fmain\u002Fcontrolled-skill-repair-experiments\u002Fresult\u002Fmmg2skill-gpt5.2-xhigh\u002Fcandidates\u002Flocation-data-to-d3\u002Fround-3\u002Fskills\u002Fd3-visualization\u002Fscripts\u002Finteractive_table_example.js",{"path":60,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":61,"sourceHtmlUrl":62},"scripts\u002Ftooltip_handler.js",5741,"https:\u002F\u002Fgithub.com\u002Flinyouxue\u002Fskill-repair-benchmark\u002Fblob\u002Fmain\u002Fcontrolled-skill-repair-experiments\u002Fresult\u002Fmmg2skill-gpt5.2-xhigh\u002Fcandidates\u002Flocation-data-to-d3\u002Fround-3\u002Fskills\u002Fd3-visualization\u002Fscripts\u002Ftooltip_handler.js",[64,71,78,85,90,95],{"skillNo":65,"name":66,"nameZh":6,"description":67,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":68,"categories":69,"keywords":70,"publishedAt":19},"01M7E1HGVRY73NBJ022CJG13X6","video-frame-extraction","Extract frames from video files and save them as images using OpenCV","https:\u002F\u002Fgithub.com\u002Flinyouxue\u002Fskill-repair-benchmark\u002Fblob\u002Fmain\u002Fjpg-ocr-stat\u002Fresult\u002Fskilltta-claude4.7\u002Fgroup_03\u002Frun_03\u002Finputs\u002Fskills\u002Fvideo-frame-extraction\u002FSKILL.md",[],[],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":19},"01M7E1HAG5R7CJ9C8NYJS771MB","openai-vision","Analyze images and multi-frame sequences using OpenAI GPT vision models","https:\u002F\u002Fgithub.com\u002Flinyouxue\u002Fskill-repair-benchmark\u002Fblob\u002Fmain\u002Fjpg-ocr-stat\u002Fresult\u002Fskilltta-claude4.7\u002Fgroup_03\u002Frun_03\u002Finputs\u002Fskills\u002Fopenai-vision\u002FSKILL.md",[],[],{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":19},"01M7E1H7DADKB6QBWKC2KQ63SZ","image-ocr","Extract text content from images using Tesseract OCR via Python, including structured field extraction from receipts and forms","https:\u002F\u002Fgithub.com\u002Flinyouxue\u002Fskill-repair-benchmark\u002Fblob\u002Fmain\u002Fjpg-ocr-stat\u002Fresult\u002Fskilltta-claude4.7\u002Fgroup_03\u002Frun_03\u002Finputs\u002Fskills\u002Fimage-ocr\u002FSKILL.md",[],[],{"skillNo":86,"name":66,"nameZh":6,"description":67,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":19},"01M7E1H0WBNT43TENGQY7AVZHD","https:\u002F\u002Fgithub.com\u002Flinyouxue\u002Fskill-repair-benchmark\u002Fblob\u002Fmain\u002Fjpg-ocr-stat\u002Fresult\u002Fskilltta-claude4.7\u002Fgroup_03\u002Frun_02\u002Finputs\u002Fskills\u002Fvideo-frame-extraction\u002FSKILL.md",[],[],{"skillNo":91,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":94,"publishedAt":19},"01M7E1GTC7D4N4Q2EF03875J9E","https:\u002F\u002Fgithub.com\u002Flinyouxue\u002Fskill-repair-benchmark\u002Fblob\u002Fmain\u002Fjpg-ocr-stat\u002Fresult\u002Fskilltta-claude4.7\u002Fgroup_03\u002Frun_02\u002Finputs\u002Fskills\u002Fopenai-vision\u002FSKILL.md",[],[],{"skillNo":96,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":19},"01M7E1GQ92CWFMGH53KSSE4WER","https:\u002F\u002Fgithub.com\u002Flinyouxue\u002Fskill-repair-benchmark\u002Fblob\u002Fmain\u002Fjpg-ocr-stat\u002Fresult\u002Fskilltta-claude4.7\u002Fgroup_03\u002Frun_02\u002Finputs\u002Fskills\u002Fimage-ocr\u002FSKILL.md",[],[]]