[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M76VY5WYZD37M0Z26FFQKTWD":3,"skill-same:01M76VY5WYZD37M0Z26FFQKTWD":95},{"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":26,"commitSha":27,"skillDirectory":28,"forksCount":14,"repositoryHtmlUrl":29,"repositoryHomepageUrl":6,"ownerHtmlUrl":30,"ownerBlogUrl":31,"ownerDescription":32,"updatedAt":33,"install":34,"resources":47},"01M76VY5WYZD37M0Z26FFQKTWD","ag-risk-evidence-pack",null,"Define and generate the manual-first evidence pack for high-risk work. Covers 6 high-risk class definitions and the 5-artifact schema required before finalizing, pushing, or handing off.","ngxccc\u002Fagent-skills-kit","ngxccc","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F163379246?v=4","01M758XVG64QK26AGK0WKB26TB","Ngoc Tran","01M758XVHB8J6MHV0YTBVDBXCA",0,"MIT","https:\u002F\u002Fgithub.com\u002Fngxccc\u002Fagent-skills-kit\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fag-risk-evidence-pack\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: ag-risk-evidence-pack\ndescription: \"Define and generate the manual-first evidence pack for high-risk work. Covers 6 high-risk class definitions and the 5-artifact schema required before finalizing, pushing, or handing off.\"\ntrigger_keywords: risk evidence, high-risk pack, evidence pack, risk gate, adversarial validation\nlayer: contract\n---\n\n# ag-risk-evidence-pack\n\n## When to Apply\n\nUse this skill when working with ag-risk-evidence-pack workflows, tasks, or system specifications.\n\n## How to Use\n\nRefer to the workflow instructions and command references detailed below.\n\n> **Output style:** Follow `process\u002Fdevelopment-protocols\u002Fcommunication-standards.md` — answer-first, plain language, no unexplained jargon, TL;DR on long responses.\n\nGenerate and validate the manual-first evidence pack required before finalizing, pushing, or handing off high-risk implementation work.\n\n## When To Invoke\n\n- **VALIDATE Layer 1 security surface check** — when the plan touches a high-risk class, flag the need for an evidence pack before routing to execute-agent.\n- **EXECUTE before marking high-risk work complete** — execute-agent must produce or verify the evidence pack exists before reporting DONE on any high-risk class.\n- **code-reviewer as pre-PR quality gate** — code-reviewer checks for the evidence pack presence before approving changes that touch a high-risk surface.\n\n## 6 High-Risk Class Definitions\n\nFrom `process\u002Fdevelopment-protocols\u002Forchestration.md` (\"High-Risk Execution Handoff\") and `process\u002Fdevelopment-protocols\u002Fimplementation-standards.md` (\"Risky Work Evidence Contract\") — both sources agree:\n\n1. **auth or identity** — authentication flows, session tokens, user identity resolution, Clerk JWT handling, or any surface that determines who the caller is.\n2. **billing or credits** — billing events, credit balance mutations, Stripe charge flows, OpenRouter credit accounting, credit transaction records, or subscription state changes.\n3. **schema\u002Fdata migration or destructive data mutation** — Prisma migrations, raw SQL mutations, destructive writes that delete or overwrite persistent data, or schema changes to existing models.\n4. **public API or external contract changes** — tRPC procedure signature changes visible to the frontend, Hono route contract changes consumed by external callers, webhook shape changes, or any API surface that third parties or the client app depend on.\n5. **deploy\u002Fruntime\u002Fcontainer\u002Fproxy\u002Fgateway behavior** — Dockerfile changes, supervisord config, start.sh, container service ports, Bun server entry, Hono route registration, Caddy proxy config, worker-node provisioning, or any change that affects how a running service starts or routes traffic.\n6. **permission, secret, or trust-boundary logic** — instance token gating, `verifyInstanceOwnership`, BYOK secret fetch paths, MITM proxy key injection, Bright Data credential handling, or any logic that controls what a caller is allowed to access.