[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M72FZTWSTAKCXM4GQY4901EB":3,"skill-same:01M72FZTWSTAKCXM4GQY4901EB":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":25,"commitSha":26,"skillDirectory":5,"forksCount":14,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":6,"ownerDescription":29,"updatedAt":30,"install":31,"resources":44},"01M72FZTWSTAKCXM4GQY4901EB","stress-tested-architecture",null,"Combines 'brainstorming' and 'grilling'. Interactive design, RFC, and system architecture workflow that couples collaborative exploration with adversarial stress-testing. Features Three-Path Classification (Spike, Bounded, Architectural), a branching Design Tree, structured Grilling Rounds (The Frontier) with recommended answers, and rigorous scrutiny on failure modes, scale, and trade-offs before locking specifications. Triggers on \u002Fstress-tested-architecture, \u002Fgrill-architecture, \"design architecture\", \"brainstorm and grill\", \"stress test plan\", or \"system design RFC\".","ZEenoz\u002FAntigravity-skills","ZEenoz","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F88967082?v=4","01M72FRVE366D26MBJP0XKJT0F","NAPHAT EM-ONG","01M72FRVF5DS4FNG440G5315FE",0,"MIT","https:\u002F\u002Fgithub.com\u002FZEenoz\u002FAntigravity-skills\u002Fblob\u002Fmain\u002Fstress-tested-architecture\u002FSKILL.md",[],[],"2026-11-10 18:39:20",false,"---\nname: stress-tested-architecture\ndescription: >\n  Combines 'brainstorming' and 'grilling'. Interactive design, RFC, and system\n  architecture workflow that couples collaborative exploration with adversarial\n  stress-testing. Features Three-Path Classification (Spike, Bounded, Architectural),\n  a branching Design Tree, structured Grilling Rounds (The Frontier) with recommended\n  answers, and rigorous scrutiny on failure modes, scale, and trade-offs before\n  locking specifications. Triggers on \u002Fstress-tested-architecture, \u002Fgrill-architecture,\n  \"design architecture\", \"brainstorm and grill\", \"stress test plan\", or \"system design RFC\".\nlicense: MIT\n---\n\n# Stress-Tested Architecture: Brainstorm & Grill\n\nTurn ideas into resilient, production-ready system architectures through collaborative ideation combined with adversarial stress-testing.\n\n## The Core Principle\n\n> **Explore openly, grill ruthlessly, lock before building.**  \n> Never rubber-stamp user assumptions. Never debate without presenting clear recommendations.\n\n\u003CHARD-GATE>\nDo NOT write code, generate boilerplate, or take implementation actions until your human partner has explicitly approved the design.\n\u003C\u002FHARD-GATE>\n\n---\n\n## 1. Request Classification\n\nBefore asking your first question, classify the request and state it out loud:\n\n* **Spike:** Feasibility question (*\"Is it possible to...\"*, *\"Can we test if...\"*). Present question + 2-3 sentence probe plan, get approval, test as cheaply as possible, report recommendation. Everything built remains throwaway.\n* **Bounded:** Well-scoped change to existing flow in this repository (e.g. new flag, one endpoint). Ask clarifying questions, present a short design in chat (approach, affected files, tests), and STOP until explicit approval is granted.\n* **Architectural:** New subsystems, multi-module features, altered API boundaries, or complex refactoring. Follow the full Design Tree & Grilling process below.\n\n*Rule:* When in doubt, choose the heavier path. Hidden complexity discovered mid-task immediately upgrades the path.\n\n---\n\n## 2. The Design Tree & Grilling Protocol\n\nArchitectures are trees of decisions: foundational choices branch into secondary implementation details.\n\n### The Frontier & Structured Rounds\nAsk only questions on the **frontier** (decisions whose prerequisites are already settled). Do not ask questions that depend on unanswered questions.\n\nFormat each round clearly with options and recommendations:\n\n```markdown\n❓ **Q1 - [Decision Title]**: [Context and concrete trade-offs between Option A and Option B]\n➡️ **Recommendation**: [Recommended choice and why, noting edge case \u002F scale trade-offs]\n\n---\n\n❓ **Q2 - [Decision Title]**: [Context and options]\n➡️ **Recommendation**: [Recommended choice]\n```\n\n### Fact-Finding vs. Decision-Making\n* **Agent's Job (Facts):** Inspect existing codebase, search documentation, review dependencies, and check environment constraints. Never ask the user for facts you can discover yourself.