[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7CFGG7NM5X15MCZAPEPJ6CW":3,"skill-same:01M7CFGG7NM5X15MCZAPEPJ6CW":92},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":15,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":24,"commitSha":25,"skillDirectory":5,"forksCount":26,"repositoryHtmlUrl":27,"repositoryHomepageUrl":28,"ownerHtmlUrl":29,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":30,"install":31,"resources":44},"01M7CFGG7NM5X15MCZAPEPJ6CW","procedural-painter",null,"Paint finished, painterly images entirely with code, with no image model, reference images or downloaded assets. Builds a procedural underpainting (3D geometry, noise landscapes, mirrored water, lights), paints it with curved brush strokes along a style flow field, adds impasto, then inspects and iterates. Use for \"paint X in the style of Y with code\", \"generative painting\", \"no-AI-image artwork\", \"made with Python\" art, or procedural illustrations in post-impressionist, impressionist, ukiyo-e, or Northern Renaissance styles.","getedgehq\u002Fskills","getedgehq","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F327350993?v=4","01M7CEH5YJQYF1PB3MDG9PA5HX","01M7CEH5ZAPY8TX4H3E04KM875",5,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Fgetedgehq\u002Fskills\u002Fblob\u002Fmain\u002Fprocedural-painter\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fgetedgehq\u002Fskills\u002Fblob\u002Fmain\u002Fprocedural-painter\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: procedural-painter\ndescription: >-\n  Paint finished, painterly images entirely with code, with no image model, reference\n  images or downloaded assets. Builds a procedural underpainting (3D geometry, noise\n  landscapes, mirrored water, lights), paints it with curved brush strokes along a\n  style flow field, adds impasto, then inspects and iterates. Use for \"paint X in the\n  style of Y with code\", \"generative painting\", \"no-AI-image artwork\", \"made with\n  Python\" art, or procedural illustrations in post-impressionist, impressionist,\n  ukiyo-e, or Northern Renaissance styles.\n---\n\n# Procedural Painter\n\nCreate a finished painterly image entirely through code.\n\n## Core constraint\n\nThe final artwork must be rendered from code.\n\nDo not:\n- call an image-generation API or model\n- download or use reference images, textures, stock art, or external visual assets\n- trace an existing artwork\n- hide image assets inside base64 or package files\n\nUse Python with NumPy, SciPy and Pillow. Nothing else is needed.\n\n## Bundled engine (use it, do not rewrite it)\n\n`scripts\u002Fpp\u002F` is a working engine; start from it and a matching example:\n\n- `pp\u002Fcore.py`: fBm value noise, colour ramps and HSV, supersampled masks, pinhole `Camera`.\n- `pp\u002Fbridge.py`: an example 3D landmark model (the Golden Gate Bridge at real proportions) and a\n  box\u002Fcable rasteriser with depth. Model new subjects the same way: boxes, extrusions, curves.\n- `pp\u002Fstrokes.py`: `Painter`, the stroke painter with coarse-to-fine layers, region-bounded\n  strokes, per-region brush limits, colour jitter hooks, a rigger brush (`line`, `dab`), and the\n  impasto finish (LIC bristles plus emboss lighting).\n- `golden_gate_*.py`: four complete paintings, one per style below. Seeds are fixed, so the\n  outputs are byte-identical on rerun. `grid.py` assembles a 2x2.\n\nRun from anywhere: `python3 scripts\u002Fgolden_gate_ukiyoe.py` writes `out\u002Fp3_ukiyoe.png`.\nPass `--under` to any stroke-based example to save only the underpainting (seconds).\n\n## The method: underpainting, then strokes\n\nPainting pixel by pixel with noise produces \"generative art\". What produces a painting is\n**stroke-based rendering over a scene built in code**, the classic Hertzmann (SIGGRAPH '98)\nalgorithm with a code-built scene in place of the photograph it normally needs.\n\n1. **Build the underpainting (the scene).