\n\n## 5-Artifact Schema\n\nPer **task-folder artefact colocation**, all artifacts go inside the selected plan's task folder (e.g. `process\u002Ffeatures\u002F{feature}\u002Factive\u002F{slug}_{date}\u002Fharness\u002F` or `process\u002Fgeneral-plans\u002Factive\u002F{slug}_{date}\u002Fharness\u002F`), so the whole pack moves with the plan as a unit. Legacy path `reports\u002Fharness\u002F` is deprecated for new writes; never write the pack to a sibling `reports\u002F` dir or any ad-hoc location. The validator script lives at `.claude\u002Fskills\u002Fag-risk-evidence-pack\u002Fscripts\u002Fvalidate-risk-artifacts.mjs`.\n\n### 1. `risk-gate.json`\n\nRecords the risk class, work description, and approver identity before work begins or is finalized.\n\n```json\n{\n  \"riskClass\": \"\u003Cone of the 6 classes above>\",\n  \"workDescription\": \"\u003Cshort description of the change>\",\n  \"approver\": \"\u003Cperson or agent that reviewed the risk classification>\",\n  \"mustStopBeforeFinalize\": true\n}\n```\n\n### 2. `context-snippets.json`\n\nRelevant code snippets with exact file and line citations for every surface the change touches in the high-risk class.\n\n```json\n{\n  \"snippets\": [\n    {\n      \"file\": \"packages\u002Fapi\u002Fsrc\u002Frouter\u002Fbilling.ts\",\n      \"lines\": \"120-145\",\n      \"description\": \"verifyInstanceOwnership call before secret read\",\n      \"content\": \"\u003Cexcerpt>\"\n    }\n  ]\n}\n```\n\n### 3. `verification.json`\n\nDocuments every verification step taken and its result. Steps must cover both the happy path and at least one failure or boundary case.\n\n```json\n{\n  \"steps\": [\n    {\n      \"step\": \"\u003Cwhat was verified>\",\n      \"command\": \"\u003Ccommand run, if applicable>\",\n      \"result\": \"PASS | FAIL | SKIP\",\n      \"notes\": \"\u003Cobservations>\"\n    }\n  ]\n}\n```\n\n### 4. `review-decision.json`\n\nThe explicit reviewer decision record. Must contain APPROVE or REJECT with a written rationale — no implicit approvals.\n\n```json\n{\n  \"reviewer\": \"\u003Cname or agent>\",\n  \"decision\": \"APPROVE | REJECT\",\n  \"rationale\": \"\u003Cwritten reason>\",\n  \"timestamp\": \"\u003CISO 8601 date>\"\n}\n```\n\n### 5. `adversarial-validation.json`\n\nRequired when the path is high-risk or attack-sensitive (e.g. auth bypass, privilege escalation, secret exfiltration). Documents adversarial scenarios considered and whether each was ruled out.\n\n```json\n{\n  \"scenarios\": [\n    {\n      \"scenario\": \"\u003Cattack or misuse description>\",\n      \"ruled_out\": true,\n      \"rationale\": \"\u003Cwhy this path is not exploitable>\"\n    }\n  ]\n}\n```\n\n## Auto-Stop Rule\n\nIf risk is `high`, do not treat the work as ready to finalize until the evidence pack exists and the reviewer decision is recorded.\n\nIf the evidence pack is missing, say so **explicitly** — do not proceed silently, do not imply the work is proven, and do not report DONE.\n\nVerbatim from `implementation-standards.md`:\n\n> Auto-stop rule:\n>\n> - if risk is `high`, do not treat the work as ready to finalize until the evidence pack exists and the reviewer decision is recorded\n> - if the evidence pack is missing, say so explicitly instead of implying the work is proven\n>\n> This contract is manual-first and opt-in by risk class. It is not a default blocking hook.\n\nVerbatim from `orchestration.md`:\n\n> If the risk gate says `mustStopBeforeFinalize: true`, do not imply the work is fully proven until the pack exists and the reviewer decision is present.\n> Keep this manual-first. Do not invent a blocking hook or alternate workflow owner.