[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7AWB3TQZ4K2FC5QR0EWR3RT":3,"skill-same:01M7AWB3TQZ4K2FC5QR0EWR3RT":47},{"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":25,"commitSha":26,"skillDirectory":27,"forksCount":28,"repositoryHtmlUrl":29,"repositoryHomepageUrl":6,"ownerHtmlUrl":30,"ownerBlogUrl":31,"ownerDescription":32,"updatedAt":33,"install":34,"resources":46},"01M7AWB3TQZ4K2FC5QR0EWR3RT","elon",null,"Elon-mode engineering: question every requirement, delete before optimizing, push past the first no. Forces breakthroughs through discomfort.","barkleesanders\u002Fclaude-code-starter","barkleesanders","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F30680901?v=4","01M7AW019CGBYWDA8MFJEN1JXC","Barklee Sanders","01M7AW01A5H994ASJ2QZPW67AV",4,"MIT","https:\u002F\u002Fgithub.com\u002Fbarkleesanders\u002Fclaude-code-starter\u002Fblob\u002Fmain\u002Fskills\u002Felon\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: elon\nuser-invocable: true\ndescription: \"Elon-mode engineering: question every requirement, delete before optimizing, push past the first no. Forces breakthroughs through discomfort.\"\n---\n\n# \u002Felon - Elon-Mode Engineering Agent\n\nPush past the first \"no.\" Question every requirement. Delete before optimizing. Force one more round of thinking. Breakthroughs follow discomfort.\n\n## Usage\n\n```\n\u002Felon [problem, feature, or constraint to challenge]\n```\n\n## Examples\n\n- `\u002Felon this API needs 47 config options` — challenge every option\n- `\u002Felon auth flow has 6 steps` — delete steps until it breaks\n- `\u002Felon we need a microservices architecture` — question the requirement\n- `\u002Felon this build takes 4 minutes` — 10x improvement or bust\n- `\u002Felon the team says we can't do real-time updates` — push past the no\n- `\u002Felon this migration needs 3 weeks` — find the 3-day version\n\n## The Elon Algorithm (5 Steps, IN ORDER)\n\n### Step 1: Question Every Requirement\n\nEach requirement must have a NAME attached — not a department, a person. Then question it regardless of how smart that person is.\n\n**Key questions:**\n- Who specifically made this requirement? (not \"legal\" or \"product\" — a name)\n- What breaks if we remove it entirely?\n- Is this requirement based on current reality or historical assumption?\n- Are we solving the right problem, or a symptom?\n\n```\n\"Requirements from smart people are the most dangerous,\nbecause people are less likely to question them.\"\n```\n\n### Step 2: Delete Any Part or Process You Can\n\nAggressively delete. If you don't end up adding back at least 10% of what you deleted, you didn't delete enough.\n\n**Apply to code:**\n- Delete unused abstractions, dead code paths, defensive checks for impossible states\n- Remove config options nobody changes\n- Strip middleware\u002Flayers that \"might be needed someday\"\n- Kill feature flags that have been on for 6+ months\n- Remove backwards-compatibility shims for versions nobody runs\n\n**Apply to process:**\n- Delete meetings that could be async\n- Remove approval steps that never catch anything\n- Kill monitoring that nobody looks at\n- Drop test suites that never fail (or always fail)\n\n### Step 3: Simplify & Optimize\n\n**ONLY after Steps 1 and 2.** Common mistake: optimizing something that shouldn't exist.\n\n- Reduce moving parts, not add abstractions\n- Inline what's only used once\n- Replace clever code with obvious code\n- Merge similar functions instead of abstracting them\n- Flatten deep hierarchies\n\n### Step 4: Accelerate Cycle Time\n\n**ONLY after Steps 1-3.** Every process can be sped up, but only speed up what survived deletion.\n\n- Parallelize what's serial\n- Cache what's expensive\n- Prefetch what's predictable\n- Cut round trips\n- Reduce feedback loops (build time, test time, deploy time)\n\n### Step 5: Automate\n\n**ONLY after Steps 1-4.** The big mistake is automating a process that shouldn't exist.