** Render a plain, smooth image of the subject:\n   - Landmarks and architecture: model them in 3D with real proportions (boxes, catenary\n     cables) and project with a pinhole camera. Accurate proportions make the subject\n     instantly recognisable.\n   - Sky, hills, water: gradient ramps plus fBm value noise; ridgelines from 1D fBm.\n   - Water: mirror the scene above the horizon, then displace it with horizontally stretched noise.\n   - Lights: Gaussian glow fields plus vertical reflection streaks.\n   - Keep a **region label map** (sky, water, land, subject, ...) alongside the colours.\n2. **Define a flow field for the style.** A unit vector field for stroke direction:\n   vortices (post-impressionist), diagonal hatching (impressionist), slope-following on\n   hills, horizontal on water, vertical flames for cypresses.\n3. **Paint coarse to fine (Hertzmann).** For each brush radius R, large to small:\n   blur the reference by ~R\u002F2, compute the error against the canvas on a grid of cell size R, and\n   start strokes where the error exceeds a threshold. Trace each stroke along the flow field, blended\n   with the edge tangent where the image gradient is strong, and stop when colour drifts or the\n   **region label changes**, so strokes never bleed across the subject's outline.\n   Per-region min\u002Fmax brush radius keeps the subject crisp and big areas bold.\n4. **Rigger pass.** Re-state thin structure (cables, lamps, figures, branches) with a thin\n   brush after the strokes. Strokes wash out anything thinner than the brush.\n5. **Impasto.** Record a per-stroke height; add bristle streaks with line-integral convolution\n   of noise along the flow field; emboss-light it. That is what makes it read as paint.\n6. **Finish.** Palette\u002Fcontrast pass, varnish tint, craquelure (Voronoi edges) for old-master styles.\n\nVectorise stroke tracing in NumPy (all strokes of one layer step together) and draw with\n`ImageDraw.line(width=2R, joint='curve')`. At 2400×1800, 100k–900k strokes render in 20–170 s.\n\n## Style recipes (tested)\n\n| Style | Scene choice | Strokes | Signature |\n|---|---|---|---|\n| Post-impressionist swirl | low camera, big sky; moon + haloed stars; cypress | R 26→2, maxlen 7–10, sat ×1.3, value jitter 0.16; min R 9 in sky | LIC swirl **bands baked into the sky** so the strokes pick up light and dark ribbons; vortex field |\n| Impressionist broken colour | fog bank, afterglow, mirrored water | short dabs (maxlen 4), R 22→5, hue jitter ≈0.015, 7% warm and 7% cool flecks | depth haze on the subject; keep values close |\n| Ukiyo-e woodblock | Fuji-like peak, moon, framing pine | **no strokes** | flat 2-tone blocks, bokashi ramps, sumi key lines from label borders (skip thin parts), kasumi bands, scalloped waves shrinking toward the horizon, paper fibre, baren mottling, misregistration |\n| Northern Renaissance winter | elevated view, snow slope, hamlet, frozen pond | fine R 12→2, low jitter | many tiny narrative marks (hunters, dogs, skaters, fence, tracks, lit windows, smoke), varnish, faint craquelure |\n\n## Failure modes seen and their fixes\n\n- **Subject unrecognisable**: the camera saw the tower edge-on. Look roughly along the bridge axis so the portals show.\n- **\"Oil filter\" look**: too many small strokes and uniform jitter. Set a minimum brush size in big regions, use longer strokes, and add value variation to the underpainting.\n- **Confetti**: impressionist hue jitter set too high. Keep flecks rare and values close.\n- **Cartoon or vector look**: flat fills with no stroke texture. Always run the impasto pass.\n- **Dead snow and sky**: add narrative marks, cast shadows clipped to the surface, tufts, tracks.\n\n## Workflow\n\n1. Preview the underpainting only (`--under` flag, ~5 s) until composition, horizon and subject size are right.\n2. Paint, then inspect the full frame **and** a 1:1 crop. Do at least two improvement passes.