\n\n## Validation Checklist\n\nSteps to confirm each artifact is complete before handoff:\n\n- [ ] `risk-gate.json` populated with correct risk class, work description, approver, and `mustStopBeforeFinalize` flag\n- [ ] `context-snippets.json` includes all affected file:line citations for every surface touching the high-risk class\n- [ ] `verification.json` documents each test step and result, covering happy path and at least one boundary\u002Ffailure case\n- [ ] `review-decision.json` has explicit APPROVE or REJECT with written rationale and timestamp — no implicit approvals\n- [ ] `adversarial-validation.json` present if the path is attack-sensitive (auth bypass, privilege escalation, secret exfiltration, trust-boundary violation)\n\n## High-Risk Work Evidence Contract\n\nVerbatim from `process\u002Fdevelopment-protocols\u002Fimplementation-standards.md` (\"Risky Work Evidence Contract\"):\n\n> For high-risk work, use a manual-first evidence pack before calling the change ready for finalize, push, or human handoff.\n>\n> High-risk classes include:\n>\n> - auth or identity flows\n> - billing, payments, or credit accounting\n> - schema\u002Fdata migrations or destructive writes\n> - public API or external contract changes\n> - deploy\u002Fruntime\u002Fcontainer\u002Fproxy\u002Fgateway behavior\n> - permission, secret, or trust-boundary logic\n>\n> Preferred artifact set inside the selected plan's task folder (`{slug}_{date}\u002Fharness\u002F`):\n>\n> - `risk-gate.json`\n> - `context-snippets.json`\n> - `verification.json`\n> - `review-decision.json`\n> - `adversarial-validation.json` for high-risk or adversarial paths\n>\n> Auto-stop rule:\n>\n> - if risk is `high`, do not treat the work as ready to finalize until the evidence pack exists and the reviewer decision is recorded\n> - if the evidence pack is missing, say so explicitly instead of implying the work is proven\n>\n> This contract is manual-first and opt-in by risk class. It is not a default blocking hook.\n\n## References\n\n- [process\u002Fcontext\u002Fall-context.md](process\u002Fcontext\u002Fall-context.md)\n","# ag-risk-evidence-pack\n\n## When to Apply\n\nUse this skill when working with ag-risk-evidence-pack workflows, tasks, or system specifications.\n\n## How to Use\n\nRefer to the workflow instructions and command references detailed below.\n\n> **Output style:** Follow `process\u002Fdevelopment-protocols\u002Fcommunication-standards.md` — answer-first, plain language, no unexplained jargon, TL;DR on long responses.\n\nGenerate and validate the manual-first evidence pack required before finalizing, pushing, or handing off high-risk implementation work.\n\n## When To Invoke\n\n- **VALIDATE Layer 1 security surface check** — when the plan touches a high-risk class, flag the need for an evidence pack before routing to execute-agent.\n- **EXECUTE before marking high-risk work complete** — execute-agent must produce or verify the evidence pack exists before reporting DONE on any high-risk class.\n- **code-reviewer as pre-PR quality gate** — code-reviewer checks for the evidence pack presence before approving changes that touch a high-risk surface.\n\n## 6 High-Risk Class Definitions\n\nFrom `process\u002Fdevelopment-protocols\u002Forchestration.md` (\"High-Risk Execution Handoff\") and `process\u002Fdevelopment-protocols\u002Fimplementation-standards.md` (\"Risky Work Evidence Contract\") — both sources agree:\n\n1. **auth or identity** — authentication flows, session tokens, user identity resolution, Clerk JWT handling, or any surface that determines who the caller is.\n2. **billing or credits** — billing events, credit balance mutations, Stripe charge flows, OpenRouter credit accounting, credit transaction records, or subscription state changes.\n3. **schema\u002Fdata migration or destructive data mutation** — Prisma migrations, raw SQL mutations, destructive writes that delete or overwrite persistent data, or schema changes to existing models.\n4. **public API or external contract changes** — tRPC procedure signature changes visible to the frontend, Hono route contract changes consumed by external callers, webhook shape changes, or any API surface that third parties or the client app depend on.