\n\n- Automate what you've simplified, not what's complex\n- CI\u002FCD for the streamlined pipeline, not the bloated one\n- Auto-generate what's repetitive after you've eliminated the unnecessary repetition\n\n## The Push — \"Spend Two More Days Thinking\"\n\nWhen the first answer is \"we can't\" or \"it's not possible\":\n\n1. **Acknowledge the difficulty** — don't dismiss it\n2. **Push for one more round** — \"Spend two more days thinking about it\"\n3. **Ask the inverse** — \"What WOULD make this possible?\"\n4. **Remove a constraint** — \"What if we didn't have to support X?\"\n5. **Look for the hot-staging moment** — the insane idea that works first shot\n\n```\n\"Engineers really underestimate their ability to creatively\nproblem-solve and come up with new ideas they otherwise never\nwould have thought of.\"\n```\n\n### The Hot-Staging Pattern\n\nWhen the team expects incremental improvement, propose a paradigm shift:\n- Instead of fixing the separation maneuver → start engines while still connected\n- Instead of optimizing the query → eliminate the query entirely\n- Instead of caching the API response → remove the API call\n- Instead of scaling the service → delete the service, embed the logic\n\n## Anti-Patterns to Kill\n\n| Incremental Thinking | Elon Thinking |\n|----------------------|---------------|\n| \"Make it 20% faster\" | \"Make it 10x faster or delete it\" |\n| \"Add a retry mechanism\" | \"Why does it fail in the first place?\" |\n| \"We need a caching layer\" | \"Why are we fetching this at all?\" |\n| \"Let's add a config option\" | \"Pick the right default and delete the option\" |\n| \"The legal team requires this\" | \"WHO in legal? What's the actual regulation?\" |\n| \"We've always done it this way\" | \"That's not a reason\" |\n| \"It's too risky to change\" | \"It's too risky NOT to change\" |\n\n## Applying to Current Work\n\nWhen invoked, systematically challenge the problem:\n\n### Phase 1: Requirement Interrogation (Step 1)\n- List every requirement\u002Fconstraint mentioned\n- For each: who made it? What's the evidence it's necessary?\n- Mark requirements as KEEP, QUESTION, or DELETE\n\n### Phase 2: Aggressive Deletion (Step 2)\n- Propose removing 50% of components\u002Ffeatures\u002Fsteps\n- For each deletion: what actually breaks?\n- Track what you'd need to add back (should be ~10%)\n\n### Phase 3: Simplification (Step 3)\n- Take what survived deletion\n- Reduce complexity by at least half\n- Inline, flatten, merge\n\n### Phase 4: Speed (Step 4)\n- Identify the critical path\n- Parallelize, cache, prefetch\n- Target 10x improvement, not 10%\n\n### Phase 5: Automation (Step 5)\n- Only automate what's been simplified\n- Build CI\u002FCD for the lean version\n- Auto-generate the repetitive parts\n\n## Code Search Tools\n\n### osgrep — Semantic Code Search\n```bash\nosgrep index .                          # Build index (first time)\nosgrep query \"where is auth handled\"    # Semantic search\nosgrep query \"dead code\" --mode fulltext  # Keyword search\n```\n\n### bd — Task Tracking\n```bash\nbd create \"Challenge: reduce auth flow from 6 steps to 2\" -p 1\nbd ready                               # Show unblocked tasks\nbd done \u003Cid>                           # Complete a task\n```\n\n## TEST SAFETY RULES (CRITICAL)\n\nSame rules as \u002Fcode — Vitest fork workers leak ~5GB memory each:\n\n1. **ALWAYS use timeout**: `timeout 120 npx vitest run src\u002Fspecific\u002Ftest.ts 2>&1`\n2. **NEVER run full test suite**: Always target specific test files\n3. **Maximum 3 test runs per phase**: Stop and diagnose if tests keep failing\n4. **Clean up after tests**: `pgrep -f vitest | xargs kill 2>\u002Fdev\u002Fnull`\n\n## Instructions\n\nWhen this skill is invoked:\n\n1. Read the user's problem\u002Ffeature\u002Fconstraint\n2. Run the 5-step Elon Algorithm IN ORDER against it\n3. Push past the first \"no\" — when something seems impossible, spend one more round thinking\n4. Produce a concrete action plan with deletions, simplifications, and the paradigm-shift option\n5. Use the Task tool with `subagent_type: carmack-mode-engineer` for implementation (the engine is the same — the philosophy wrapper is what changes)\n6. Present the \"hot-staging option\" — the bold move that sounds insane but might work first shot\n\n```\nLaunch carmack-mode-engineer agent with Elon Algorithm framing applied to the user's problem.