[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7AYVG0PR0HRE74MSDGPHZZS":3,"skill-same:01M7AYVG0PR0HRE74MSDGPHZZS":85},{"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":14,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":29,"ownerDescription":6,"updatedAt":30,"install":31,"resources":44},"01M7AYVG0PR0HRE74MSDGPHZZS","Data Visualization",null,"Produce a chart, graph, dashboard, or any data visualization that reads as one system — elegant, accessible, and consistent in light and dark — BRAND-NEUTRAL, shipping a placeholder palette to swap for your own. Read this BEFORE generating ANY chart (bar, line, area, heatmap, scatter, sparkline, donut), choosing chart colors, building a stat tile \u002F meter \u002F KPI row, or laying out a dashboard. Teaches a design-system-AGNOSTIC method: a form heuristic, a color formula with a runnable validator, mark specs, and interaction rules. The method is invariant; a design system plugs in its own ramps and surfaces. A validated default palette is documented in `references\u002Fpalette.md` — swap that file's values for your brand's. Triggers on: \"chart\", \"graph\", \"plot\", \"data viz\", \"dashboard\", \"analytics\", \"visualize data\", \"categorical colors\", \"sequential \u002F diverging palette\", \"stat tile\", \"sparkline\", \"heatmap\", \"legend\", \"axis\", \"tooltip\", \"chart colors\", \"color by series\".","Neuroca-Inc\u002FPerfect_Prompts","Neuroca-Inc","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F227924653?v=4","01M7AYTSB99MRF8RXN50Y6VMD1","Neuroca, Inc.","01M7AYTSCPQYMAXNT4M4YYE3CS",0,"MIT","https:\u002F\u002Fgithub.com\u002FNeuroca-Inc\u002FPerfect_Prompts\u002Fblob\u002Fmain\u002FPrompts\u002FSystem_Prompts_Leaks\u002FAnthropic\u002Fclaude-code\u002Fskills\u002Fdataviz\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: Data Visualization\ndescription: >\n  Produce a chart, graph, dashboard, or any data visualization that reads as one\n  system — elegant, accessible, and consistent in light and dark — BRAND-NEUTRAL,\n  shipping a placeholder palette to swap for your own. Read this BEFORE generating\n  ANY chart (bar, line, area, heatmap, scatter,\n  sparkline, donut), choosing chart colors, building a stat tile \u002F meter \u002F KPI row,\n  or laying out a dashboard. Teaches a design-system-AGNOSTIC method: a form\n  heuristic, a color formula with a runnable validator, mark specs, and interaction\n  rules. The method is invariant; a design system plugs in its own ramps and\n  surfaces. A validated default palette is documented in `references\u002Fpalette.md`\n  — swap that file's values for your brand's. Triggers on: \"chart\", \"graph\", \"plot\", \"data viz\", \"dashboard\",\n  \"analytics\", \"visualize data\", \"categorical colors\", \"sequential \u002F diverging\n  palette\", \"stat tile\", \"sparkline\", \"heatmap\", \"legend\", \"axis\", \"tooltip\",\n  \"chart colors\", \"color by series\".\n---\n\n# Data Visualization\n\nA chart is **read by people and executed by you**. This skill turns \"make it look\ngood\" into a procedure with checks, so the result is right by construction rather\nthan by taste.\n\n**The method here is design-system-agnostic.** Nothing in the procedure, the form\nheuristic, the six checks, or the mark specs is specific to one product. A design\nsystem supplies a small set of *parameters* (its ramps, a categorical order, a\ndiverging pair, a status palette, a texture, its surfaces, its filter components);\nthe method consumes them unchanged. A **validated default palette** is the\nreference instance, fully specified in `references\u002Fpalette.md`. To target your\nbrand, read that file's structure and substitute its values — touch nothing else.