\n5. **deploy\u002Fruntime\u002Fcontainer\u002Fproxy\u002Fgateway behavior** — Dockerfile changes, supervisord config, start.sh, container service ports, Bun server entry, Hono route registration, Caddy proxy config, worker-node provisioning, or any change that affects how a running service starts or routes traffic.\n6. **permission, secret, or trust-boundary logic** — instance token gating, `verifyInstanceOwnership`, BYOK secret fetch paths, MITM proxy key injection, Bright Data credential handling, or any logic that controls what a caller is allowed to access.\n\n## 5-Artifact Schema\n\nPer **task-folder artefact colocation**, all artifacts go inside the selected plan's task folder (e.g. `process\u002Ffeatures\u002F{feature}\u002Factive\u002F{slug}_{date}\u002Fharness\u002F` or `process\u002Fgeneral-plans\u002Factive\u002F{slug}_{date}\u002Fharness\u002F`), so the whole pack moves with the plan as a unit. Legacy path `reports\u002Fharness\u002F` is deprecated for new writes; never write the pack to a sibling `reports\u002F` dir or any ad-hoc location. The validator script lives at `.claude\u002Fskills\u002Fag-risk-evidence-pack\u002Fscripts\u002Fvalidate-risk-artifacts.mjs`.\n\n### 1. `risk-gate.json`\n\nRecords the risk class, work description, and approver identity before work begins or is finalized.\n\n```json\n{\n  \"riskClass\": \"\u003Cone of the 6 classes above>\",\n  \"workDescription\": \"\u003Cshort description of the change>\",\n  \"approver\": \"\u003Cperson or agent that reviewed the risk classification>\",\n  \"mustStopBeforeFinalize\": true\n}\n```\n\n### 2. `context-snippets.json`\n\nRelevant code snippets with exact file and line citations for every surface the change touches in the high-risk class.\n\n```json\n{\n  \"snippets\": [\n    {\n      \"file\": \"packages\u002Fapi\u002Fsrc\u002Frouter\u002Fbilling.ts\",\n      \"lines\": \"120-145\",\n      \"description\": \"verifyInstanceOwnership call before secret read\",\n      \"content\": \"\u003Cexcerpt>\"\n    }\n  ]\n}\n```\n\n### 3. `verification.json`\n\nDocuments every verification step taken and its result. Steps must cover both the happy path and at least one failure or boundary case.\n\n```json\n{\n  \"steps\": [\n    {\n      \"step\": \"\u003Cwhat was verified>\",\n      \"command\": \"\u003Ccommand run, if applicable>\",\n      \"result\": \"PASS | FAIL | SKIP\",\n      \"notes\": \"\u003Cobservations>\"\n    }\n  ]\n}\n```\n\n### 4. `review-decision.json`\n\nThe explicit reviewer decision record. Must contain APPROVE or REJECT with a written rationale — no implicit approvals.\n\n```json\n{\n  \"reviewer\": \"\u003Cname or agent>\",\n  \"decision\": \"APPROVE | REJECT\",\n  \"rationale\": \"\u003Cwritten reason>\",\n  \"timestamp\": \"\u003CISO 8601 date>\"\n}\n```\n\n### 5. `adversarial-validation.json`\n\nRequired when the path is high-risk or attack-sensitive (e.g. auth bypass, privilege escalation, secret exfiltration). Documents adversarial scenarios considered and whether each was ruled out.\n\n```json\n{\n  \"scenarios\": [\n    {\n      \"scenario\": \"\u003Cattack or misuse description>\",\n      \"ruled_out\": true,\n      \"rationale\": \"\u003Cwhy this path is not exploitable>\"\n    }\n  ]\n}\n```\n\n## Auto-Stop Rule\n\nIf risk is `high`, do not treat the work as ready to finalize until the evidence pack exists and the reviewer decision is recorded.\n\nIf the evidence pack is missing, say so **explicitly** — do not proceed silently, do not imply the work is proven, and do not report DONE.\n\nVerbatim from `implementation-standards.md`:\n\n> Auto-stop rule:\n>\n> - if risk is `high`, do not treat the work as ready to finalize until the evidence pack exists and the reviewer decision is recorded\n> - if the evidence pack is missing, say so explicitly instead of implying the work is proven\n>\n> This contract is manual-first and opt-in by risk class. It is not a default blocking hook.\n\nVerbatim from `orchestration.md`:\n\n> If the risk gate says `mustStopBeforeFinalize: true`, do not imply the work is fully proven until the pack exists and the reviewer decision is present.