[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7CT44J5MGG6G2Y6T8B5SFQ8":3,"skill-same:01M7CT44J5MGG6G2Y6T8B5SFQ8":148},{"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":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":6,"ownerHtmlUrl":29,"ownerBlogUrl":6,"ownerDescription":30,"updatedAt":31,"install":32,"resources":45},"01M7CT44J5MGG6G2Y6T8B5SFQ8","harness-creator",null,"Build, audit, and improve harnesses that make AI coding agents reliable: AGENTS.md\u002FCLAUDE.md instruction files, feature\u002Fstate tracking, verification gates, scope boundaries, session handoff, memory persistence, context budgets, tool-permission safety, and multi-agent coordination. Use this whenever a coding agent is unreliable across sessions — forgets context, drifts out of scope, claims \"done\" before tests pass, or starts each session inconsistently — or when creating or assessing AGENTS.md, CLAUDE.md, feature_list.json, init.sh, progress.md, or session-handoff files. Reach for it even if the user never says the word \"harness.\"","Hareesh-Reddy-9126\u002FPS044-SmartHire","Hareesh-Reddy-9126","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F203651565?v=4","01M7CRVG65SPPJE7CDJT0KRKKY","hareesh reddy","01M7CRVG6TEPD8RCR0GBDP5ANS",1,"MIT","https:\u002F\u002Fgithub.com\u002FHareesh-Reddy-9126\u002FPS044-SmartHire\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fharness-creator\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: harness-creator\ndescription: >-\n  Build, audit, and improve harnesses that make AI coding agents reliable: AGENTS.md\u002FCLAUDE.md\n  instruction files, feature\u002Fstate tracking, verification gates, scope boundaries, session\n  handoff, memory persistence, context budgets, tool-permission safety, and multi-agent\n  coordination. Use this whenever a coding agent is unreliable across sessions — forgets context,\n  drifts out of scope, claims \"done\" before tests pass, or starts each session inconsistently —\n  or when creating or assessing AGENTS.md, CLAUDE.md, feature_list.json, init.sh, progress.md, or\n  session-handoff files. Reach for it even if the user never says the word \"harness.\"\nlicense: MIT\n---\n\n# Harness Creator\n\nUse this skill to make a repository easier for coding agents to start, stay in scope, verify work, and resume across sessions. Keep the harness small enough that agents actually follow it.\n\nNot for model selection, prompt tuning in isolation, chat UI design, or general app architecture.\n\n## Core Model\n\nEvery useful coding-agent harness has five subsystems:\n\n| Subsystem | Minimal artifact | Purpose |\n|---|---|---|\n| Instructions | `AGENTS.md` or `CLAUDE.md` | Startup path, working rules, definition of done |\n| State | `feature_list.json`, `progress.md` | Current feature, status, evidence, next step |\n| Verification | `init.sh` or documented commands | Tests\u002Fchecks the agent must run before claiming done |\n| Scope | Feature dependencies and done criteria | Prevents overreach and half-finished work |\n| Lifecycle | `session-handoff.md`, end-of-session routine | Makes the next session restartable |\n\n## First Move\n\n1. Inspect what already exists: instruction files, feature\u002Fstate files, verification commands, docs, package manifests.\n2. Ask only for missing context that cannot be inferred safely: target agent, desired file name, tolerance for structure, and whether overwriting is allowed.\n3. Prefer a minimal harness first. Add memory, tool safety, multi-agent, or benchmark details only when the user's problem calls for them.\n\n## Common Tasks\n\n### Create a harness\n\nUse the bundled script when working on a local repository:\n\n```bash\nnode skills\u002Fharness-creator\u002Fscripts\u002Fcreate-harness.mjs --target \u002Fpath\u002Fto\u002Fproject\n```\n\nOptions:\n\n- `--agent-file CLAUDE.md` for Claude-oriented projects.\n- `--package-manager npm|pnpm|yarn|bun` when detection is wrong.\n- `--commands \"cmd one,cmd two\"` for custom verification.\n- `--force` only after confirming overwrites are acceptable.