\n\n> The single most important habit: **the color part is computable, so compute it.**\n> Never eyeball whether a palette is colorblind-safe — run `scripts\u002Fvalidate_palette.js`.\n\n## The procedure — do these in order\n\nColor comes LAST. Most bad charts pick colors first.\n\n1. **Pick the form.** What is the data's job — magnitude, identity, polarity, a\n   single headline, change-over-time? The job picks the chart type, and sometimes\n   the answer is *not a chart* (a stat tile or hero number). → `references\u002Fchoosing-a-form.md`\n2. **Assign color by the job it does.** Categorical (identity), sequential\n   (magnitude), diverging (polarity), or status (state) — each has one rule.\n   Assign categorical hues in fixed order, never cycled. → `references\u002Fcolor-formula.md`\n3. **VALIDATE the palette — run the script, don't reason about ΔE.**\n   `node scripts\u002Fvalidate_palette.js \"\u003Chex,hex,…>\" --mode light` (relative to\n   this skill's base directory — or load it as `\u003Cscript type=\"module\">` in the\n   chart's own page, where it reads\n   `data-palette` off `\u003Cbody>` and logs a `console.table` report). It returns\n   pass\u002Ffail on the lightness band, chroma floor, adjacent-pair CVD separation,\n   the normal-vision floor, and contrast. Fix anything that FAILs before continuing. Re-run for\n   `--mode dark` with that mode's surface.\n4. **Apply mark specs & spacers.** Thin marks, 4px rounded data-ends anchored to\n   the baseline, 2px lines, ≥8px markers, a 2px surface gap between fills (stacked\n   segments and adjacent bars alike) and a 2px surface ring on overlapping marks,\n   selective direct labels. → `references\u002Fmarks-and-anatomy.md`\n5. **Add the hover layer — by default.** An HTML\u002FSVG chart *is* interactive; ship\n   a crosshair+tooltip on line\u002Farea and a per-mark hover tooltip on bar\u002Fdot\u002Fcell.\n   The only form that skips it is a bare stat tile with no plot. Hit targets bigger\n   than the mark; filters in one row above the charts. → `references\u002Finteraction.md`\n6. **Final accessibility pass.** For ≥ 2 series a legend is always present and ≤ 4\n   are also direct-labeled (a single series needs no legend box — the title names\n   it), so identity is never color-alone; a table view exists; dark mode is **selected** — its own\n   steps from the same ramps, validated against the dark surface, not an automatic\n   flip; texture is available for the CVD\u002Fprint\u002Fforced-colors case.\n7. **Render it and look at it.** The validator checks color, not layout — open or\n   screenshot the output and eyeball it for label collisions, geometry, and overflow\n   before calling it done.\n\nThen check the result against **`references\u002Fanti-patterns.md`** — it is the catalog\nof what goes wrong. If your chart matches an entry, it's wrong.\n\n## Non-negotiables (true in every design system)\n\n- **Assign categorical hues in fixed order, never cycled.** A 9th series is never a\n  generated hue — it folds into \"Other,\" small multiples, or composite encoding.\n- **One axis.** Never a dual-axis chart (two y-scales). Two measures of different\n  scale → two charts, small multiples, or indexed to a common base. *(This is the\n  #1 chart mistake — see anti-patterns.)*\n- **Color follows the entity, never its rank.** A filter that changes the series\n  count must not repaint the survivors.\n- **Sequential = one hue, light→dark. Diverging = two hues + a neutral gray\n  midpoint.** Never a rainbow; never a hue at the diverging midpoint.\n- **Run the validator before shipping any categorical palette.