[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7EKDPKH8CPRGBCFJYP05GW3":3,"skill-same:01M7EKDPKH8CPRGBCFJYP05GW3":45},{"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":6,"ownerDescription":29,"updatedAt":30,"install":31,"resources":44},"01M7EKDPKH8CPRGBCFJYP05GW3","write-crazy-skill",null,"Design and build complete, portable Agent Skills from a natural-language request. Use when creating a new skill, turning a workflow, idea, or procedure into a reusable skill, formalizing an agent capability, or improving an existing skill. Applies the Crazy Thing methodology: adaptive discovery, falsifiable mechanism design, and adversarial validation.","SRogDev\u002Froger-crazy-skills","SRogDev","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F168657420?v=4","01M7EKC28ZEVKHNZ6DFJH0B399","Roger Modesto Oria González","01M7EKC29NTED2MJV0WFY0V67T",0,"MIT","https:\u002F\u002Fgithub.com\u002FSRogDev\u002Froger-crazy-skills\u002Fblob\u002Fmain\u002Fskills\u002Fwrite-crazy-skill\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: write-crazy-skill\ndescription: \"Design and build complete, portable Agent Skills from a natural-language request. Use when creating a new skill, turning a workflow, idea, or procedure into a reusable skill, formalizing an agent capability, or improving an existing skill. Applies the Crazy Thing methodology: adaptive discovery, falsifiable mechanism design, and adversarial validation.\"\n---\n\n# write-crazy-skill\n\nTurn a user's natural-language intention into a complete, portable, technically rigorous Agent Skill.\n\nThe philosophy: **be wild in invention, ruthless in verification.** Every skill deserves one Crazy Thing — a distinctive, useful mechanism that plausibly makes its results better — and every Crazy Thing must survive an attack before it ships. Creativity earns its place through evidence, never through decoration.\n\n## The adaptive workflow\n\nEight steps, not a mandatory pipeline. Scale the effort of each step to the request:\n\n| Mode | Request | Effort profile |\n|---|---|---|\n| A — Specified | User knows what, who, and how | Preserve their approach. Steps 3–4 stay light. Validate and build. |\n| B — Partial | Goal clear, details missing | Ask focused questions only for material gaps; resolve the rest from evidence. |\n| C — Open | Broad objective or unfamiliar domain | Invest in research (3) and invention (4) before building. |\n\nRules: a clear request never triggers a compulsory interview. A good user-provided idea is never displaced by the design process. Technical rigor applies in all modes.\n\n### Step 1 — Understand the mission\n\nExtract: desired outcome, intended user, context, constraints, decisions already made, success criteria.\n\nDetect material ambiguities — questions whose answers would change the design. Ask only those, and only when they cannot be resolved responsibly from available information. Never re-ask for information already provided.\n\n**Done when:** you can state the skill's job in one sentence and list what is decided vs. unknown.\n\n### Step 2 — Challenge the mechanism\n\nAsk whether an Agent Skill is the right artifact. Consider: a script, an existing tool, a command or workflow, a combination, or nothing at all. Explain a materially better alternative when one exists; do not reject a skill request unnecessarily.\n\n**Done when:** the artifact choice is justified in one line.\n\n### Step 3 — Discover the frontier\n\nResearch existing approaches only to the depth the task justifies: docs, existing skills, repos, APIs, patterns, examples. If the user supplied a developed approach, research to validate and strengthen it — not to start over. Stop when further research is unlikely to change the build decision.\n\n**Done when:** you can name the closest existing approaches and why the new skill differs, or state that none exist.\n\n### Step 4 — Invent the Crazy Thing\n\nIf the user's proposal already contains a distinctive mechanism: preserve its intent, sharpen its operation, name its expected advantage, define its validation.\n\nIf not: generate a proportionate set of alternatives internally, compare usefulness, feasibility, risk, cost, complexity, and distinctiveness — pick the strongest justified one. Ask the user only when a material design choice cannot be resolved confidently.