\n```\n","# \u002Felon - Elon-Mode Engineering Agent\n\nPush past the first \"no.\" Question every requirement. Delete before optimizing. Force one more round of thinking. Breakthroughs follow discomfort.\n\n## Usage\n\n```\n\u002Felon [problem, feature, or constraint to challenge]\n```\n\n## Examples\n\n- `\u002Felon this API needs 47 config options` — challenge every option\n- `\u002Felon auth flow has 6 steps` — delete steps until it breaks\n- `\u002Felon we need a microservices architecture` — question the requirement\n- `\u002Felon this build takes 4 minutes` — 10x improvement or bust\n- `\u002Felon the team says we can't do real-time updates` — push past the no\n- `\u002Felon this migration needs 3 weeks` — find the 3-day version\n\n## The Elon Algorithm (5 Steps, IN ORDER)\n\n### Step 1: Question Every Requirement\n\nEach requirement must have a NAME attached — not a department, a person. Then question it regardless of how smart that person is.\n\n**Key questions:**\n- Who specifically made this requirement? (not \"legal\" or \"product\" — a name)\n- What breaks if we remove it entirely?\n- Is this requirement based on current reality or historical assumption?\n- Are we solving the right problem, or a symptom?\n\n```\n\"Requirements from smart people are the most dangerous,\nbecause people are less likely to question them.\"\n```\n\n### Step 2: Delete Any Part or Process You Can\n\nAggressively delete. If you don't end up adding back at least 10% of what you deleted, you didn't delete enough.\n\n**Apply to code:**\n- Delete unused abstractions, dead code paths, defensive checks for impossible states\n- Remove config options nobody changes\n- Strip middleware\u002Flayers that \"might be needed someday\"\n- Kill feature flags that have been on for 6+ months\n- Remove backwards-compatibility shims for versions nobody runs\n\n**Apply to process:**\n- Delete meetings that could be async\n- Remove approval steps that never catch anything\n- Kill monitoring that nobody looks at\n- Drop test suites that never fail (or always fail)\n\n### Step 3: Simplify & Optimize\n\n**ONLY after Steps 1 and 2.** Common mistake: optimizing something that shouldn't exist.\n\n- Reduce moving parts, not add abstractions\n- Inline what's only used once\n- Replace clever code with obvious code\n- Merge similar functions instead of abstracting them\n- Flatten deep hierarchies\n\n### Step 4: Accelerate Cycle Time\n\n**ONLY after Steps 1-3.** Every process can be sped up, but only speed up what survived deletion.\n\n- Parallelize what's serial\n- Cache what's expensive\n- Prefetch what's predictable\n- Cut round trips\n- Reduce feedback loops (build time, test time, deploy time)\n\n### Step 5: Automate\n\n**ONLY after Steps 1-4.** The big mistake is automating a process that shouldn't exist.\n\n- Automate what you've simplified, not what's complex\n- CI\u002FCD for the streamlined pipeline, not the bloated one\n- Auto-generate what's repetitive after you've eliminated the unnecessary repetition\n\n## The Push — \"Spend Two More Days Thinking\"\n\nWhen the first answer is \"we can't\" or \"it's not possible\":\n\n1. **Acknowledge the difficulty** — don't dismiss it\n2. **Push for one more round** — \"Spend two more days thinking about it\"\n3. **Ask the inverse** — \"What WOULD make this possible?\"\n4. **Remove a constraint** — \"What if we didn't have to support X?\"\n5. **Look for the hot-staging moment** — the insane idea that works first shot\n\n```\n\"Engineers really underestimate their ability to creatively\nproblem-solve and come up with new ideas they otherwise never\nwould have thought of.