\n3. Deterministic `SEED` in every source; save the PNG next to its source.\n\n## Deliver\n\n- final PNG (≥1600×1200)\n- Python source + seed + dependencies\n- 3–5 bullets on the procedural techniques used\n\n## Quality bar\n\nThe artwork should be visually interesting before the viewer knows it was made with code.\nIf it looks like \"generative art\" rather than a painting, keep iterating.\n","# Procedural Painter\n\nCreate a finished painterly image entirely through code.\n\n## Core constraint\n\nThe final artwork must be rendered from code.\n\nDo not:\n- call an image-generation API or model\n- download or use reference images, textures, stock art, or external visual assets\n- trace an existing artwork\n- hide image assets inside base64 or package files\n\nUse Python with NumPy, SciPy and Pillow. Nothing else is needed.\n\n## Bundled engine (use it, do not rewrite it)\n\n`scripts\u002Fpp\u002F` is a working engine; start from it and a matching example:\n\n- `pp\u002Fcore.py`: fBm value noise, colour ramps and HSV, supersampled masks, pinhole `Camera`.\n- `pp\u002Fbridge.py`: an example 3D landmark model (the Golden Gate Bridge at real proportions) and a\n  box\u002Fcable rasteriser with depth. Model new subjects the same way: boxes, extrusions, curves.\n- `pp\u002Fstrokes.py`: `Painter`, the stroke painter with coarse-to-fine layers, region-bounded\n  strokes, per-region brush limits, colour jitter hooks, a rigger brush (`line`, `dab`), and the\n  impasto finish (LIC bristles plus emboss lighting).\n- `golden_gate_*.py`: four complete paintings, one per style below. Seeds are fixed, so the\n  outputs are byte-identical on rerun. `grid.py` assembles a 2x2.\n\nRun from anywhere: `python3 scripts\u002Fgolden_gate_ukiyoe.py` writes `out\u002Fp3_ukiyoe.png`.\nPass `--under` to any stroke-based example to save only the underpainting (seconds).\n\n## The method: underpainting, then strokes\n\nPainting pixel by pixel with noise produces \"generative art\". What produces a painting is\n**stroke-based rendering over a scene built in code**, the classic Hertzmann (SIGGRAPH '98)\nalgorithm with a code-built scene in place of the photograph it normally needs.\n\n1. **Build the underpainting (the scene).** Render a plain, smooth image of the subject:\n   - Landmarks and architecture: model them in 3D with real proportions (boxes, catenary\n     cables) and project with a pinhole camera. Accurate proportions make the subject\n     instantly recognisable.\n   - Sky, hills, water: gradient ramps plus fBm value noise; ridgelines from 1D fBm.\n   - Water: mirror the scene above the horizon, then displace it with horizontally stretched noise.\n   - Lights: Gaussian glow fields plus vertical reflection streaks.\n   - Keep a **region label map** (sky, water, land, subject, ...) alongside the colours.\n2. **Define a flow field for the style.** A unit vector field for stroke direction:\n   vortices (post-impressionist), diagonal hatching (impressionist), slope-following on\n   hills, horizontal on water, vertical flames for cypresses.\n3. **Paint coarse to fine (Hertzmann).** For each brush radius R, large to small:\n   blur the reference by ~R\u002F2, compute the error against the canvas on a grid of cell size R, and\n   start strokes where the error exceeds a threshold. Trace each stroke along the flow field, blended\n   with the edge tangent where the image gradient is strong, and stop when colour drifts or the\n   **region label changes**, so strokes never bleed across the subject's outline.\n   Per-region min\u002Fmax brush radius keeps the subject crisp and big areas bold.\n4. **Rigger pass.** Re-state thin structure (cables, lamps, figures, branches) with a thin\n   brush after the strokes. Strokes wash out anything thinner than the brush.\n5. **Impasto.** Record a per-stroke height; add bristle streaks with line-integral convolution\n   of noise along the flow field; emboss-light it. That is what makes it read as paint.