\n* **User's Job (Decisions):** Decide business priorities, risk tolerance, and directional choices from your recommended options.\n\n---\n\n## 3. The 5 Grilling Vectors (Adversarial Scrutiny)\n\nEvery proposed architecture must be stress-tested against these 5 failure vectors before finalizing:\n\n1. **Failure Modes & Resilience:** What happens if the network drops, third-party API times out, DB locks, or partial writes occur? Where is the circuit breaker \u002F retry policy?\n2. **Scale & Concurrency:** How does this behave at 10x or 100x volume? Are there race conditions, memory leaks, or N+1 query bottlenecks?\n3. **Seams & Isolation:** Can each unit be tested in total isolation without booting the universe? Are internal implementation details leaking across boundaries?\n4. **YAGNI & Simplicity (Ponytail Lens):** Are there unrequested abstractions (interfaces with 1 implementation, speculative factories)? What can be deleted?\n5. **Rollback & Blast Radius:** If a deployment fails or data is corrupted, how is state restored safely?\n\n---\n\n## 4. Architectural Spec & Self-Review\n\nWhen the frontier is resolved, write the design specification to:\n`docs\u002Fspecs\u002FYYYY-MM-DD-\u003Ctopic>-design.md`\n\n### Mandatory Spec Sections:\n1. **Context & Goals:** Problem statement, in-scope, and explicit out-of-scope.\n2. **System Architecture & Data Flow:** Component boundaries, contracts, sequence.\n3. **Failure Handling & Edge Cases:** Fallbacks, retries, and data consistency.\n4. **Testing Strategy:** Unit seams, integration harnesses, and verification plan.\n5. **Alternative Approaches Rejected:** Why simpler or competing designs were discarded.\n\n### Spec Self-Review Gate:\nBefore showing the spec to the user, execute an inline self-review:\n* [ ] **Placeholder scan:** No \"TODO\", \"TBD\", or vague requirements.\n* [ ] **Consistency check:** Architecture matches data flow and component responsibilities.\n* [ ] **Ambiguity check:** All critical requirements are unambiguous and verifiable.\n* [ ] **Scope check:** Sized appropriately for an implementation plan (or decomposed into sub-phases).\n\n---\n\n## 5. Handoff to Implementation\n\nOnce the user approves the written specification:\n* Invoke `writing-plans` (or `phase-implementation-planner`) to generate a step-by-step implementation plan.\n* Transition cleanly from architecture mode to execution mode.\n","# Stress-Tested Architecture: Brainstorm & Grill\n\nTurn ideas into resilient, production-ready system architectures through collaborative ideation combined with adversarial stress-testing.\n\n## The Core Principle\n\n> **Explore openly, grill ruthlessly, lock before building.**  \n> Never rubber-stamp user assumptions. Never debate without presenting clear recommendations.\n\n\u003CHARD-GATE>\nDo NOT write code, generate boilerplate, or take implementation actions until your human partner has explicitly approved the design.\n\u003C\u002FHARD-GATE>\n\n---\n\n## 1. Request Classification\n\nBefore asking your first question, classify the request and state it out loud:\n\n* **Spike:** Feasibility question (*\"Is it possible to...\"*, *\"Can we test if...\"*). Present question + 2-3 sentence probe plan, get approval, test as cheaply as possible, report recommendation. Everything built remains throwaway.\n* **Bounded:** Well-scoped change to existing flow in this repository (e.g. new flag, one endpoint). Ask clarifying questions, present a short design in chat (approach, affected files, tests), and STOP until explicit approval is granted.\n* **Architectural:** New subsystems, multi-module features, altered API boundaries, or complex refactoring. Follow the full Design Tree & Grilling process below.\n\n*Rule:* When in doubt, choose the heavier path. Hidden complexity discovered mid-task immediately upgrades the path.\n\n---\n\n## 2. The Design Tree & Grilling Protocol\n\nArchitectures are trees of decisions: foundational choices branch into secondary implementation details.\n\n### The Frontier & Structured Rounds\nAsk only questions on the **frontier** (decisions whose prerequisites are already settled). Do not ask questions that depend on unanswered questions.\n\nFormat each round clearly with options and recommendations:\n\n```markdown\n❓ **Q1 - [Decision Title]**: [Context and concrete trade-offs between Option A and Option B]\n➡️ **Recommendation**: [Recommended choice and why, noting edge case \u002F scale trade-offs]\n\n---\n\n❓ **Q2 - [Decision Title]**: [Context and options]\n➡️ **Recommendation**: [Recommended choice]\n```\n\n### Fact-Finding vs. Decision-Making\n* **Agent's Job (Facts):** Inspect existing codebase, search documentation, review dependencies, and check environment constraints. Never ask the user for facts you can discover yourself.