[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6AFTGX7W1T95PKYBBPJRJCM":3,"skill-same:01M6AFTGX7W1T95PKYBBPJRJCM":67},{"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":31,"linkOnly":32,"markdownContent":33,"markdownBody":34,"frontMatter":35,"refName":37,"commitSha":38,"skillDirectory":39,"forksCount":40,"repositoryHtmlUrl":41,"repositoryHomepageUrl":42,"ownerHtmlUrl":43,"ownerBlogUrl":44,"ownerDescription":45,"updatedAt":46,"install":47,"resources":60},"01M6AFTGX7W1T95PKYBBPJRJCM","red-team-tactics",null,"Red team tactics principles based on MITRE ATT&CK. Attack phases, detection evasion, reporting.","davila7\u002Fclaude-code-templates","davila7","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F6216945?v=4","01M6ADEWWFPS191NFM0Y1EX1JH","Daniel Avila","01M6ADJHGM78PHQRD3XZTFDVKK",33481,"MIT","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fsecurity\u002Fred-team-tactics\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30],"red team","red team tactics","team","red","reporting","ATT&CK","detection","evasion","grep","read","principles","ck","2026-11-10 10:12:30",false,"---\nname: red-team-tactics\ndescription: Red team tactics principles based on MITRE ATT&CK. Attack phases, detection evasion, reporting.\nallowed-tools: Read, Glob, Grep\n---\n\n# Red Team Tactics\n\n> Adversary simulation principles based on MITRE ATT&CK framework.\n\n---\n\n## 1. MITRE ATT&CK Phases\n\n### Attack Lifecycle\n\n```\nRECONNAISSANCE → INITIAL ACCESS → EXECUTION → PERSISTENCE\n       ↓              ↓              ↓            ↓\n   PRIVILEGE ESC → DEFENSE EVASION → CRED ACCESS → DISCOVERY\n       ↓              ↓              ↓            ↓\nLATERAL MOVEMENT → COLLECTION → C2 → EXFILTRATION → IMPACT\n```\n\n### Phase Objectives\n\n| Phase | Objective |\n|-------|-----------|\n| **Recon** | Map attack surface |\n| **Initial Access** | Get first foothold |\n| **Execution** | Run code on target |\n| **Persistence** | Survive reboots |\n| **Privilege Escalation** | Get admin\u002Froot |\n| **Defense Evasion** | Avoid detection |\n| **Credential Access** | Harvest credentials |\n| **Discovery** | Map internal network |\n| **Lateral Movement** | Spread to other systems |\n| **Collection** | Gather target data |\n| **C2** | Maintain command channel |\n| **Exfiltration** | Extract data |\n\n---\n\n## 2. Reconnaissance Principles\n\n### Passive vs Active\n\n| Type | Trade-off |\n|------|-----------|\n| **Passive** | No target contact, limited info |\n| **Active** | Direct contact, more detection risk |\n\n### Information Targets\n\n| Category | Value |\n|----------|-------|\n| Technology stack | Attack vector selection |\n| Employee info | Social engineering |\n| Network ranges | Scanning scope |\n| Third parties | Supply chain attack |\n\n---\n\n## 3. Initial Access Vectors\n\n### Selection Criteria\n\n| Vector | When to Use |\n|--------|-------------|\n| **Phishing** | Human target, email access |\n| **Public exploits** | Vulnerable services exposed |\n| **Valid credentials** | Leaked or cracked |\n| **Supply chain** | Third-party access |\n\n---\n\n## 4. Privilege Escalation Principles\n\n### Windows Targets\n\n| Check | Opportunity |\n|-------|-------------|\n| Unquoted service paths | Write to path |\n| Weak service permissions | Modify service |\n| Token privileges | Abuse SeDebug, etc. |\n| Stored credentials | Harvest |\n\n### Linux Targets\n\n| Check | Opportunity |\n|-------|-------------|\n| SUID binaries | Execute as owner |\n| Sudo misconfiguration | Command execution |\n| Kernel vulnerabilities | Kernel exploits |\n| Cron jobs | Writable scripts |\n\n---\n\n## 5. Defense Evasion Principles\n\n### Key Techniques\n\n| Technique | Purpose |\n|-----------|---------|\n| LOLBins | Use legitimate tools |\n| Obfuscation | Hide malicious code |\n| Timestomping | Hide file modifications |\n| Log clearing | Remove evidence |\n\n### Operational Security\n\n- Work during business hours\n- Mimic legitimate traffic patterns\n- Use encrypted channels\n- Blend with normal behavior\n\n---\n\n## 6. Lateral Movement Principles\n\n### Credential Types\n\n| Type | Use |\n|------|-----|\n| Password | Standard auth |\n| Hash | Pass-the-hash |\n| Ticket | Pass-the-ticket |\n| Certificate | Certificate auth |\n\n### Movement Paths\n\n- Admin shares\n- Remote services (RDP, SSH, WinRM)\n- Exploitation of internal services\n\n---\n\n## 7. Active Directory Attacks\n\n### Attack Categories\n\n| Attack | Target |\n|--------|--------|\n| Kerberoasting | Service account passwords |\n| AS-REP Roasting | Accounts without pre-auth |\n| DCSync | Domain credentials |\n| Golden Ticket | Persistent domain access |\n\n---\n\n## 8. Reporting Principles\n\n### Attack Narrative\n\nDocument the full attack chain:\n1. How initial access was gained\n2. What techniques were used\n3. What objectives were achieved\n4. Where detection failed\n\n### Detection Gaps\n\nFor each successful technique:\n- What should have detected it?\n- Why didn't detection work?\n- How to improve detection\n\n---\n\n## 9. Ethical Boundaries\n\n### Always\n\n- Stay within scope\n- Minimize impact\n- Report immediately if real threat found\n- Document all actions\n\n### Never\n\n- Destroy production data\n- Cause denial of service (unless scoped)\n- Access beyond proof of concept\n- Retain sensitive data\n\n---\n\n## 10. Anti-Patterns\n\n| ❌ Don't | ✅ Do |\n|----------|-------|\n| Rush to exploitation | Follow methodology |\n| Cause damage | Minimize impact |\n| Skip reporting | Document everything |\n| Ignore scope | Stay within boundaries |\n\n---\n\n> **Remember:** Red team simulates attackers to improve defenses, not to cause harm.\n","# Red Team Tactics\n\n> Adversary simulation principles based on MITRE ATT&CK framework.\n\n---\n\n## 1. MITRE ATT&CK Phases\n\n### Attack Lifecycle\n\n```\nRECONNAISSANCE → INITIAL ACCESS → EXECUTION → PERSISTENCE\n       ↓              ↓              ↓            ↓\n   PRIVILEGE ESC → DEFENSE EVASION → CRED ACCESS → DISCOVERY\n       ↓              ↓              ↓            ↓\nLATERAL MOVEMENT → COLLECTION → C2 → EXFILTRATION → IMPACT\n```\n\n### Phase Objectives\n\n| Phase | Objective |\n|-------|-----------|\n| **Recon** | Map attack surface |\n| **Initial Access** | Get first foothold |\n| **Execution** | Run code on target |\n| **Persistence** | Survive reboots |\n| **Privilege Escalation** | Get admin\u002Froot |\n| **Defense Evasion** | Avoid detection |\n| **Credential Access** | Harvest credentials |\n| **Discovery** | Map internal network |\n| **Lateral Movement** | Spread to other systems |\n| **Collection** | Gather target data |\n| **C2** | Maintain command channel |\n| **Exfiltration** | Extract data |\n\n---\n\n## 2. Reconnaissance Principles\n\n### Passive vs Active\n\n| Type | Trade-off |\n|------|-----------|\n| **Passive** | No target contact, limited info |\n| **Active** | Direct contact, more detection risk |\n\n### Information Targets\n\n| Category | Value |\n|----------|-------|\n| Technology stack | Attack vector selection |\n| Employee info | Social engineering |\n| Network ranges | Scanning scope |\n| Third parties | Supply chain attack |\n\n---\n\n## 3. Initial Access Vectors\n\n### Selection Criteria\n\n| Vector | When to Use |\n|--------|-------------|\n| **Phishing** | Human target, email access |\n| **Public exploits** | Vulnerable services exposed |\n| **Valid credentials** | Leaked or cracked |\n| **Supply chain** | Third-party access |\n\n---\n\n## 4. Privilege Escalation Principles\n\n### Windows Targets\n\n| Check | Opportunity |\n|-------|-------------|\n| Unquoted service paths | Write to path |\n| Weak service permissions | Modify service |\n| Token privileges | Abuse SeDebug, etc. |\n| Stored credentials | Harvest |\n\n### Linux Targets\n\n| Check | Opportunity |\n|-------|-------------|\n| SUID binaries | Execute as owner |\n| Sudo misconfiguration | Command execution |\n| Kernel vulnerabilities | Kernel exploits |\n| Cron jobs | Writable scripts |\n\n---\n\n## 5. Defense Evasion Principles\n\n### Key Techniques\n\n| Technique | Purpose |\n|-----------|---------|\n| LOLBins | Use legitimate tools |\n| Obfuscation | Hide malicious code |\n| Timestomping | Hide file modifications |\n| Log clearing | Remove evidence |\n\n### Operational Security\n\n- Work during business hours\n- Mimic legitimate traffic patterns\n- Use encrypted channels\n- Blend with normal behavior\n\n---\n\n## 6. Lateral Movement Principles\n\n### Credential Types\n\n| Type | Use |\n|------|-----|\n| Password | Standard auth |\n| Hash | Pass-the-hash |\n| Ticket | Pass-the-ticket |\n| Certificate | Certificate auth |\n\n### Movement Paths\n\n- Admin shares\n- Remote services (RDP, SSH, WinRM)\n- Exploitation of internal services\n\n---\n\n## 7. Active Directory Attacks\n\n### Attack Categories\n\n| Attack | Target |\n|--------|--------|\n| Kerberoasting | Service account passwords |\n| AS-REP Roasting | Accounts without pre-auth |\n| DCSync | Domain credentials |\n| Golden Ticket | Persistent domain access |\n\n---\n\n## 8. Reporting Principles\n\n### Attack Narrative\n\nDocument the full attack chain:\n1. How initial access was gained\n2. What techniques were used\n3. What objectives were achieved\n4. Where detection failed\n\n### Detection Gaps\n\nFor each successful technique:\n- What should have detected it?\n- Why didn't detection work?\n- How to improve detection\n\n---\n\n## 9. Ethical Boundaries\n\n### Always\n\n- Stay within scope\n- Minimize impact\n- Report immediately if real threat found\n- Document all actions\n\n### Never\n\n- Destroy production data\n- Cause denial of service (unless scoped)\n- Access beyond proof of concept\n- Retain sensitive data\n\n---\n\n## 10. Anti-Patterns\n\n| ❌ Don't | ✅ Do |\n|----------|-------|\n| Rush to exploitation | Follow methodology |\n| Cause damage | Minimize impact |\n| Skip reporting | Document everything |\n| Ignore scope | Stay within boundaries |\n\n---\n\n> **Remember:** Red team simulates attackers to improve defenses, not to cause harm.\n",{"name":5,"description":7,"allowed-tools":36},"Read, Glob, Grep","main","2b749c82b5d11fac39d9a6e021ce3f5b8a541bd1","cli-tool\u002Fcomponents\u002Fskills\u002Fsecurity\u002Fred-team-tactics",3931,"https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates","https:\u002F\u002Faitmpl.com","https:\u002F\u002Fgithub.com\u002Fdavila7","https:\u002F\u002Fdanielavila.me","Building AI dev tools with LLMs","2026-11-14 06:14:46",{"source":8,"skillName":5,"commands":48,"prompt":58,"zipAvailable":59},[49,52,55],{"tool":50,"command":51},"npx","npx skills add davila7\u002Fclaude-code-templates --skill red-team-tactics",{"tool":53,"command":54},"bunx","bunx skills add davila7\u002Fclaude-code-templates --skill red-team-tactics",{"tool":56,"command":57},"pnpm","pnpm dlx skills add davila7\u002Fclaude-code-templates --skill red-team-tactics","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fsecurity\u002Fred-team-tactics\u002FSKILL.md",true,[61],{"path":62,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":65,"sourceHtmlUrl":66},"reference\u002Ffeature-matrix.md","REFERENCE","参考文档",7074,"https:\u002F\u002Fgithub.com\u002Finernoro\u002Fprd_agent\u002Fblob\u002Fmain\u002F.claude\u002Fskills\u002Ffeature-emerge\u002Freference\u002Ffeature-matrix.md",[68,100,127,160,195,219],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":79,"publishedAt":31},"01M70NHBTQ8BV0A2SCAZXEPHCX","wealthville-pool-scoring","Score DeFi liquidity pools before providing liquidity. Returns a 0-100 pool score and an Enter\u002FHold\u002FExit\u002FReduce\u002FAvoid verdict with calibrated confidence for ~68,800 Solana pools and 575 EVM pools, plus a public miss-inclusive track record. Use when asked whether a pool is worth LPing into, which pools look best right now, or how accurate the scores have actually been.