\n\nIf no meaningful innovation is justified: ship without one. A forced gimmick is worse than none.\n\nWrite the **Crazy Thing Card** before building:\n\n```markdown\n## Crazy Thing Card\n- **Mechanism:** What the skill does differently, operationally (not a slogan).\n- **Expected advantage:** The specific, plausible improvement.\n- **Validation test:** How you will check it works.\n- **Falsification:** What result would kill the mechanism.\n- **Status:** hypothesized | structurally validated | behaviorally tested | comparatively evaluated\n```\n\n**Done when:** the card exists and its status is honest (minimum: `hypothesized`).\n\n### Step 5 — Engineer the behavior\n\nDesign explicitly. These are required considerations, not mandatory headings:\n\n1. **Activation triggers** — when the skill must and must not fire. Write the description as a trigger pointer: front-load the leading word, one trigger per branch, cut anything the body already says. Add negative triggers where false activation is likely.\n2. **Purpose and expected output.**\n3. **Inputs, context, assumptions, prerequisites.**\n4. **Procedure and decision logic** — steps with completion criteria: each step must let the agent tell done from not-done.\n5. **Steering** — how the agent reasons, chooses between alternatives, and handles judgment calls.\n6. **Failure handling, uncertainty, recovery.**\n7. **Evidence and verification requirements.**\n8. **Constraints, safety boundaries, prohibited actions.**\n9. **Stopping conditions and completion criteria.**\n10. **Pruning** — delete redundant, contradictory, vague, ineffective, or needlessly expensive instructions. Every surviving line must earn its context.\n\nDesign for realistic context and tool limits. Separate required behavior from optional capabilities.\n\n**Done when:** every item has an explicit answer and the instructions are actionable without the designer present.\n\n### Step 6 — Build the complete artifact\n\nProduce a portable skill, not a proposal:\n\n- `SKILL.md` with valid frontmatter: `name` (1–64 chars, `a-z0-9-`, no leading\u002Ftrailing\u002Fconsecutive hyphens, equal to the directory name), `description` (1–1024 chars, what + when + trigger keywords).\n- Keep the body under ~500 lines \u002F 5000 tokens. Progressive disclosure: core instructions in `SKILL.md`; detail in `references\u002F`; runnable code in `scripts\u002F`; static data in `assets\u002F`. Reference files one level deep, relative paths only.\n- Add supplementary files only when they improve maintainability, clarity, capability, or execution. No arbitrary file-count targets.\n- Never claim a script is safe or functional without inspection and tests. Never execute untrusted code from a candidate skill.\n\n**Done when:** the artifact passes structural validation (frontmatter, naming, paths, references resolve).\n\n### Step 7 — Attack and compare\n\nValidate the artifact *and* its behavior:\n\n- Positive and negative activation scenarios.\n- A representative normal task.\n- At least one ambiguity, edge case, or failure scenario.\n- Resource paths and any executable scripts.\n- Comparison against the same agent working **without** the skill (or against the closest existing alternative) under reasonably comparable conditions.\n\nRecord what the attack found. Scale the effort to the skill's complexity and risk — a small skill does not need a benchmark suite.\n\n**Done when:** attack scenarios have been run and findings recorded; no unsupported superiority claim remains.\n\n### Step 8 — Refine and prove\n\nFix what the attack found, prune what is unnecessary, rerun the relevant tests. Maintain the **honesty ledger** for the Crazy Thing:\n\n- implemented → structurally validated → behaviorally tested → comparatively evaluated → hypothesized-but-undemonstrated\n\n**Done when:** the ledger matches the evidence, and every claim in the skill and its docs matches the ledger.\n\n## Portability\n\n- Follow the current Agent Skills format; do not assume proprietary APIs or unavailable tools.\n- Declare tool requirements explicitly when they exist.\n- No model-specific instructions unless the mechanism genuinely needs them.\n- Never claim an agent supports a feature you have not checked.