\n6. **Finish.** Palette\u002Fcontrast pass, varnish tint, craquelure (Voronoi edges) for old-master styles.\n\nVectorise stroke tracing in NumPy (all strokes of one layer step together) and draw with\n`ImageDraw.line(width=2R, joint='curve')`. At 2400×1800, 100k–900k strokes render in 20–170 s.\n\n## Style recipes (tested)\n\n| Style | Scene choice | Strokes | Signature |\n|---|---|---|---|\n| Post-impressionist swirl | low camera, big sky; moon + haloed stars; cypress | R 26→2, maxlen 7–10, sat ×1.3, value jitter 0.16; min R 9 in sky | LIC swirl **bands baked into the sky** so the strokes pick up light and dark ribbons; vortex field |\n| Impressionist broken colour | fog bank, afterglow, mirrored water | short dabs (maxlen 4), R 22→5, hue jitter ≈0.015, 7% warm and 7% cool flecks | depth haze on the subject; keep values close |\n| Ukiyo-e woodblock | Fuji-like peak, moon, framing pine | **no strokes** | flat 2-tone blocks, bokashi ramps, sumi key lines from label borders (skip thin parts), kasumi bands, scalloped waves shrinking toward the horizon, paper fibre, baren mottling, misregistration |\n| Northern Renaissance winter | elevated view, snow slope, hamlet, frozen pond | fine R 12→2, low jitter | many tiny narrative marks (hunters, dogs, skaters, fence, tracks, lit windows, smoke), varnish, faint craquelure |\n\n## Failure modes seen and their fixes\n\n- **Subject unrecognisable**: the camera saw the tower edge-on. Look roughly along the bridge axis so the portals show.\n- **\"Oil filter\" look**: too many small strokes and uniform jitter. Set a minimum brush size in big regions, use longer strokes, and add value variation to the underpainting.\n- **Confetti**: impressionist hue jitter set too high. Keep flecks rare and values close.\n- **Cartoon or vector look**: flat fills with no stroke texture. Always run the impasto pass.\n- **Dead snow and sky**: add narrative marks, cast shadows clipped to the surface, tufts, tracks.\n\n## Workflow\n\n1. Preview the underpainting only (`--under` flag, ~5 s) until composition, horizon and subject size are right.\n2. Paint, then inspect the full frame **and** a 1:1 crop. Do at least two improvement passes.\n3. Deterministic `SEED` in every source; save the PNG next to its source.\n\n## Deliver\n\n- final PNG (≥1600×1200)\n- Python source + seed + dependencies\n- 3–5 bullets on the procedural techniques used\n\n## Quality bar\n\nThe artwork should be visually interesting before the viewer knows it was made with code.\nIf it looks like \"generative art\" rather than a painting, keep iterating.\n",{"name":5,"description":7},"main","01960aeb08909dbd0c1a2d4f219cdb300099b8b9",0,"https:\u002F\u002Fgithub.com\u002Fgetedgehq\u002Fskills","https:\u002F\u002Fgetedge.cc","https:\u002F\u002Fgithub.com\u002Fgetedgehq","2026-11-12 10:05:02",{"source":8,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add getedgehq\u002Fskills --skill procedural-painter",{"tool":37,"command":38},"bunx","bunx skills add getedgehq\u002Fskills --skill procedural-painter",{"tool":40,"command":41},"pnpm","pnpm dlx skills add getedgehq\u002Fskills --skill procedural-painter","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fgetedgehq\u002Fskills\u002Fblob\u002Fmain\u002Fprocedural-painter\u002FSKILL.md",true,[45,51,55,61,65,69,73,77,80,84,88],{"path":46,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":49,"sourceHtmlUrl":50},"DERIVATION.json","REFERENCE","参考文档",3250,"https:\u002F\u002Fgithub.com\u002Fgetedgehq\u002Fskills\u002Fblob\u002Fmain\u002Fprocedural-painter\u002FDERIVATION.json",{"path":52,"resourceType":52,"resourceTypeDesc":53,"sizeBytes":54,"sourceHtmlUrl":15},"LICENSE","许可证",10756,{"path":56,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":59,"sourceHtmlUrl":60},"scripts\u002Fgolden_gate_bruegel_winter.py","SCRIPT","脚本",11294,"https:\u002F\u002Fgithub.