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fweb-data\u002Fwealthville-pool-scoring\u002FSKILL.md",[74],{"categoryNo":75,"categoryName":76,"taxonomyType":77,"taxonomyTypeDesc":78},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99],"scoring","pool","wealthville pool scoring","liquidity","which","for","exit","now","use","when","reduce","with","record","track","verdict","evm","solana","how","public","look",{"skillNo":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":107,"publishedAt":31},"01M70MB6VR8ERJ4EM8D5KHBMEV","technical-debt-auditor","Scans a codebase and produces a quantified technical debt report with a prioritized remediation plan. Analyzes dead code, TODO\u002FFIXME\u002FHACK markers, dependency staleness, complexity hotspots, code duplication signals, test coverage gaps, unused exports, and outdated patterns. Use this skill when the user asks to audit their codebase for tech debt, wants a health check of their code quality, says things like \"where should I focus refactoring\", \"find code smells\", \"audit my codebase\", \"what technical debt do we have\", \"prioritize cleanup work\", or asks about code quality metrics. Also trigger when the user mentions \"code rot\", \"legacy cleanup\", \"refactoring priorities\", or wants to understand the overall health of a project before a major effort. Trigger even if the user doesn't say \"technical debt\" explicitly — any request to systematically assess code quality and identify improvement priorities belongs here.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdevelopment\u002Ftechnical-debt-auditor\u002FSKILL.md",[106],{"categoryNo":75,"categoryName":76,"taxonomyType":77,"taxonomyTypeDesc":78},[108,109,110,111,112,113,114,115,116,117,118,89,119,120,121,122,123,124,125,126],"technical debt","debt","technical","technical debt auditor","auditor","coverage","complexity","markers","project","cleanup","unused","code","todo","work","plan","focus","signals","audit","dependency",{"skillNo":128,"name":129,"nameZh":6,"description":130,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":131,"categories":132,"keywords":142,"publishedAt":31},"01M70KPYH9QNHCNME5GJQGE22K","readonly-sql-guard","Make an agent's database access provably read-only. Use when an agent runs caller-supplied SQL against a production\u002FERP\u002Fanalytics database (a \"query\" MCP tool, text-to-SQL, an admin console), or when reviewing DB-access code for write\u002FDDL\u002Fside-effect\u002Ftransaction-escape risks. Checks what a statement CALLS, not just its shape.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fdatabase\u002Freadonly-sql-guard\u002FSKILL.md",[133,136,137],{"categoryNo":134,"categoryName":135,"taxonomyType":77,"taxonomyTypeDesc":78},"01JBSEEDCAT000000000000010","后端与接口",{"categoryNo":75,"categoryName":76,"taxonomyType":77,"taxonomyTypeDesc":78},{"categoryNo":138,"categoryName":139,"taxonomyType":140,"taxonomyTypeDesc":141},"01JBSEEDCAT000000000000033","数据分析师","PROFESSION","适用职业",[143,144,145,146,147,148,149,85,150,151,152,153,154,155,156,88,157,158,89,159],"readonly","guard","sql guard","sql","readonly sql