\n\nThen explain what was created and how the user should replace placeholder feature entries.\n\n### Audit an existing harness\n\nRun:\n\n```bash\nnode skills\u002Fharness-creator\u002Fscripts\u002Fvalidate-harness.mjs --target \u002Fpath\u002Fto\u002Fproject\n```\n\nReport the five subsystem scores, the lowest-scoring area, and the first 2-3 changes that would improve reliability. Treat the lowest score as a candidate bottleneck; confirm with failures, logs, or task outcomes before claiming causality.\n\n### Produce a report\n\nUse when the user wants a shareable assessment:\n\n```bash\nnode skills\u002Fharness-creator\u002Fscripts\u002Frender-assessment-html.mjs --target \u002Fpath\u002Fto\u002Fproject\nnode skills\u002Fharness-creator\u002Fscripts\u002Frun-benchmark.mjs --target \u002Fpath\u002Fto\u002Fproject --html \u002Fpath\u002Fto\u002Freport.html\n```\n\nBe clear that this is a structural benchmark. The benchmark first runs a self-check — it scaffolds a throwaway harness and validates it, proving the bundled scripts work end-to-end — then scores the target and eval coverage. Real effectiveness still needs before\u002Fafter agent sessions on representative tasks.\n\n## When to Read References\n\nLoad only the reference needed for the user's problem:\n\n- Memory across sessions: [Memory Persistence](references\u002Fmemory-persistence-pattern.md)\n- Reusable workflows as skills: [Skill Runtime](references\u002Fskill-runtime-pattern.md)\n- Permissions, tools, concurrency: [Tool Registry & Safety](references\u002Ftool-registry-pattern.md)\n- Context budget and progressive disclosure: [Context Engineering](references\u002Fcontext-engineering-pattern.md)\n- Delegation and parallel agents: [Multi-Agent Coordination](references\u002Fmulti-agent-pattern.md)\n- Hooks, startup, long-running work: [Lifecycle & Bootstrap](references\u002Flifecycle-bootstrap-pattern.md)\n- Non-obvious failure modes: [Gotchas](references\u002Fgotchas.md)\n\n## Design Rules\n\n- Keep the root instruction file short: routing and invariants, not a full manual.\n- Put project facts in project docs, not in the skill.\n- Make verification commands explicit and runnable.\n- Require evidence before marking a feature done.\n- Use one active feature unless the harness has explicit multi-agent ownership boundaries.\n- Prefer append\u002Fupdate state files over relying on chat history.\n- Never hide destructive behavior in scripts; overwrites require explicit user approval.\n\n## Deliverable Checklist\n\nFor a usable minimal harness, leave the target project with:\n\n- [ ] `AGENTS.md` or `CLAUDE.md`\n- [ ] `feature_list.json`\n- [ ] `progress.md`\n- [ ] `init.sh`\n- [ ] Optional `session-handoff.md` for multi-session work\n- [ ] Documented verification evidence or next action\n\nIf you cannot create files, provide exact file contents and commands instead.\n","# Harness Creator\n\nUse this skill to make a repository easier for coding agents to start, stay in scope, verify work, and resume across sessions. Keep the harness small enough that agents actually follow it.\n\nNot for model selection, prompt tuning in isolation, chat UI design, or general app architecture.\n\n## Core Model\n\nEvery useful coding-agent harness has five subsystems:\n\n| Subsystem | Minimal artifact | Purpose |\n|---|---|---|\n| Instructions | `AGENTS.md` or `CLAUDE.md` | Startup path, working rules, definition of done |\n| State | `feature_list.json`, `progress.md` | Current feature, status, evidence, next step |\n| Verification | `init.sh` or documented commands | Tests\u002Fchecks the agent must run before claiming done |\n| Scope | Feature dependencies and done criteria | Prevents overreach and half-finished work |\n| Lifecycle | `session-handoff.md`, end-of-session routine | Makes the next session restartable |\n\n## First Move\n\n1. Inspect what already exists: instruction files, feature\u002Fstate files, verification commands, docs, package manifests.\n2. Ask only for missing context that cannot be inferred safely: target agent, desired file name, tolerance for structure, and whether overwriting is allowed.