\n* **User's Job (Decisions):** Decide business priorities, risk tolerance, and directional choices from your recommended options.\n\n---\n\n## 3. The 5 Grilling Vectors (Adversarial Scrutiny)\n\nEvery proposed architecture must be stress-tested against these 5 failure vectors before finalizing:\n\n1. **Failure Modes & Resilience:** What happens if the network drops, third-party API times out, DB locks, or partial writes occur? Where is the circuit breaker \u002F retry policy?\n2. **Scale & Concurrency:** How does this behave at 10x or 100x volume? Are there race conditions, memory leaks, or N+1 query bottlenecks?\n3. **Seams & Isolation:** Can each unit be tested in total isolation without booting the universe? Are internal implementation details leaking across boundaries?\n4. **YAGNI & Simplicity (Ponytail Lens):** Are there unrequested abstractions (interfaces with 1 implementation, speculative factories)? What can be deleted?\n5. **Rollback & Blast Radius:** If a deployment fails or data is corrupted, how is state restored safely?\n\n---\n\n## 4. Architectural Spec & Self-Review\n\nWhen the frontier is resolved, write the design specification to:\n`docs\u002Fspecs\u002FYYYY-MM-DD-\u003Ctopic>-design.md`\n\n### Mandatory Spec Sections:\n1. **Context & Goals:** Problem statement, in-scope, and explicit out-of-scope.\n2. **System Architecture & Data Flow:** Component boundaries, contracts, sequence.\n3. **Failure Handling & Edge Cases:** Fallbacks, retries, and data consistency.\n4. **Testing Strategy:** Unit seams, integration harnesses, and verification plan.\n5. **Alternative Approaches Rejected:** Why simpler or competing designs were discarded.\n\n### Spec Self-Review Gate:\nBefore showing the spec to the user, execute an inline self-review:\n* [ ] **Placeholder scan:** No \"TODO\", \"TBD\", or vague requirements.\n* [ ] **Consistency check:** Architecture matches data flow and component responsibilities.\n* [ ] **Ambiguity check:** All critical requirements are unambiguous and verifiable.\n* [ ] **Scope check:** Sized appropriately for an implementation plan (or decomposed into sub-phases).\n\n---\n\n## 5. Handoff to Implementation\n\nOnce the user approves the written specification:\n* Invoke `writing-plans` (or `phase-implementation-planner`) to generate a step-by-step implementation plan.\n* Transition cleanly from architecture mode to execution mode.\n",{"name":5,"license":15,"description":24},"Combines 'brainstorming' and 'grilling'. Interactive design, RFC, and system architecture workflow that couples collaborative exploration with adversarial stress-testing. Features Three-Path Classification (Spike, Bounded, Architectural), a branching Design Tree, structured Grilling Rounds (The Frontier) with recommended answers, and rigorous scrutiny on failure modes, scale, and trade-offs before locking specifications. Triggers on \u002Fstress-tested-architecture, \u002Fgrill-architecture, \"design architecture\", \"brainstorm and grill\", \"stress test plan\", or \"system design RFC\".\n","main","4e771b8ea3d217398b89087775ed5bffdc9bdc4b","https:\u002F\u002Fgithub.com\u002FZEenoz\u002FAntigravity-skills","https:\u002F\u002Fgithub.com\u002FZEenoz","Yo, It's me ZEenoz from CPE RMUTT! 👌","2026-11-01 12:12:12",{"source":8,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add ZEenoz\u002FAntigravity-skills --skill stress-tested-architecture",{"tool":37,"command":38},"bunx","bunx skills add ZEenoz\u002FAntigravity-skills --skill stress-tested-architecture",{"tool":40,"command":41},"pnpm","pnpm dlx skills add ZEenoz\u002FAntigravity-skills --skill stress-tested-architecture","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FZEenoz\u002FAntigravity-skills\u002Fblob\u002Fmain\u002Fstress-tested-architecture\u002FSKILL.md",true,[],[46,55,64,71,79,86],{"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":50,"licenseFileUrl":51,"sourceHtmlUrl":52,"categories":53,"keywords":54,"publishedAt":19},"01M72G1JF15JC7MMKWGCTBVF9K","web-artifacts-builder","Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn\u002Fui). Use for complex artifacts requiring state management, routing, or shadcn\u002Fui components - not for simple single-file HTML\u002FJSX