** CVD ΔE ≥ 8 is the\n  target (OKLab ×100); 6–8 is a floor that is legal ONLY with secondary encoding. A\n  normal-vision floor below 15 is a hard FAIL — full-color readers can't tell the\n  pair apart; re-step it on the adjacent pairlist (secondary encoding does not excuse\n  this one); under `--pairs all` cut series or facet instead — see check 4. A contrast WARN\n  obligates visible labels or a table view — it is not dismissable.\n- **Thin marks; a legend always present for ≥ 2 series (none for one), with\n  selective direct labels (never a number on every point); recessive grid\u002Faxes.**\n- **Text wears text tokens, never the series color** — values, labels, and legends\n  stay in primary\u002Fsecondary\u002Fmuted ink; a colored mark beside them carries identity.\n- **Status colors are reserved** (good\u002Fwarning\u002Fserious\u002Fcritical) and never reused\n  for \"series 4\"; they ship with an icon + label, never color alone.\n\n## Plugging in a design system\n\nThe method is invariant; only these parameters change per system. The reference\ninstance — every value filled in — is `references\u002Fpalette.md`.\n\n| Parameter | What the system provides |\n|---|---|\n| **Ramps** | the hue scales (named steps) the palette draws from |\n| **Categorical theme** | the fixed hue order (a named theme); default + alternates |\n| **Sequential hue** | the default single hue for magnitude |\n| **Diverging pair** | two warm\u002Fcool poles + a neutral midpoint |\n| **Status palette** | good \u002F warning \u002F serious \u002F critical — steps distinct from categorical |\n| **Texture fill** | one directional hand-drawn fill, used at 45° \u002F 135° |\n| **Surfaces** | light & dark chart-surface colors (the validator needs these) |\n| **Filter controls** | date-range & dimension controls (behavioral spec in `interaction.md`) |\n\nTo onboard a new system: fill those rows, feed its ramps to the validator, and let\nit snap each slot to the nearest passing step. Structure and rules stay as written.\n\n## Reference files\n\n| File | What it answers |\n|------|-----------------|\n| `references\u002Fchoosing-a-form.md` | Which chart type \u002F is it even a chart? |\n| `references\u002Fcolor-formula.md` | The four jobs, the six checks, snap-to-passing |\n| `references\u002Fmarks-and-anatomy.md` | Mark specs, spacers, labels, figures, hero number |\n| `references\u002Finteraction.md` | Tooltips & hover, filters & time ranges |\n| `references\u002Fcomponents.md` | The pieces a chart is made of — build each in plain HTML |\n| `references\u002Fanti-patterns.md` | **What goes wrong — check every chart against this** |\n| `references\u002Fpalette.md` | **The reference palette instance** — every parameter, filled in; swap for your brand's |\n| `scripts\u002Fvalidate_palette.js` | Runnable six-checks validator (run it; don't eyeball) |\n","# Data Visualization\n\nA chart is **read by people and executed by you**. This skill turns \"make it look\ngood\" into a procedure with checks, so the result is right by construction rather\nthan by taste.\n\n**The method here is design-system-agnostic.** Nothing in the procedure, the form\nheuristic, the six checks, or the mark specs is specific to one product. A design\nsystem supplies a small set of *parameters* (its ramps, a categorical order, a\ndiverging pair, a status palette, a texture, its surfaces, its filter components);\nthe method consumes them unchanged. A **validated default palette** is the\nreference instance, fully specified in `references\u002Fpalette.md`. To target your\nbrand, read that file's structure and substitute its values — touch nothing else.\n\n> The single most important habit: **the color part is computable, so compute it.**\n> Never eyeball whether a palette is colorblind-safe — run `scripts\u002Fvalidate_palette.js`.\n\n## The procedure — do these in order\n\nColor comes LAST. Most bad charts pick colors first.