\n> Keep this manual-first. Do not invent a blocking hook or alternate workflow owner.\n\n## Validation Checklist\n\nSteps to confirm each artifact is complete before handoff:\n\n- [ ] `risk-gate.json` populated with correct risk class, work description, approver, and `mustStopBeforeFinalize` flag\n- [ ] `context-snippets.json` includes all affected file:line citations for every surface touching the high-risk class\n- [ ] `verification.json` documents each test step and result, covering happy path and at least one boundary\u002Ffailure case\n- [ ] `review-decision.json` has explicit APPROVE or REJECT with written rationale and timestamp — no implicit approvals\n- [ ] `adversarial-validation.json` present if the path is attack-sensitive (auth bypass, privilege escalation, secret exfiltration, trust-boundary violation)\n\n## High-Risk Work Evidence Contract\n\nVerbatim from `process\u002Fdevelopment-protocols\u002Fimplementation-standards.md` (\"Risky Work Evidence Contract\"):\n\n> For high-risk work, use a manual-first evidence pack before calling the change ready for finalize, push, or human handoff.\n>\n> High-risk classes include:\n>\n> - auth or identity flows\n> - billing, payments, or credit accounting\n> - schema\u002Fdata migrations or destructive writes\n> - public API or external contract changes\n> - deploy\u002Fruntime\u002Fcontainer\u002Fproxy\u002Fgateway behavior\n> - permission, secret, or trust-boundary logic\n>\n> Preferred artifact set inside the selected plan's task folder (`{slug}_{date}\u002Fharness\u002F`):\n>\n> - `risk-gate.json`\n> - `context-snippets.json`\n> - `verification.json`\n> - `review-decision.json`\n> - `adversarial-validation.json` for high-risk or adversarial paths\n>\n> Auto-stop rule:\n>\n> - if risk is `high`, do not treat the work as ready to finalize until the evidence pack exists and the reviewer decision is recorded\n> - if the evidence pack is missing, say so explicitly instead of implying the work is proven\n>\n> This contract is manual-first and opt-in by risk class. It is not a default blocking hook.\n\n## References\n\n- [process\u002Fcontext\u002Fall-context.md](process\u002Fcontext\u002Fall-context.md)\n",{"name":5,"layer":24,"description":7,"trigger_keywords":25},"contract","risk evidence, high-risk pack, evidence pack, risk gate, adversarial validation","main","1ef0dcd00fe806a8dc4e0b7173b9db967c3ab274",".claude\u002Fskills\u002Fag-risk-evidence-pack","https:\u002F\u002Fgithub.com\u002Fngxccc\u002Fagent-skills-kit","https:\u002F\u002Fgithub.com\u002Fngxccc","https:\u002F\u002Fngxccc.github.io","Make it work, make it right, make it fast.","2026-08-02 20:59:07",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":46},[36,39,42],{"tool":37,"command":38},"npx","npx skills add ngxccc\u002Fagent-skills-kit --skill ag-risk-evidence-pack",{"tool":40,"command":41},"bunx","bunx skills add ngxccc\u002Fagent-skills-kit --skill ag-risk-evidence-pack",{"tool":43,"command":44},"pnpm","pnpm dlx skills add ngxccc\u002Fagent-skills-kit --skill ag-risk-evidence-pack","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fngxccc\u002Fagent-skills-kit\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fag-risk-evidence-pack\u002FSKILL.md",true,[48,54,60,64,67,71,75,78,81,84,87,91],{"path":49,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":52,"sourceHtmlUrl":53},"README.md","REFERENCE","参考文档",2393,"https:\u002F\u002Fgithub.com\u002Fngxccc\u002Fagent-skills-kit\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fag-risk-evidence-pack\u002FREADME.md",{"path":55,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":58,"sourceHtmlUrl":59},"scripts\u002Ffixtures\u002Fvalidate-evidence-pack\u002Ffail\u002Fharness\u002Fcontext-snippets.json","SCRIPT","脚本",19,"https:\u002F\u002Fgithub.com\u002Fngxccc\u002Fagent-skills-kit\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fag-risk-evidence-pack\u002Fscripts\u002Ffixtures\u002Fvalidate-evidence-pack\u002Ffail\u002Fharness\u002Fcontext-snippets.json",{"path":61,