\n3. Prefer a minimal harness first. Add memory, tool safety, multi-agent, or benchmark details only when the user's problem calls for them.\n\n## Common Tasks\n\n### Create a harness\n\nUse the bundled script when working on a local repository:\n\n```bash\nnode skills\u002Fharness-creator\u002Fscripts\u002Fcreate-harness.mjs --target \u002Fpath\u002Fto\u002Fproject\n```\n\nOptions:\n\n- `--agent-file CLAUDE.md` for Claude-oriented projects.\n- `--package-manager npm|pnpm|yarn|bun` when detection is wrong.\n- `--commands \"cmd one,cmd two\"` for custom verification.\n- `--force` only after confirming overwrites are acceptable.\n\nThen explain what was created and how the user should replace placeholder feature entries.\n\n### Audit an existing harness\n\nRun:\n\n```bash\nnode skills\u002Fharness-creator\u002Fscripts\u002Fvalidate-harness.mjs --target \u002Fpath\u002Fto\u002Fproject\n```\n\nReport the five subsystem scores, the lowest-scoring area, and the first 2-3 changes that would improve reliability. Treat the lowest score as a candidate bottleneck; confirm with failures, logs, or task outcomes before claiming causality.\n\n### Produce a report\n\nUse when the user wants a shareable assessment:\n\n```bash\nnode skills\u002Fharness-creator\u002Fscripts\u002Frender-assessment-html.mjs --target \u002Fpath\u002Fto\u002Fproject\nnode skills\u002Fharness-creator\u002Fscripts\u002Frun-benchmark.mjs --target \u002Fpath\u002Fto\u002Fproject --html \u002Fpath\u002Fto\u002Freport.html\n```\n\nBe clear that this is a structural benchmark. The benchmark first runs a self-check — it scaffolds a throwaway harness and validates it, proving the bundled scripts work end-to-end — then scores the target and eval coverage. Real effectiveness still needs before\u002Fafter agent sessions on representative tasks.\n\n## When to Read References\n\nLoad only the reference needed for the user's problem:\n\n- Memory across sessions: [Memory Persistence](references\u002Fmemory-persistence-pattern.md)\n- Reusable workflows as skills: [Skill Runtime](references\u002Fskill-runtime-pattern.md)\n- Permissions, tools, concurrency: [Tool Registry & Safety](references\u002Ftool-registry-pattern.md)\n- Context budget and progressive disclosure: [Context Engineering](references\u002Fcontext-engineering-pattern.md)\n- Delegation and parallel agents: [Multi-Agent Coordination](references\u002Fmulti-agent-pattern.md)\n- Hooks, startup, long-running work: [Lifecycle & Bootstrap](references\u002Flifecycle-bootstrap-pattern.md)\n- Non-obvious failure modes: [Gotchas](references\u002Fgotchas.md)\n\n## Design Rules\n\n- Keep the root instruction file short: routing and invariants, not a full manual.\n- Put project facts in project docs, not in the skill.\n- Make verification commands explicit and runnable.\n- Require evidence before marking a feature done.\n- Use one active feature unless the harness has explicit multi-agent ownership boundaries.\n- Prefer append\u002Fupdate state files over relying on chat history.\n- Never hide destructive behavior in scripts; overwrites require explicit user approval.\n\n## Deliverable Checklist\n\nFor a usable minimal harness, leave the target project with:\n\n- [ ] `AGENTS.md` or `CLAUDE.md`\n- [ ] `feature_list.json`\n- [ ] `progress.md`\n- [ ] `init.sh`\n- [ ] Optional `session-handoff.md` for multi-session work\n- [ ] Documented verification evidence or next action\n\nIf you cannot create files, provide exact file contents and commands instead.