\n\n1. **Pick the form.** What is the data's job — magnitude, identity, polarity, a\n   single headline, change-over-time? The job picks the chart type, and sometimes\n   the answer is *not a chart* (a stat tile or hero number). → `references\u002Fchoosing-a-form.md`\n2. **Assign color by the job it does.** Categorical (identity), sequential\n   (magnitude), diverging (polarity), or status (state) — each has one rule.\n   Assign categorical hues in fixed order, never cycled. → `references\u002Fcolor-formula.md`\n3. **VALIDATE the palette — run the script, don't reason about ΔE.**\n   `node scripts\u002Fvalidate_palette.js \"\u003Chex,hex,…>\" --mode light` (relative to\n   this skill's base directory — or load it as `\u003Cscript type=\"module\">` in the\n   chart's own page, where it reads\n   `data-palette` off `\u003Cbody>` and logs a `console.table` report). It returns\n   pass\u002Ffail on the lightness band, chroma floor, adjacent-pair CVD separation,\n   the normal-vision floor, and contrast. Fix anything that FAILs before continuing. Re-run for\n   `--mode dark` with that mode's surface.\n4. **Apply mark specs & spacers.** Thin marks, 4px rounded data-ends anchored to\n   the baseline, 2px lines, ≥8px markers, a 2px surface gap between fills (stacked\n   segments and adjacent bars alike) and a 2px surface ring on overlapping marks,\n   selective direct labels. → `references\u002Fmarks-and-anatomy.md`\n5. **Add the hover layer — by default.** An HTML\u002FSVG chart *is* interactive; ship\n   a crosshair+tooltip on line\u002Farea and a per-mark hover tooltip on bar\u002Fdot\u002Fcell.\n   The only form that skips it is a bare stat tile with no plot. Hit targets bigger\n   than the mark; filters in one row above the charts. → `references\u002Finteraction.md`\n6. **Final accessibility pass.** For ≥ 2 series a legend is always present and ≤ 4\n   are also direct-labeled (a single series needs no legend box — the title names\n   it), so identity is never color-alone; a table view exists; dark mode is **selected** — its own\n   steps from the same ramps, validated against the dark surface, not an automatic\n   flip; texture is available for the CVD\u002Fprint\u002Fforced-colors case.\n7. **Render it and look at it.** The validator checks color, not layout — open or\n   screenshot the output and eyeball it for label collisions, geometry, and overflow\n   before calling it done.\n\nThen check the result against **`references\u002Fanti-patterns.md`** — it is the catalog\nof what goes wrong. If your chart matches an entry, it's wrong.\n\n## Non-negotiables (true in every design system)\n\n- **Assign categorical hues in fixed order, never cycled.** A 9th series is never a\n  generated hue — it folds into \"Other,\" small multiples, or composite encoding.\n- **One axis.** Never a dual-axis chart (two y-scales). Two measures of different\n  scale → two charts, small multiples, or indexed to a common base. *(This is the\n  #1 chart mistake — see anti-patterns.)*\n- **Color follows the entity, never its rank.** A filter that changes the series\n  count must not repaint the survivors.\n- **Sequential = one hue, light→dark. Diverging = two hues + a neutral gray\n  midpoint.** Never a rainbow; never a hue at the diverging midpoint.\n- **Run the validator before shipping any categorical palette.** CVD ΔE ≥ 8 is the\n  target (OKLab ×100); 6–8 is a floor that is legal ONLY with secondary encoding. A\n  normal-vision floor below 15 is a hard FAIL — full-color readers can't tell the\n  pair apart; re-step it on the adjacent pairlist (secondary encoding does not excuse\n  this one); under `--pairs all` cut series or facet instead — see check 4. A contrast WARN\n  obligates visible labels or a table view — it is not dismissable.