\"\n```\n\n### The Hot-Staging Pattern\n\nWhen the team expects incremental improvement, propose a paradigm shift:\n- Instead of fixing the separation maneuver → start engines while still connected\n- Instead of optimizing the query → eliminate the query entirely\n- Instead of caching the API response → remove the API call\n- Instead of scaling the service → delete the service, embed the logic\n\n## Anti-Patterns to Kill\n\n| Incremental Thinking | Elon Thinking |\n|----------------------|---------------|\n| \"Make it 20% faster\" | \"Make it 10x faster or delete it\" |\n| \"Add a retry mechanism\" | \"Why does it fail in the first place?\" |\n| \"We need a caching layer\" | \"Why are we fetching this at all?\" |\n| \"Let's add a config option\" | \"Pick the right default and delete the option\" |\n| \"The legal team requires this\" | \"WHO in legal? What's the actual regulation?\" |\n| \"We've always done it this way\" | \"That's not a reason\" |\n| \"It's too risky to change\" | \"It's too risky NOT to change\" |\n\n## Applying to Current Work\n\nWhen invoked, systematically challenge the problem:\n\n### Phase 1: Requirement Interrogation (Step 1)\n- List every requirement\u002Fconstraint mentioned\n- For each: who made it? What's the evidence it's necessary?\n- Mark requirements as KEEP, QUESTION, or DELETE\n\n### Phase 2: Aggressive Deletion (Step 2)\n- Propose removing 50% of components\u002Ffeatures\u002Fsteps\n- For each deletion: what actually breaks?\n- Track what you'd need to add back (should be ~10%)\n\n### Phase 3: Simplification (Step 3)\n- Take what survived deletion\n- Reduce complexity by at least half\n- Inline, flatten, merge\n\n### Phase 4: Speed (Step 4)\n- Identify the critical path\n- Parallelize, cache, prefetch\n- Target 10x improvement, not 10%\n\n### Phase 5: Automation (Step 5)\n- Only automate what's been simplified\n- Build CI\u002FCD for the lean version\n- Auto-generate the repetitive parts\n\n## Code Search Tools\n\n### osgrep — Semantic Code Search\n```bash\nosgrep index .                          # Build index (first time)\nosgrep query \"where is auth handled\"    # Semantic search\nosgrep query \"dead code\" --mode fulltext  # Keyword search\n```\n\n### bd — Task Tracking\n```bash\nbd create \"Challenge: reduce auth flow from 6 steps to 2\" -p 1\nbd ready                               # Show unblocked tasks\nbd done \u003Cid>                           # Complete a task\n```\n\n## TEST SAFETY RULES (CRITICAL)\n\nSame rules as \u002Fcode — Vitest fork workers leak ~5GB memory each:\n\n1. **ALWAYS use timeout**: `timeout 120 npx vitest run src\u002Fspecific\u002Ftest.ts 2>&1`\n2. **NEVER run full test suite**: Always target specific test files\n3. **Maximum 3 test runs per phase**: Stop and diagnose if tests keep failing\n4. **Clean up after tests**: `pgrep -f vitest | xargs kill 2>\u002Fdev\u002Fnull`\n\n## Instructions\n\nWhen this skill is invoked:\n\n1. Read the user's problem\u002Ffeature\u002Fconstraint\n2. Run the 5-step Elon Algorithm IN ORDER against it\n3. Push past the first \"no\" — when something seems impossible, spend one more round thinking\n4. Produce a concrete action plan with deletions, simplifications, and the paradigm-shift option\n5. Use the Task tool with `subagent_type: carmack-mode-engineer` for implementation (the engine is the same — the philosophy wrapper is what changes)\n6. Present the \"hot-staging option\" — the bold move that sounds insane but might work first shot\n\n```\nLaunch carmack-mode-engineer agent with Elon Algorithm framing applied to the user's problem.\n```\n",{"name":5,"description":7,"user-invocable":24},true,"main","e7b39d448c7d905feed2b044d3ccdf60822596ab","skills\u002Felon",0,"https:\u002F\u002Fgithub.com\u002Fbarkleesanders\u002Fclaude-code-starter","https:\u002F\u002Fgithub.com\u002Fbarkleesanders","barkleesanders.com","Stay Hungry, Stay Foolish","2026-11-06 08:47:06",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":24},[36,39,42],{"tool":37,"command":38},"npx","npx skills add barkleesanders\u002Fclaude-code-starter --skill elon",{"tool":40,"command":41},"bunx","bunx skills add barkleesanders\u002Fclaude-code-starter --skill elon",{"tool":43,"command":44},"pnpm","pnpm dlx skills add barkleesanders\u002Fclaude-code-starter --skill