\n",{"name":5,"license":15,"description":7},"main","bc2f998beb877748d6e8c4588942b4ff2cfa495b",".claude\u002Fskills\u002Fharness-creator",0,"https:\u002F\u002Fgithub.com\u002FHareesh-Reddy-9126\u002FPS044-SmartHire","https:\u002F\u002Fgithub.com\u002FHareesh-Reddy-9126","🎓 B.Tech 3rd Year | CS&IT | 📈 LeetCode Grinder | Building side projects that actually matter | 🤝 Looking for: Internship 2026 | Open Source Collabs","2026-10-29 13:27:16",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add Hareesh-Reddy-9126\u002FPS044-SmartHire --skill harness-creator",{"tool":38,"command":39},"bunx","bunx skills add Hareesh-Reddy-9126\u002FPS044-SmartHire --skill harness-creator",{"tool":41,"command":42},"pnpm","pnpm dlx skills add Hareesh-Reddy-9126\u002FPS044-SmartHire --skill harness-creator","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FHareesh-Reddy-9126\u002FPS044-SmartHire\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fharness-creator\u002FSKILL.md",true,[46,52,56,60,64,68,72,76,80,84,88,92,98,102,106,110,114,120,124,128,132,136,140,144],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"agents\u002Fopenai.yaml","REFERENCE","参考文档",290,"https:\u002F\u002Fgithub.com\u002FHareesh-Reddy-9126\u002FPS044-SmartHire\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fharness-creator\u002Fagents\u002Fopenai.yaml",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"evals\u002Fevals.json",7238,"https:\u002F\u002Fgithub.com\u002FHareesh-Reddy-9126\u002FPS044-SmartHire\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fharness-creator\u002Fevals\u002Fevals.json",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"README-UK.md",3455,"https:\u002F\u002Fgithub.com\u002FHareesh-Reddy-9126\u002FPS044-SmartHire\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fharness-creator\u002FREADME-UK.md",{"path":61,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":62,"sourceHtmlUrl":63},"README.md",2422,"https:\u002F\u002Fgithub.com\u002FHareesh-Reddy-9126\u002FPS044-SmartHire\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fharness-creator\u002FREADME.md",{"path":65,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":66,"sourceHtmlUrl":67},"references\u002Fcontext-engineering-pattern.md",5186,"https:\u002F\u002Fgithub.com\u002FHareesh-Reddy-9126\u002FPS044-SmartHire\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fharness-creator\u002Freferences\u002Fcontext-engineering-pattern.md",{"path":69,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":70,"sourceHtmlUrl":71},"references\u002Fgotchas.md",6789,"https:\u002F\u002Fgithub.com\u002FHareesh-Reddy-9126\u002FPS044-SmartHire\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fharness-creator\u002Freferences\u002Fgotchas.md",{"path":73,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":74,"sourceHtmlUrl":75},"references\u002Flifecycle-bootstrap-pattern.md",8333,"https:\u002F\u002Fgithub.com\u002FHareesh-Reddy-9126\u002FPS044-SmartHire\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fharness-creator\u002Freferences\u002Flifecycle-bootstrap-pattern.md",{"path":77,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":78,"sourceHtmlUrl":79},"references\u002Fmemory-persistence-pattern.md",4486,"https:\u002F\u002Fgithub.com\u002FHareesh-Reddy-9126\u002FPS044-SmartHire\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fharness-creator\u002Freferences\u002Fmemory-persistence-pattern.md",{"path":81,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":82,"sourceHtmlUrl":83},"references\u002Fmulti-agent-pattern.md",6496,"https:\u002F\u002Fgithub.com\u002FHareesh-Reddy-9126\u002FPS044-SmartHire\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fharness-creator\u002Freferences\u002Fmulti-agent-pattern.md",{"path":85,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":86,"sourceHtmlUrl":87},"references\u002Fskill-runtime-pattern.md",1805,"https:\u002F\u002Fgithub.com\u002FHareesh-Reddy-9126\u002FPS044-SmartHire\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fharness-creator\u002Freferences\u002Fskill-runtime-pattern.md",{"path":89,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":90,"sourceHtmlUrl":91},"references\u002Ftool-registry-pattern.md",6136,"https:\u002F\u002Fgithub.com\u002FHareesh-Reddy-9126\u002FPS044-SmartHire\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fharness-creator\u002Freferences\u002Ftool-registry-pattern.md",{"path":93,"resourceType":94,"resourceTypeDesc":95,"sizeBytes":96,"sourceHtmlUrl":97},"scripts\u002Fcreate-harness.mjs","SCRIPT","脚本",2745,"https:\u002F\u002Fgithub.com\u002FHareesh-Reddy-9126\u002FPS044-SmartHire\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fharness-creator\u002Fscripts\u002Fcreate-harness.mjs",{"path":99,"resourceType":94,"resourceTypeDesc":95,"sizeBytes":100,"sourceHtmlUrl":101},"scripts\u002Flib\u002Fharness-utils.mjs",16497,"https:\u002F\u002Fgithub.com\u002FHareesh-Reddy-9126\u002FPS044-SmartHire\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fharness-creator\u002Fscripts\u002Flib\u002Fharness-utils.mjs",{"path":103,"resourceType":94,"resourceTypeDesc":95,"sizeBytes":104,"sourceHtmlUrl":105},"scripts\u002Frender-assessment-html.mjs",839,"https:\u002F\u002Fgithub.com\u002FHareesh-Reddy-9126\u002FPS044-SmartHire\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fharness-creator\u002Fscripts\u002Frender-assessment-html.mjs",{"path":107,"resourceType":94,"resourceTypeDesc":95,"sizeBytes":108,"sourceHtmlUrl":109},"scripts\u002Frun-benchmark.mjs",7260,"https:\u002F\u002Fgithub.com\u002FHareesh-Reddy-9126\u002FPS044-SmartHire\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fharness-creator\u002Fscripts\u002Frun-benchmark.mjs",{"path":111,"resourceType":94,"resourceTypeDesc":95,"sizeBytes":112,"sourceHtmlUrl":113},"scripts\u002Fvalidate-harness.mjs",1154,"https:\u002F\u002Fgithub.com\u002FHareesh-Reddy-9126\u002FPS044-SmartHire\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fharness-creator\u002Fscripts\u002Fvalidate-harness.mjs",{"path":115,"resourceType":116,"resourceTypeDesc":117,"sizeBytes":118,"sourceHtmlUrl":119},"SKILL.md.en","OTHER","其他",5188,"https:\u002F\u002Fgithub.com\u002FHareesh-Reddy-9126\u002FPS044-SmartHire\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fharness-creator\u002FSKILL.md.en",{"path":121,"resourceType":116,"resourceTypeDesc":117,"sizeBytes":122,"sourceHtmlUrl":123},"SKILL.md.uk",8250,"https:\u002F\u002Fgithub.com\u002FHareesh-Reddy-9126\u002FPS044-SmartHire\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fharness-creator\u002FSKILL.md.uk",{"path":125,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":126,"sourceHtmlUrl":127},"templates\u002Fagents.md",2361,"https:\u002F\u002Fgithub.com\u002FHareesh-Reddy-9126\u002FPS044-SmartHire\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fharness-creator\u002Ftemplates\u002Fagents.md",{"path":129,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":130,"sourceHtmlUrl":131},"templates\u002Ffeature-list.json",1390,"https:\u002F\u002Fgithub.com\u002FHareesh-Reddy-9126\u002FPS044-SmartHire\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fharness-creator\u002Ftemplates\u002Ffeature-list.json",{"path":133,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":134,"sourceHtmlUrl":135},"templates\u002Ffeature-list.schema.json",1385,"https:\u002F\u002Fgithub.com\u002FHareesh-Reddy-9126\u002FPS044-SmartHire\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fharness-creator\u002Ftemplates\u002Ffeature-list.schema.json",{"path":137,"resourceType":94,"resourceTypeDesc":95,"sizeBytes":138,"sourceHtmlUrl":139},"templates\u002Finit.sh",2692,"https:\u002F\u002Fgithub.com\u002FHareesh-Reddy-9126\u002FPS044-SmartHire\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fharness-creator\u002Ftemplates\u002Finit.sh",{"path":141,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":142,"sourceHtmlUrl":143},"templates\u002Fprogress.md",1051,"https:\u002F\u002Fgithub.com\u002FHareesh-Reddy-9126\u002FPS044-SmartHire\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fharness-creator\u002Ftemplates\u002Fprogress.md",{"path":145,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":146,"sourceHtmlUrl":147},"templates\u002Fsession-handoff.md",509,"https:\u002F\u002Fgithub.com\u002FHareesh-Reddy-9126\u002FPS044-SmartHire\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fharness-creator\u002Ftemplates\u002Fsession-handoff.md",[149,158,166,173,180,187],{"skillNo":150,"name":151,"nameZh":6,"description":152,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":153,"licenseFileUrl":154,"sourceHtmlUrl":155,"categories":156,"keywords":157