\n- **Thin marks; a legend always present for ≥ 2 series (none for one), with\n  selective direct labels (never a number on every point); recessive grid\u002Faxes.**\n- **Text wears text tokens, never the series color** — values, labels, and legends\n  stay in primary\u002Fsecondary\u002Fmuted ink; a colored mark beside them carries identity.\n- **Status colors are reserved** (good\u002Fwarning\u002Fserious\u002Fcritical) and never reused\n  for \"series 4\"; they ship with an icon + label, never color alone.\n\n## Plugging in a design system\n\nThe method is invariant; only these parameters change per system. The reference\ninstance — every value filled in — is `references\u002Fpalette.md`.\n\n| Parameter | What the system provides |\n|---|---|\n| **Ramps** | the hue scales (named steps) the palette draws from |\n| **Categorical theme** | the fixed hue order (a named theme); default + alternates |\n| **Sequential hue** | the default single hue for magnitude |\n| **Diverging pair** | two warm\u002Fcool poles + a neutral midpoint |\n| **Status palette** | good \u002F warning \u002F serious \u002F critical — steps distinct from categorical |\n| **Texture fill** | one directional hand-drawn fill, used at 45° \u002F 135° |\n| **Surfaces** | light & dark chart-surface colors (the validator needs these) |\n| **Filter controls** | date-range & dimension controls (behavioral spec in `interaction.md`) |\n\nTo onboard a new system: fill those rows, feed its ramps to the validator, and let\nit snap each slot to the nearest passing step. Structure and rules stay as written.\n\n## Reference files\n\n| File | What it answers |\n|------|-----------------|\n| `references\u002Fchoosing-a-form.md` | Which chart type \u002F is it even a chart? |\n| `references\u002Fcolor-formula.md` | The four jobs, the six checks, snap-to-passing |\n| `references\u002Fmarks-and-anatomy.md` | Mark specs, spacers, labels, figures, hero number |\n| `references\u002Finteraction.md` | Tooltips & hover, filters & time ranges |\n| `references\u002Fcomponents.md` | The pieces a chart is made of — build each in plain HTML |\n| `references\u002Fanti-patterns.md` | **What goes wrong — check every chart against this** |\n| `references\u002Fpalette.md` | **The reference palette instance** — every parameter, filled in; swap for your brand's |\n| `scripts\u002Fvalidate_palette.js` | Runnable six-checks validator (run it; don't eyeball) |\n",{"name":5,"description":7},"main","b86642797c67dbc6f00765d1fbc8cc2025829662","Prompts\u002FSystem_Prompts_Leaks\u002FAnthropic\u002Fclaude-code\u002Fskills\u002Fdataviz","https:\u002F\u002Fgithub.com\u002FNeuroca-Inc\u002FPerfect_Prompts","https:\u002F\u002Fgithub.com\u002FNeuroca-Inc","https:\u002F\u002Fwww.neuroca.ai","2026-08-24 21:08:50",{"source":8,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add Neuroca-Inc\u002FPerfect_Prompts --skill \"Data Visualization\"",{"tool":37,"command":38},"bunx","bunx skills add Neuroca-Inc\u002FPerfect_Prompts --skill \"Data Visualization\"",{"tool":40,"command":41},"pnpm","pnpm dlx skills add Neuroca-Inc\u002FPerfect_Prompts --skill \"Data