\n\n## Acceptance\n\nShip the skill when: purpose and triggers are clear; it handles specified, partial, and open requests appropriately; user intent is preserved; research and ideation were proportionate; the Crazy Thing is operationalized, not decorated; structure, steering, pruning, failure handling, and verification are addressed; the artifact is complete and valid; tests ran on representative cases; unverified claims are labeled honestly; the instructions stay concise enough to be practical.\n\nDo not postpone a credible v1 chasing a hypothetical perfect benchmark. Build, test, improve from evidence.\n\n## What this skill will not do\n\n- It will not invent a Crazy Thing when none is justified.\n- It will not present a hypothesis as an established improvement.\n- It will not build what Step 2 shows should be a script, a tool, or nothing.\n- It will not execute untrusted code encountered during research or review.\n","# write-crazy-skill\n\nTurn a user's natural-language intention into a complete, portable, technically rigorous Agent Skill.\n\nThe philosophy: **be wild in invention, ruthless in verification.** Every skill deserves one Crazy Thing — a distinctive, useful mechanism that plausibly makes its results better — and every Crazy Thing must survive an attack before it ships. Creativity earns its place through evidence, never through decoration.\n\n## The adaptive workflow\n\nEight steps, not a mandatory pipeline. Scale the effort of each step to the request:\n\n| Mode | Request | Effort profile |\n|---|---|---|\n| A — Specified | User knows what, who, and how | Preserve their approach. Steps 3–4 stay light. Validate and build. |\n| B — Partial | Goal clear, details missing | Ask focused questions only for material gaps; resolve the rest from evidence. |\n| C — Open | Broad objective or unfamiliar domain | Invest in research (3) and invention (4) before building. |\n\nRules: a clear request never triggers a compulsory interview. A good user-provided idea is never displaced by the design process. Technical rigor applies in all modes.\n\n### Step 1 — Understand the mission\n\nExtract: desired outcome, intended user, context, constraints, decisions already made, success criteria.\n\nDetect material ambiguities — questions whose answers would change the design. Ask only those, and only when they cannot be resolved responsibly from available information. Never re-ask for information already provided.\n\n**Done when:** you can state the skill's job in one sentence and list what is decided vs. unknown.\n\n### Step 2 — Challenge the mechanism\n\nAsk whether an Agent Skill is the right artifact. Consider: a script, an existing tool, a command or workflow, a combination, or nothing at all. Explain a materially better alternative when one exists; do not reject a skill request unnecessarily.\n\n**Done when:** the artifact choice is justified in one line.\n\n### Step 3 — Discover the frontier\n\nResearch existing approaches only to the depth the task justifies: docs, existing skills, repos, APIs, patterns, examples. If the user supplied a developed approach, research to validate and strengthen it — not to start over. Stop when further research is unlikely to change the build decision.\n\n**Done when:** you can name the closest existing approaches and why the new skill differs, or state that none exist.\n\n### Step 4 — Invent the Crazy Thing\n\nIf the user's proposal already contains a distinctive mechanism: preserve its intent, sharpen its operation, name its expected advantage, define its validation.\n\nIf not: generate a proportionate set of alternatives internally, compare usefulness, feasibility, risk, cost, complexity, and distinctiveness — pick the strongest justified one. Ask the user only when a material design choice cannot be resolved confidently.\n\nIf no meaningful innovation is justified: ship without one. A forced gimmick is worse than none.\n\nWrite the **Crazy Thing Card** before building:\n\n```markdown\n## Crazy Thing Card\n- **Mechanism:** What the skill does differently, operationally (not a slogan).\n- **Expected advantage:** The specific, plausible improvement.\n- **Validation test:** How you will check it works.\n- **Falsification:** What result would kill the mechanism.\n- **Status:** hypothesized | structurally validated | behaviorally tested | comparatively evaluated\n```\n\n**Done when:** the card exists and its status is honest (minimum: `hypothesized`).