com\u002Fgetedgehq\u002Fskills\u002Fblob\u002Fmain\u002Fprocedural-painter\u002Fscripts\u002Fgolden_gate_bruegel_winter.py",{"path":62,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":63,"sourceHtmlUrl":64},"scripts\u002Fgolden_gate_impressionist.py",5870,"https:\u002F\u002Fgithub.com\u002Fgetedgehq\u002Fskills\u002Fblob\u002Fmain\u002Fprocedural-painter\u002Fscripts\u002Fgolden_gate_impressionist.py",{"path":66,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":67,"sourceHtmlUrl":68},"scripts\u002Fgolden_gate_post_impressionist.py",10675,"https:\u002F\u002Fgithub.com\u002Fgetedgehq\u002Fskills\u002Fblob\u002Fmain\u002Fprocedural-painter\u002Fscripts\u002Fgolden_gate_post_impressionist.py",{"path":70,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":71,"sourceHtmlUrl":72},"scripts\u002Fgolden_gate_ukiyoe.py",9474,"https:\u002F\u002Fgithub.com\u002Fgetedgehq\u002Fskills\u002Fblob\u002Fmain\u002Fprocedural-painter\u002Fscripts\u002Fgolden_gate_ukiyoe.py",{"path":74,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":75,"sourceHtmlUrl":76},"scripts\u002Fgrid.py",927,"https:\u002F\u002Fgithub.com\u002Fgetedgehq\u002Fskills\u002Fblob\u002Fmain\u002Fprocedural-painter\u002Fscripts\u002Fgrid.py",{"path":78,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":26,"sourceHtmlUrl":79},"scripts\u002Fpp\u002F__init__.py","https:\u002F\u002Fgithub.com\u002Fgetedgehq\u002Fskills\u002Fblob\u002Fmain\u002Fprocedural-painter\u002Fscripts\u002Fpp\u002F__init__.py",{"path":81,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":82,"sourceHtmlUrl":83},"scripts\u002Fpp\u002Fbridge.py",8141,"https:\u002F\u002Fgithub.com\u002Fgetedgehq\u002Fskills\u002Fblob\u002Fmain\u002Fprocedural-painter\u002Fscripts\u002Fpp\u002Fbridge.py",{"path":85,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":86,"sourceHtmlUrl":87},"scripts\u002Fpp\u002Fcore.py",6097,"https:\u002F\u002Fgithub.com\u002Fgetedgehq\u002Fskills\u002Fblob\u002Fmain\u002Fprocedural-painter\u002Fscripts\u002Fpp\u002Fcore.py",{"path":89,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":90,"sourceHtmlUrl":91},"scripts\u002Fpp\u002Fstrokes.py",8701,"https:\u002F\u002Fgithub.com\u002Fgetedgehq\u002Fskills\u002Fblob\u002Fmain\u002Fprocedural-painter\u002Fscripts\u002Fpp\u002Fstrokes.py",[93,101,109,116,123,131],{"skillNo":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":97,"sourceHtmlUrl":98,"categories":99,"keywords":100,"publishedAt":19},"01M7CFVPC1P7JN60J5AN9AZZ5G","zero-downtime-cloud-move","Runbook for moving a live app from one cloud to another (Google Cloud to AWS, AWS to Google Cloud, a PaaS to your own account, or one storage provider to another) without downtime. The agent inventories what is really running, builds the new stack next to the old one, keeps a one-line rollback for every phase, proves the new stack with real workloads before any traffic moves, cuts over with a checklist, watches a fixed window after the switch, copies data with an idempotent job whose second pass must report 0 left, and deletes the old cloud last. Use when someone asks to migrate, move or replatform a production app, switch cloud providers, move a backend, database files or object storage, plan a DNS cutover, or decommission an old cloud account.","https:\u002F\u002Fgithub.com\u002Fgetedgehq\u002Fskills\u002Fblob\u002Fmain\u002Fzero-downtime-cloud-move\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fgetedgehq\u002Fskills\u002Fblob\u002Fmain\u002Fzero-downtime-cloud-move\u002FSKILL.md",[],[],{"skillNo":102,"name":103,"nameZh":6,"description":104,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":105,"sourceHtmlUrl":106,"categories":107,"keywords":108,"publishedAt":19},"01M7CFVH8VN6G2KE8PBFD1CRMN","zayats-ceo-branding","Build an evidence-based CEO positioning paper, Personal Branding Roadmap, and editorial workflow using Marina Zayats's public method. Use for executive branding, LinkedIn ghostwriting