Visualization\"","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FNeuroca-Inc\u002FPerfect_Prompts\u002Fblob\u002Fmain\u002FPrompts\u002FSystem_Prompts_Leaks\u002FAnthropic\u002Fclaude-code\u002Fskills\u002Fdataviz\u002FSKILL.md",true,[45,51,55,59,63,67,71,75,81],{"path":46,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":49,"sourceHtmlUrl":50},"references\u002Fanti-patterns.md","REFERENCE","参考文档",6098,"https:\u002F\u002Fgithub.com\u002FNeuroca-Inc\u002FPerfect_Prompts\u002Fblob\u002Fmain\u002FPrompts\u002FSystem_Prompts_Leaks\u002FAnthropic\u002Fclaude-code\u002Fskills\u002Fdataviz\u002Freferences\u002Fanti-patterns.md",{"path":52,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":53,"sourceHtmlUrl":54},"references\u002Fchoosing-a-form.md",3104,"https:\u002F\u002Fgithub.com\u002FNeuroca-Inc\u002FPerfect_Prompts\u002Fblob\u002Fmain\u002FPrompts\u002FSystem_Prompts_Leaks\u002FAnthropic\u002Fclaude-code\u002Fskills\u002Fdataviz\u002Freferences\u002Fchoosing-a-form.md",{"path":56,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":57,"sourceHtmlUrl":58},"references\u002Fcolor-formula.md",8235,"https:\u002F\u002Fgithub.com\u002FNeuroca-Inc\u002FPerfect_Prompts\u002Fblob\u002Fmain\u002FPrompts\u002FSystem_Prompts_Leaks\u002FAnthropic\u002Fclaude-code\u002Fskills\u002Fdataviz\u002Freferences\u002Fcolor-formula.md",{"path":60,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":61,"sourceHtmlUrl":62},"references\u002Fcomponents.md",2142,"https:\u002F\u002Fgithub.com\u002FNeuroca-Inc\u002FPerfect_Prompts\u002Fblob\u002Fmain\u002FPrompts\u002FSystem_Prompts_Leaks\u002FAnthropic\u002Fclaude-code\u002Fskills\u002Fdataviz\u002Freferences\u002Fcomponents.md",{"path":64,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":65,"sourceHtmlUrl":66},"references\u002Finteraction.md",3767,"https:\u002F\u002Fgithub.com\u002FNeuroca-Inc\u002FPerfect_Prompts\u002Fblob\u002Fmain\u002FPrompts\u002FSystem_Prompts_Leaks\u002FAnthropic\u002Fclaude-code\u002Fskills\u002Fdataviz\u002Freferences\u002Finteraction.md",{"path":68,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":69,"sourceHtmlUrl":70},"references\u002Fmarks-and-anatomy.md",6088,"https:\u002F\u002Fgithub.com\u002FNeuroca-Inc\u002FPerfect_Prompts\u002Fblob\u002Fmain\u002FPrompts\u002FSystem_Prompts_Leaks\u002FAnthropic\u002Fclaude-code\u002Fskills\u002Fdataviz\u002Freferences\u002Fmarks-and-anatomy.md",{"path":72,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":73,"sourceHtmlUrl":74},"references\u002Fpalette.md",9069,"https:\u002F\u002Fgithub.com\u002FNeuroca-Inc\u002FPerfect_Prompts\u002Fblob\u002Fmain\u002FPrompts\u002FSystem_Prompts_Leaks\u002FAnthropic\u002Fclaude-code\u002Fskills\u002Fdataviz\u002Freferences\u002Fpalette.md",{"path":76,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":79,"sourceHtmlUrl":80},"scripts\u002Fvalidate_palette.js","SCRIPT","脚本",18491,"https:\u002F\u002Fgithub.com\u002FNeuroca-Inc\u002FPerfect_Prompts\u002Fblob\u002Fmain\u002FPrompts\u002FSystem_Prompts_Leaks\u002FAnthropic\u002Fclaude-code\u002Fskills\u002Fdataviz\u002Fscripts\u002Fvalidate_palette.js",{"path":82,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":83,"sourceHtmlUrl":84},"scripts\u002Fvalidate_palette.py",16259,"https:\u002F\u002Fgithub.com\u002FNeuroca-Inc\u002FPerfect_Prompts\u002Fblob\u002Fmain\u002FPrompts\u002FSystem_Prompts_Leaks\u002FAnthropic\u002Fclaude-code\u002Fskills\u002Fdataviz\u002Fscripts\u002Fvalidate_palette.py",[86,93,100,107,116,122],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":19},"01M7AZ411KKTF445RVBJ76MMXZ","{{SKILL_ID}}","{{ONE_SENTENCE_ACTIVATION_DESCRIPTION}}","https:\u002F\u002Fgithub.com\u002FNeuroca-Inc\u002FPerfect_Prompts\u002Fblob\u002Fmain\u002FStandards\u002FTemplates\u002FSKILL_TEMPLATE_v1.0_20260822\u002FSKILL.md",[],[],{"skillNo":94,"name":95,"nameZh":6,"description":96,"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},"01M7AZ3NGM1XAZESN0CFVY0JXH","session-handoff","Generate rigorous, multi-artifact session handoff packages that preserve full context for zero-loss context switching between AI sessions. Use this skill whenever the user asks to: save session state, create a handoff, package context for a new session, summarize and preserve a conversation for later, do a session dump, create