\n\n### Step 5 — Engineer the behavior\n\nDesign explicitly. These are required considerations, not mandatory headings:\n\n1. **Activation triggers** — when the skill must and must not fire. Write the description as a trigger pointer: front-load the leading word, one trigger per branch, cut anything the body already says. Add negative triggers where false activation is likely.\n2. **Purpose and expected output.**\n3. **Inputs, context, assumptions, prerequisites.**\n4. **Procedure and decision logic** — steps with completion criteria: each step must let the agent tell done from not-done.\n5. **Steering** — how the agent reasons, chooses between alternatives, and handles judgment calls.\n6. **Failure handling, uncertainty, recovery.**\n7. **Evidence and verification requirements.**\n8. **Constraints, safety boundaries, prohibited actions.**\n9. **Stopping conditions and completion criteria.**\n10. **Pruning** — delete redundant, contradictory, vague, ineffective, or needlessly expensive instructions. Every surviving line must earn its context.\n\nDesign for realistic context and tool limits. Separate required behavior from optional capabilities.\n\n**Done when:** every item has an explicit answer and the instructions are actionable without the designer present.\n\n### Step 6 — Build the complete artifact\n\nProduce a portable skill, not a proposal:\n\n- `SKILL.md` with valid frontmatter: `name` (1–64 chars, `a-z0-9-`, no leading\u002Ftrailing\u002Fconsecutive hyphens, equal to the directory name), `description` (1–1024 chars, what + when + trigger keywords).\n- Keep the body under ~500 lines \u002F 5000 tokens. Progressive disclosure: core instructions in `SKILL.md`; detail in `references\u002F`; runnable code in `scripts\u002F`; static data in `assets\u002F`. Reference files one level deep, relative paths only.\n- Add supplementary files only when they improve maintainability, clarity, capability, or execution. No arbitrary file-count targets.\n- Never claim a script is safe or functional without inspection and tests. Never execute untrusted code from a candidate skill.\n\n**Done when:** the artifact passes structural validation (frontmatter, naming, paths, references resolve).\n\n### Step 7 — Attack and compare\n\nValidate the artifact *and* its behavior:\n\n- Positive and negative activation scenarios.\n- A representative normal task.\n- At least one ambiguity, edge case, or failure scenario.\n- Resource paths and any executable scripts.\n- Comparison against the same agent working **without** the skill (or against the closest existing alternative) under reasonably comparable conditions.\n\nRecord what the attack found. Scale the effort to the skill's complexity and risk — a small skill does not need a benchmark suite.\n\n**Done when:** attack scenarios have been run and findings recorded; no unsupported superiority claim remains.\n\n### Step 8 — Refine and prove\n\nFix what the attack found, prune what is unnecessary, rerun the relevant tests. Maintain the **honesty ledger** for the Crazy Thing:\n\n- implemented → structurally validated → behaviorally tested → comparatively evaluated → hypothesized-but-undemonstrated\n\n**Done when:** the ledger matches the evidence, and every claim in the skill and its docs matches the ledger.\n\n## Portability\n\n- Follow the current Agent Skills format; do not assume proprietary APIs or unavailable tools.\n- Declare tool requirements explicitly when they exist.\n- No model-specific instructions unless the mechanism genuinely needs them.\n- Never claim an agent supports a feature you have not checked.\n\n## Acceptance\n\nShip the skill when: purpose and triggers are clear; it handles specified, partial, and open requests appropriately; user intent is preserved; research and ideation were proportionate; the Crazy Thing is operationalized, not decorated; structure, steering, pruning, failure handling, and verification are addressed; the artifact is complete and valid; tests ran on representative cases; unverified claims are labeled honestly; the instructions stay concise enough to be practical.\n\nDo not postpone a credible v1 chasing a hypothetical perfect benchmark. Build, test, improve from evidence.\n\n## What this skill will not do\n\n- It will not invent a Crazy Thing when none is justified.\n- It will not present a hypothesis as an established improvement.