,"publishedAt":19},"01M7CT84AFNKCD7HYFGTK9V65T","webapp-testing","Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.","Apache-2.0","https:\u002F\u002Fgithub.com\u002FHareesh-Reddy-9126\u002FPS044-SmartHire\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fwebapp-testing\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002FHareesh-Reddy-9126\u002FPS044-SmartHire\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fwebapp-testing\u002FSKILL.md",[],[],{"skillNo":159,"name":160,"nameZh":6,"description":161,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":153,"licenseFileUrl":162,"sourceHtmlUrl":163,"categories":164,"keywords":165,"publishedAt":19},"01M7CT7XM14XJZT9F5N634FPVP","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.","https:\u002F\u002Fgithub.com\u002FHareesh-Reddy-9126\u002FPS044-SmartHire\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fweb-artifacts-builder\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002FHareesh-Reddy-9126\u002FPS044-SmartHire\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fweb-artifacts-builder\u002FSKILL.md",[],[],{"skillNo":167,"name":168,"nameZh":6,"description":169,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":153,"licenseFileUrl":6,"sourceHtmlUrl":170,"categories":171,"keywords":172,"publishedAt":19},"01M7CT7RAWP38MMBQZ274RNM34","web-app-penetration-testing","Pentest a web app or website end to end — black-box testing of a live URL, staging environment, or local dev server that finds and exploits real vulnerabilities (auth bypass, broken access control, IDOR, injection, XSS, SSRF, business logic) and proves each one with a working proof-of-concept instead of a signature match. Runs with Strix, either the self-hosted open-source CLI or the managed app.strix.ai cloud. Use when the user asks to pentest, hack, security-test, or audit their web app, website, web application, or staging site.","https:\u002F\u002Fgithub.com\u002FHareesh-Reddy-9126\u002FPS044-SmartHire\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fweb-app-penetration-testing\u002FSKILL.md",[],[],{"skillNo":174,"name":175,"nameZh":6,"description":176,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":177,"categories":178,"keywords":179,"publishedAt":19},"01M7CT7K4CW6BNQEY2D1W1GNM4","vercel-react-best-practices","React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React\u002FNext.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.","https:\u002F\u002Fgithub.com\u002FHareesh-Reddy-9126\u002FPS044-SmartHire\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Fvercel-react-best-practices\u002FSKILL.md",[],[],{"skillNo":181,"name":182,"nameZh":6,"description":183,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":184,"categories":185,"keywords":186,"publishedAt":19},"01M7CT7EFR7S5RXBGX2E2Q8H6X","typescript-pro","Implements advanced TypeScript type systems, creates custom type guards, utility types, and branded types, and configures tRPC for end-to-end type safety. Use when building TypeScript applications requiring advanced generics, conditional or mapped types, discriminated unions, monorepo setup, or full-stack type safety with tRPC.","https:\u002F\u002Fgithub.com\u002FHareesh-Reddy-9126\u002FPS044-SmartHire\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftypescript-pro\u002FSKILL.md",[],[],{"skillNo":188,"name":189,"nameZh":6,"description":190,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":153,"licenseFileUrl":191,"sourceHtmlUrl":192,"categories":193,"keywords":194,"publishedAt":19},"01M7CT7BR0WF3BPWYSD7SP4MJP","theme-factory","Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors\u002Ffonts that you can apply to any artifact that has been creating, or can generate a new theme on-the-fly.","https:\u002F\u002Fgithub.com\u002FHareesh-Reddy-9126\u002FPS044-SmartHire\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftheme-factory\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002FHareesh-Reddy-9126\u002FPS044-SmartHire\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ftheme-factory\u002FSKILL.md",[],[]]