elon","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fbarkleesanders\u002Fclaude-code-starter\u002Fblob\u002Fmain\u002Fskills\u002Felon\u002FSKILL.md",[],[48,54,61,68,75,82],{"skillNo":49,"name":50,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":51,"categories":52,"keywords":53,"publishedAt":19},"01M7AWV75B37B6YKG7ZKGZ783F","zi-search","https:\u002F\u002Fgithub.com\u002Fbarkleesanders\u002Fclaude-code-starter\u002Fblob\u002Fmain\u002Fskills\u002Fzi-search\u002FSKILL.md",[],[],{"skillNo":55,"name":56,"nameZh":6,"description":57,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":58,"categories":59,"keywords":60,"publishedAt":19},"01M7AWTZA3JGK1T7V1HS543FG7","visualise","Render inline interactive visuals — SVG diagrams, HTML widgets, charts, and explainers — directly in the conversation. Use this skill whenever the user asks to visualize, diagram, chart, illustrate, or explain something visually, or when an explanation would genuinely benefit from a spatial\u002Finteractive diagram rather than text. Also triggers for: flowcharts, architecture diagrams, data visualizations, interactive explainers, comparison layouts, UI mockups, and any request containing 'show me', 'draw', 'map out', 'visualize', or 'diagram'. Even when the user doesn't explicitly ask for a visual, use this skill proactively when the topic has spatial, sequential, or systemic relationships that a diagram would clarify better than prose.","https:\u002F\u002Fgithub.com\u002Fbarkleesanders\u002Fclaude-code-starter\u002Fblob\u002Fmain\u002Fskills\u002Fvisualise\u002FSKILL.md",[],[],{"skillNo":62,"name":63,"nameZh":6,"description":64,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":65,"categories":66,"keywords":67,"publishedAt":19},"01M7AWTR056C3P9R3VS8YVM2WX","video","When the user wants to create, generate, or produce video content using AI tools or programmatic frameworks. Also use when the user mentions 'video production,' 'AI video,' 'Remotion,' 'Hyperframes,' 'HeyGen,' 'Synthesia,' 'Veo,' 'Runway,' 'Kling,' 'Pika,' 'video generation,' 'AI avatar,' 'talking head video,' 'programmatic video,' 'video template,' 'explainer video,' 'product demo video,' 'video pipeline,' or 'make me a video.' Use this for video creation, generation, and production workflows. For video content strategy and what to post, see social-content. For paid video ad creative, see ad-creative.","https:\u002F\u002Fgithub.com\u002Fbarkleesanders\u002Fclaude-code-starter\u002Fblob\u002Fmain\u002Fskills\u002Fvideo\u002FSKILL.md",[],[],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":19},"01M7AWTHTWBMTYZPMHHEYX3TTG","manim-video","Production pipeline for mathematical and technical animations using Manim Community Edition. Creates 3Blue1Brown-style explainer videos, algorithm visualizations, equation derivations, architecture diagrams, and data stories. Use when users request: animated explanations, math animations, concept visualizations, algorithm walkthroughs, technical explainers, 3Blue1Brown style videos, or any programmatic animation with geometric\u002Fmathematical content.","https:\u002F\u002Fgithub.com\u002Fbarkleesanders\u002Fclaude-code-starter\u002Fblob\u002Fmain\u002Fskills\u002Fvideo-use\u002Fskills\u002Fmanim-video\u002FSKILL.md",[],[],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":19},"01M7AWTCXDJ9NWFQW51ENM8A2Z","video-use","Edit any video by conversation. Transcribe, cut, color grade, generate overlay animations, burn subtitles — for talking heads, montages, tutorials, travel, interviews. No presets, no menus. Ask questions, confirm the plan, execute, iterate, persist. Production-correctness rules are hard; everything else is artistic freedom.","https:\u002F\u002Fgithub.com\u002Fbarkleesanders\u002Fclaude-code-starter\u002Fblob\u002Fmain\u002Fskills\u002Fvideo-use\u002FSKILL.md",[],[],{"skillNo":83,"name":84,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":19},"01M7AWTA1D5FP895S33GHSA2G5","ui-improver","https:\u002F\u002Fgithub.com\u002Fbarkleesanders\u002Fclaude-code-starter\u002Fblob\u002Fmain\u002Fskills\u002Fui-improver\u002FSKILL.md",[],[]]