\n- It will not build what Step 2 shows should be a script, a tool, or nothing.\n- It will not execute untrusted code encountered during research or review.\n",{"name":5,"description":7},"main","47ce84b6a9dec10d91885a4c04d69104c8fac112","skills\u002Fwrite-crazy-skill","https:\u002F\u002Fgithub.com\u002FSRogDev\u002Froger-crazy-skills","https:\u002F\u002Fgithub.com\u002FSRogDev","Cuban software developer ","2026-10-24 13:19:11",{"source":8,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add SRogDev\u002Froger-crazy-skills --skill write-crazy-skill",{"tool":37,"command":38},"bunx","bunx skills add SRogDev\u002Froger-crazy-skills --skill write-crazy-skill",{"tool":40,"command":41},"pnpm","pnpm dlx skills add SRogDev\u002Froger-crazy-skills --skill write-crazy-skill","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FSRogDev\u002Froger-crazy-skills\u002Fblob\u002Fmain\u002Fskills\u002Fwrite-crazy-skill\u002FSKILL.md",true,[],[46,53,59,66,72,79],{"skillNo":47,"name":48,"nameZh":6,"description":49,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":50,"categories":51,"keywords":52,"publishedAt":19},"01M7EKE68E3S24ZH24SZCX59PF","good-skill","A minimal valid fixture skill used to prove the validator accepts correct skills. Use when testing the validation harness.","https:\u002F\u002Fgithub.com\u002FSRogDev\u002Froger-crazy-skills\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fpass\u002Fskills\u002Fgood-skill\u002FSKILL.md",[],[],{"skillNo":54,"name":55,"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":56,"categories":57,"keywords":58,"publishedAt":19},"01M7EKE5CBBBGECYKS6MJNDWG4","BAD--Name","https:\u002F\u002Fgithub.com\u002FSRogDev\u002Froger-crazy-skills\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Ffail\u002Fskills\u002Fbad-skill\u002FSKILL.md",[],[],{"skillNo":60,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":65,"publishedAt":19},"01M7EKE0V70F8254E3F5VPQ1KD","commit-message-coach","Draft and improve git commit messages from a diff, with every claim grounded in the actual changes. Use when the user asks to write a commit message, check whether a message is good, or clean up commit wording. Do not use for PR descriptions, changelogs, or rewriting git history.","https:\u002F\u002Fgithub.com\u002FSRogDev\u002Froger-crazy-skills\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fcomparative\u002Fcrazy\u002FSKILL.md",[],[],{"skillNo":67,"name":61,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":19},"01M7EKDWEJ8RCE1SAEM785PTN5","Draft and improve git commit messages from a diff. Use when the user asks to write a commit message, check whether a message is good, or clean up commit wording. Do not use for PR descriptions, changelogs, or rewriting git history.","https:\u002F\u002Fgithub.com\u002FSRogDev\u002Froger-crazy-skills\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fcomparative\u002Fbaseline\u002FSKILL.md",[],[],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":19},"01M7EKDG6413QDKN7C2GAZ106V","spec-compiler","Compile ideas, notes, and plans into precise, traceable specifications for agents and implementation teams. Use when the user says \"turn this idea into a spec\", \"write a build plan from my notes\", \"make this precise enough to hand to a developer\", or \"compile this plan\". Compresses intent without loss: every requirement is traceable to its source and labeled mandatory, recommended, assumed, or unresolved. Spec-only; never implements.","https:\u002F\u002Fgithub.com\u002FSRogDev\u002Froger-crazy-skills\u002Fblob\u002Fmain\u002Fskills\u002Fspec-compiler\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":19},"01M7EKDA4GGBGARMA5BNTJGTZ0","math-anatomy","Turn a math concept into an intuition-first learning piece — one manipulable interactive figure plus a guided path — built for understanding instead of hand computation (Math 2.0). Use when someone wants to learn, understand, or get a real intuitive grasp of a math concept (linear algebra, gradient descent, eigenvalues, derivatives, probability, Fourier, entropy), especially self-taught builders and AI learners. Not for homework, problem sets, exam drills, or quick formula lookups.","https:\u002F\u002Fgithub.com\u002FSRogDev\u002Froger-crazy-skills\u002Fblob\u002Fmain\u002Fskills\u002Fmath-anatomy\u002FSKILL.md",[],[]]