artifacts.","Apache-2.0","https:\u002F\u002Fgithub.com\u002FZEenoz\u002FAntigravity-skills\u002Fblob\u002Fmain\u002Fweb-artifacts-builder\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002FZEenoz\u002FAntigravity-skills\u002Fblob\u002Fmain\u002Fweb-artifacts-builder\u002FSKILL.md",[],[],{"skillNo":56,"name":57,"nameZh":6,"description":58,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":59,"licenseFileUrl":60,"sourceHtmlUrl":61,"categories":62,"keywords":63,"publishedAt":19},"01M72G0BQ49V2PR7A9HZ6J2DJV","task-observer","Monitors task execution for skill improvement opportunities: logs patterns, user corrections and methodology worth preserving to the workspace, turns them into skill updates in a weekly review, and flags repeating work as new skills. Use during ANY multi-step task, agentic workflow, or work session. Also triggers in post-task feedback discussions and when the user mentions skill observations, the observation log, or skill taxonomy. Also known as \"One Skill to Rule Them All\" — trigger on this phrase too. IMPORTANT: invoke this skill before the FIRST tool call of any session and before writing or proposing a plan — any turn that will involve a tool call counts. This sentence is the session-start trigger and the only activation layer that survives an unreachable config file; pair it with a CLAUDE.md instruction or a session-start hook (references\u002Fenvironments.md). A subagent dispatched by a session already running it does not run it: it writes nothing and puts its findings in its report.","CC-BY-4.0","https:\u002F\u002Fgithub.com\u002FZEenoz\u002FAntigravity-skills\u002Fblob\u002Fmain\u002Ftask-observer\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FZEenoz\u002FAntigravity-skills\u002Fblob\u002Fmain\u002Ftask-observer\u002FSKILL.md",[],[],{"skillNo":65,"name":66,"nameZh":6,"description":67,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":68,"categories":69,"keywords":70,"publishedAt":19},"01M72G03AMHVRC5XFZFKP9R7YM","superpowers-ponytail","Combines 'using-superpowers' and 'ponytail'. Enforces disciplined skill invocation BEFORE any response or action (brainstorming, systematic-debugging, process skills first) while strictly executing with Ponytail's ruthless simplicity (YAGNI, minimal diff, stdlib\u002Fnative first, no boilerplate, shortest working path). Use on ANY coding, debugging, or architecture task where you want both strict skill-first workflow and lazy minimal-diff execution. Also triggers on \u002Fsuperpowers-ponytail, \u002Fponytail-superpowers, \"ponytail superpowers\", \"lazy superpowers\", or whenever combining disciplined process with minimalist code.","https:\u002F\u002Fgithub.com\u002FZEenoz\u002FAntigravity-skills\u002Fblob\u002Fmain\u002Fsuperpowers-ponytail\u002FSKILL.md",[],[],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":50,"licenseFileUrl":75,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":19},"01M72FZPTQGZ9VYRDB0K9W2VNP","skill-creator","Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.","https:\u002F\u002Fgithub.com\u002FZEenoz\u002FAntigravity-skills\u002Fblob\u002Fmain\u002Fskill-creator\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002FZEenoz\u002FAntigravity-skills\u002Fblob\u002Fmain\u002Fskill-creator\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},"01M72FYPBH41AZCZGM51HKXNQ9","precision-diagnostics","Combines 'systematic-debugging' and 'diagnosing-bugs'. Strict multi-phase root-cause diagnosis protocol for hard bugs, intermittent failures, test breakages, and performance regressions. Enforces building a tight deterministic feedback loop (repro), multi-boundary instrumentation, ranked falsifiable hypotheses, and minimal root-cause fixes with regression tests before any code edits. Triggers on \u002Fprecision-diagnostics, \u002Fdiagnose, \"diagnose bug\", \"debug hard bug\", \"systematic debug\", or any persistent\u002Fintermittent software failure.","https:\u002F\u002Fgithub.com\u002FZEenoz\u002FAntigravity-skills\u002Fblob\u002Fmain\u002Fprecision-diagnostics\u002FSKILL.md",[],[],{"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},"01M72FYFHVHCAN8E9SJ8F8H616","pptx-generator","Generate, edit, and read PowerPoint presentations. Create from scratch with PptxGenJS (cover, TOC, content, section divider, summary slides), edit existing PPTX via XML workflows, or extract text with markitdown. Triggers: PPT, PPTX, PowerPoint, presentation, slide, deck, slides.","https:\u002F\u002Fgithub.com\u002FZEenoz\u002FAntigravity-skills\u002Fblob\u002Fmain\u002Fpptx-generator\u002FSKILL.md",[],[]]