a context transfer, prepare a state snapshot, export session knowledge, hand off to another agent, persist session memory, \"wrap up\" or \"save where we are\", create a knowledge package, synthesize session context, or produce a resumption artifact. Also trigger when the user says things like \"save this for next time\", \"capture everything we discussed\", \"I need to pick this up later\", \"package this session\", \"make sure nothing is lost\", \"create a handoff document\", \"session export\", \"context preservation\", or any variant of persisting conversational and working state. Even if the user just says \"handoff\" or \"save state\" — use this skill.","https:\u002F\u002Fgithub.com\u002FNeuroca-Inc\u002FPerfect_Prompts\u002Fblob\u002Fmain\u002FSkills\u002Fsession_handoff_skill\u002FSKILL.md",[],[],{"skillNo":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":106,"publishedAt":19},"01M7AZ3BVYS86JM0M0HWWVV2BC","vdm-publication-bundle","Generate, audit, and validate complete VDM research bundles following theorem-bearing manuscript standards. Use this skill when the user wants to: create a research bundle, Lean4 package from formal claims, SymPy adversarial symbolic audit script, a skeptical-reviewer Jupyter notebook, score papers w\u002F CRAFT\u002FBASS review metrics, audit burden coverage, generate SHA256 manifests, create figures following standards, scaffold a new Complete Formalism publication from claims, or check whether existing bundles meet certificate requirements. Also trigger when the user mentions \"publication bundle\",\"validation bundle\",\"CRAFT score\",\"BASS score\",\"burden coverage\",\"claim attack\",\"gate check\",\"reviewer notebook\",\"adversarial audit\",\"publication certificate\",\"closure certificate\",\"artifact manifest\", \"figure standards\", \"review-ready\", or any CF\u002FCFN publication workflow. Even if the user just says \"score this paper\"\u002F\"check if this is publication-ready\", use this skill.","https:\u002F\u002Fgithub.com\u002FNeuroca-Inc\u002FPerfect_Prompts\u002Fblob\u002Fmain\u002FSkills\u002Frigorous_research\u002FSKILL.md",[],[],{"skillNo":108,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":111,"licenseFileUrl":112,"sourceHtmlUrl":113,"categories":114,"keywords":115,"publishedAt":19},"01M7AZ380339DJMS208D1E3YZ8","pdf","Use when tasks involve reading, creating, or reviewing PDF files where rendering and layout matter; prefer visual checks by rendering pages (Poppler) and use Python tools such as `reportlab`, `pdfplumber`, and `pypdf` for generation and extraction.","Apache-2.0","https:\u002F\u002Fgithub.com\u002FNeuroca-Inc\u002FPerfect_Prompts\u002Fblob\u002Fmain\u002FSkills\u002Fpdf\u002Fpdf_skill\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002FNeuroca-Inc\u002FPerfect_Prompts\u002Fblob\u002Fmain\u002FSkills\u002Fpdf\u002Fpdf_skill\u002FSKILL.md",[],[],{"skillNo":117,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":111,"licenseFileUrl":118,"sourceHtmlUrl":119,"categories":120,"keywords":121,"publishedAt":19},"01M7AZ33T1W54V1MK3Q3Z6PC0F","https:\u002F\u002Fgithub.com\u002FNeuroca-Inc\u002FPerfect_Prompts\u002Fblob\u002Fmain\u002FSkills\u002Fpdf\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002FNeuroca-Inc\u002FPerfect_Prompts\u002Fblob\u002Fmain\u002FSkills\u002Fpdf\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":15,"licenseFileUrl":6,"sourceHtmlUrl":126,"categories":127,"keywords":128,"publishedAt":19},"01M7AZ2ZPWTG4W9EYAVMB8E5GN","template-skill","Replace with description of the skill and when Claude should use it.","https:\u002F\u002Fgithub.com\u002FNeuroca-Inc\u002FPerfect_Prompts\u002Fblob\u002Fmain\u002FSkills\u002Fofficial-anthropic-skills\u002Ftemplate\u002FSKILL.md",[],[]]