briefs, profile strategy, and recurring CEO-approved content planning.","https:\u002F\u002Fgithub.com\u002Fgetedgehq\u002Fskills\u002Fblob\u002Fmain\u002Fzayats-ceo-branding\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fgetedgehq\u002Fskills\u002Fblob\u002Fmain\u002Fzayats-ceo-branding\u002FSKILL.md",[],[],{"skillNo":110,"name":111,"nameZh":6,"description":112,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":113,"categories":114,"keywords":115,"publishedAt":19},"01M7CFV9BB7G8K8CX9RKZ3GECX","yc-app-roast","YC App Roast: roast a YC or a16z Speedrun application. Use when a founder wants their YC or Speedrun answers scored, asks \"what would a YC partner think\", wants the weak answers found or rewritten, or wants their draft checked before they submit. Scores every answer 0-10 against public advice from YC and Speedrun partners, names the top issue with the exact words that cost points, and writes a rewrite from the founder's own facts. Works for YC and a16z Speedrun. Not affiliated with Y Combinator or a16z.","https:\u002F\u002Fgithub.com\u002Fgetedgehq\u002Fskills\u002Fblob\u002Fmain\u002Fyc-app-roast\u002FSKILL.md",[],[],{"skillNo":117,"name":118,"nameZh":6,"description":119,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":120,"categories":121,"keywords":122,"publishedAt":19},"01M7CFV11Z1HB9EEWFQ6PCJ98X","yc-app-review","YC App Review: get a YC or a16z Speedrun application reviewed by people you trust. Use when a founder wants friends, mentors or alumni to review their YC or Speedrun application, or asks to share their draft for feedback. Builds a shareable review page (one HTML file, application-portal look) where reviewers leave notes per question and press \"Send my notes\" to send them back as text, then parses the notes into proposed rewrites. Optional tracked private links per reviewer. Works for YC and a16z Speedrun. Not affiliated with Y Combinator or a16z.","https:\u002F\u002Fgithub.com\u002Fgetedgehq\u002Fskills\u002Fblob\u002Fmain\u002Fyc-app-review\u002FSKILL.md",[],[],{"skillNo":124,"name":125,"nameZh":6,"description":126,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":127,"sourceHtmlUrl":128,"categories":129,"keywords":130,"publishedAt":19},"01M7CFTSVJV7XCSW62W39MX8CZ","x-growth-playbook","X Growth Playbook. Analyse a person's own X (Twitter) posts and tell them what to post next, with the numbers behind every claim. Compares quote posts vs originals, links vs no links, short vs long, time of day in their timezone, media vs text and the topics they name, reports medians with n, then writes a 10-step plan and the next 7 posts in their voice. Use when the user says \"analyse my X posts\", \"what works on my Twitter\", \"how do I grow on X\", \"what should I post next on X\", \"audit my X account\", or shares an X data archive, X API export or a list of their posts. Runs on the user's computer.","https:\u002F\u002Fgithub.com\u002Fgetedgehq\u002Fskills\u002Fblob\u002Fmain\u002Fx-growth-playbook\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fgetedgehq\u002Fskills\u002Fblob\u002Fmain\u002Fx-growth-playbook\u002FSKILL.md",[],[],{"skillNo":132,"name":133,"nameZh":6,"description":134,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":135,"sourceHtmlUrl":136,"categories":137,"keywords":138,"publishedAt":19},"01M7CFTK101S3P00MQ129G5YNH","workplan","Create, update, or close work plans for multi-step tasks. Use when starting refactors, bug lists, feature work, migrations, or any task with 2+ steps. Also use after auto-compaction to re-orient. Triggers: \"workplan\", \"work plan\", \"create a plan\", \"what's the plan\", \"where was I\", or when Claude detects a multi-step task that needs tracking.","https:\u002F\u002Fgithub.com\u002Fgetedgehq\u002Fskills\u002Fblob\u002Fmain\u002Fworkplan\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fgetedgehq\u002Fskills\u002Fblob\u002Fmain\u002Fworkplan\u002FSKILL.md",[],[]]