guard","erp","effect","read-only","db","just","tool","calls","only","MCP","access","database","query",{"skillNo":161,"name":162,"nameZh":6,"description":163,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":164,"licenseFileUrl":165,"sourceHtmlUrl":166,"categories":167,"keywords":171,"publishedAt":31},"01M6AFY6F7CC2BBZP1QD6VTNVC","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\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Futilities\u002Fweb-artifacts-builder\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Futilities\u002Fweb-artifacts-builder\u002FSKILL.md",[168],{"categoryNo":169,"categoryName":170,"taxonomyType":77,"taxonomyTypeDesc":78},"01JBSEEDCAT000000000000009","前端开发",[172,173,174,175,176,177,178,179,180,181,182,183,184,185,186,187,188,189,190,191,192,193,85,194],"artifacts builder","web","web artifacts builder","artifacts","builder","state","routing","state management","component","css","frontend","ui","Tools","file","components","shadcn","react","Tailwind","suite","jsx","html","single-file","ui components",{"skillNo":196,"name":197,"nameZh":6,"description":198,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":164,"licenseFileUrl":199,"sourceHtmlUrl":200,"categories":201,"keywords":206,"publishedAt":31},"01M6AFWF33SFV9Z3SF4PEEE4BF","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.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fsecurity\u002Fwebapp-testing\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fsecurity\u002Fwebapp-testing\u002FSKILL.md",[202,205],{"categoryNo":203,"categoryName":204,"taxonomyType":77,"taxonomyTypeDesc":78},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":169,"categoryName":170,"taxonomyType":77,"taxonomyTypeDesc":78},[207,208,209,210,211,173,212,182,183,213,214,215,216,85,217,91,218],"webapp testing","testing","webapp","browser","playwright","applications","debugging","toolkit","logs","screenshots","local","behavior",{"skillNo":220,"name":221,"nameZh":6,"description":222,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":164,"licenseFileUrl":223,"sourceHtmlUrl":224,"categories":225,"keywords":233,"publishedAt":31},"01M6AF67Q67JJJ5V51JR2P52KA","discernment-nudge","After you give a substantive answer or draft that the user may act on — advice or recommendations, drafted artifacts such as goals, plans, pitches, proposals, or emails, estimates or projections, analysis or interpretation of data, factual claims they may rely on, or a multi-step argument — invoke this skill BEFORE finalizing your reply and then, if it applies, append 2-3 short follow-up questions, each tied to something specific in what you just produced, that help the user check key facts, probe the reasoning or assumptions, and notice missing context. Do this at most once per conversation. Skip it when the user asked a trivial how-to or simple lookup, wants a purely educational explanation, asked you only to format, convert, or assemble a file from content they provided, is writing code they will run, is doing creative writing or casual chat, or already asked you to double-check, cite, or review — the skill file explains these boundaries and the exact output format.","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fproductivity\u002Fdiscernment-nudge\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fdavila7\u002Fclaude-code-templates\u002Fblob\u002Fmain\u002Fcli-tool\u002Fcomponents\u002Fskills\u002Fproductivity\u002Fdiscernment-nudge\u002FSKILL.md",[226,229,230],{"categoryNo":227,"categoryName":228,"taxonomyType":77,"taxonomyTypeDesc":78},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":75,"categoryName":76,"taxonomyType":77,"taxonomyTypeDesc":78},{"categoryNo":231,"categoryName":232,"taxonomyType":140,"taxonomyTypeDesc":141},"01JBSEEDCAT000000000000036","内容创作者",[234,235,236,237,238,239,240,241,175,242,185,119,243,244,245,246,247,155,248,89,249,250,251,252,253,97,254],"discernment nudge","nudge","interpretation","help","run","reasoning","data","writing","lookup","content","review","conversation","short","up","invoke","you","analysis","claims","argument","assemble","recommendations"]