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":62,"sourceHtmlUrl":63},"scripts\u002Ffixtures\u002Fvalidate-evidence-pack\u002Ffail\u002Fharness\u002Freview-decision.json",124,"https:\u002F\u002Fgithub.com\u002Fngxccc\u002Fagent-skills-kit\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fag-risk-evidence-pack\u002Fscripts\u002Ffixtures\u002Fvalidate-evidence-pack\u002Ffail\u002Fharness\u002Freview-decision.json",{"path":65,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":62,"sourceHtmlUrl":66},"scripts\u002Ffixtures\u002Fvalidate-evidence-pack\u002Ffail\u002Fharness\u002Frisk-gate.json","https:\u002F\u002Fgithub.com\u002Fngxccc\u002Fagent-skills-kit\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fag-risk-evidence-pack\u002Fscripts\u002Ffixtures\u002Fvalidate-evidence-pack\u002Ffail\u002Fharness\u002Frisk-gate.json",{"path":68,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":69,"sourceHtmlUrl":70},"scripts\u002Ffixtures\u002Fvalidate-evidence-pack\u002Ffail\u002Fharness\u002Fverification.json",16,"https:\u002F\u002Fgithub.com\u002Fngxccc\u002Fagent-skills-kit\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fag-risk-evidence-pack\u002Fscripts\u002Ffixtures\u002Fvalidate-evidence-pack\u002Ffail\u002Fharness\u002Fverification.json",{"path":72,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":73,"sourceHtmlUrl":74},"scripts\u002Ffixtures\u002Fvalidate-evidence-pack\u002Fpass\u002Fharness\u002Fadversarial-validation.json",20,"https:\u002F\u002Fgithub.com\u002Fngxccc\u002Fagent-skills-kit\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fag-risk-evidence-pack\u002Fscripts\u002Ffixtures\u002Fvalidate-evidence-pack\u002Fpass\u002Fharness\u002Fadversarial-validation.json",{"path":76,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":58,"sourceHtmlUrl":77},"scripts\u002Ffixtures\u002Fvalidate-evidence-pack\u002Fpass\u002Fharness\u002Fcontext-snippets.json","https:\u002F\u002Fgithub.com\u002Fngxccc\u002Fagent-skills-kit\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fag-risk-evidence-pack\u002Fscripts\u002Ffixtures\u002Fvalidate-evidence-pack\u002Fpass\u002Fharness\u002Fcontext-snippets.json",{"path":79,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":62,"sourceHtmlUrl":80},"scripts\u002Ffixtures\u002Fvalidate-evidence-pack\u002Fpass\u002Fharness\u002Freview-decision.json","https:\u002F\u002Fgithub.com\u002Fngxccc\u002Fagent-skills-kit\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fag-risk-evidence-pack\u002Fscripts\u002Ffixtures\u002Fvalidate-evidence-pack\u002Fpass\u002Fharness\u002Freview-decision.json",{"path":82,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":62,"sourceHtmlUrl":83},"scripts\u002Ffixtures\u002Fvalidate-evidence-pack\u002Fpass\u002Fharness\u002Frisk-gate.json","https:\u002F\u002Fgithub.com\u002Fngxccc\u002Fagent-skills-kit\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fag-risk-evidence-pack\u002Fscripts\u002Ffixtures\u002Fvalidate-evidence-pack\u002Fpass\u002Fharness\u002Frisk-gate.json",{"path":85,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":69,"sourceHtmlUrl":86},"scripts\u002Ffixtures\u002Fvalidate-evidence-pack\u002Fpass\u002Fharness\u002Fverification.json","https:\u002F\u002Fgithub.com\u002Fngxccc\u002Fagent-skills-kit\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fag-risk-evidence-pack\u002Fscripts\u002Ffixtures\u002Fvalidate-evidence-pack\u002Fpass\u002Fharness\u002Fverification.json",{"path":88,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":89,"sourceHtmlUrl":90},"scripts\u002Fvalidate-evidence-pack.mjs",2115,"https:\u002F\u002Fgithub.com\u002Fngxccc\u002Fagent-skills-kit\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fag-risk-evidence-pack\u002Fscripts\u002Fvalidate-evidence-pack.mjs",{"path":92,"resourceType":56,"resourceTypeDesc":57,"sizeBytes":93,"sourceHtmlUrl":94},"scripts\u002Fvalidate-risk-artifacts.mjs",2729,"https:\u002F\u002Fgithub.com\u002Fngxccc\u002Fagent-skills-kit\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fag-risk-evidence-pack\u002Fscripts\u002Fvalidate-risk-artifacts.mjs",[96,103,110,117,124,131],{"skillNo":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":102,"publishedAt":19},"01M76W3C8X6Q5DS0364KQT7W7A","zustand","Rules and standards for state management using Zustand in React and Next.js. Use when implementing client-side stores, persistence with localStorage, or preventing SSR hydration mismatch.","https:\u002F\u002Fgithub.com\u002Fngxccc\u002Fagent-skills-kit\u002Fblob\u002Fmain\u002Fskills\u002F.curated\u002Fzustand\u002FSKILL.md",[],[],{"skillNo":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":109,"publishedAt":19},"01M76W39FJGES309VAH7SFWA9Y","zod","Zod v4 schema validation best practices. Use when defining schemas, utilizing safeParse, or customizing error messages.","https:\u002F\u002Fgithub.com\u002Fngxccc\u002Fagent-skills-kit\u002Fblob\u002Fmain\u002Fskills\u002F.curated\u002Fzod\u002FSKILL.md",[],[],{"skillNo":111,"name":112,"nameZh":6,"description":113,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":114,"categories":115,"keywords":116,"publishedAt":19},"01M76W36HTYA4BR5FKCWMX1RFR","upstash-ratelimit","Rules, standards, and references for rate limiting in serverless environments using Upstash Ratelimit. Use when implementing rate limiting, configuring Upstash Redis, or handling request blocking.","https:\u002F\u002Fgithub.com\u002Fngxccc\u002Fagent-skills-kit\u002Fblob\u002Fmain\u002Fskills\u002F.curated\u002Fupstash-ratelimit\u002FSKILL.md",[],[],{"skillNo":118,"name":119,"nameZh":6,"description":120,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":121,"categories":122,"keywords":123,"publishedAt":19},"01M76W32H4PS01WFRS7FNPK2G1","ui-design","UI\u002FUX and frontend design best practices guidelines (formerly frontend-design). This skill should be used when writing, reviewing, or designing frontend code to ensure accessibility, performance, and usability. Triggers on tasks involving HTML structure, CSS styling, responsive layouts, form design, animations, or accessibility improvements.","https:\u002F\u002Fgithub.com\u002Fngxccc\u002Fagent-skills-kit\u002Fblob\u002Fmain\u002Fskills\u002F.curated\u002Fui-design\u002FSKILL.md",[],[],{"skillNo":125,"name":126,"nameZh":6,"description":127,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":128,"categories":129,"keywords":130,"publishedAt":19},"01M76W2YAP6RK8N0EVWFG54VD7","typescript","TypeScript performance, tsconfig, type errors, async patterns — triggered when the user asks to \"optimize TypeScript performance\", \"speed up tsc compilation\", \"configure tsconfig.json\", \"fix type errors\", \"improve async patterns\", or encounters TS errors (TS2322, TS2339, \"is not assignable to\"). Also triggers on .ts, .tsx, .d.ts file work involving type definitions, module organization, or memory management. Does NOT cover TypeScript basics, framework-specific patterns, or testing.","https:\u002F\u002Fgithub.com\u002Fngxccc\u002Fagent-skills-kit\u002Fblob\u002Fmain\u002Fskills\u002F.curated\u002Ftypescript\u002FSKILL.md",[],[],{"skillNo":132,"name":133,"nameZh":6,"description":134,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":135,"categories":136,"keywords":137,"publishedAt":19},"01M76W2RMAZNNJQ2HECH3X6ZSH","typescript-refactor","TypeScript and TSX refactoring and modernization guidelines from a principal specialist perspective, current to TypeScript 6.0 and React 19. This skill should be used when refactoring, reviewing, or modernizing TypeScript or React\u002FTSX code for type safety, compiler performance, and idiomatic patterns. Triggers on tasks involving type architecture, narrowing, generics, discriminated unions, error handling, React component and hook typing, or migration to modern TypeScript features (satisfies, using, const type parameters, inferred type predicates, isolatedDeclarations, erasable syntax, import attributes).","https:\u002F\u002Fgithub.com\u002Fngxccc\u002Fagent-skills-kit\u002Fblob\u002Fmain\u002Fskills\u002F.curated\u002Ftypescript-refactor\u002FSKILL.md",[],[]]