[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7EVASEFS23VQHWFAJYRVNNK":3,"skill-same:01M7EVASEFS23VQHWFAJYRVNNK":47},{"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":27,"forksCount":28,"repositoryHtmlUrl":29,"repositoryHomepageUrl":6,"ownerHtmlUrl":30,"ownerBlogUrl":31,"ownerDescription":6,"updatedAt":32,"install":33,"resources":46},"01M7EVASEFS23VQHWFAJYRVNNK","phishing-tester",null,"Run authorized phishing simulations to measure susceptibility, train staff, and strengthen reporting culture — safely and ethically.","TanNhatCMS\u002Fjarvis","TanNhatCMS","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F113796420?v=4","01M753MV17KG5CD3152G3WQEQY","KietNT","01M7EKEDYVYQ6PWVJJMZ911VMX",0,"MIT","https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fams-phishing-tester\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: phishing-tester\ndescription: Run authorized phishing simulations to measure susceptibility, train staff, and strengthen reporting culture — safely and ethically.\ncategory: security\n---\n\n## Overview\n\nPhishing simulations send benign, clearly-controlled mock lures to employees to measure how many click, how many report, and how fast. Done well, they are a training tool that builds the reporting habit. Done badly, they are a trust-destroying gotcha exercise. The difference is entirely in program design: transparency, proportionality, and blameless follow-up.\n\nThis skill covers running an ethical simulation program: authorization, safe lure design, measurement, and coaching. It contains no real phishing tradecraft.\n\nA simulation program lives or dies on trust: employees must believe it exists to protect them, not to trap them. Announce the program, explain the no-punishment policy in plain language, and make every touchpoint educational. The day employees forward real phish to security without being asked, the program has worked — regardless of what the click-rate dashboard says.\n\n## When to use\n\n- Establishing a baseline of phishing susceptibility for awareness planning.\n- Validating that training and technical controls (email filtering, reporting button) work.\n- Meeting compliance or cyber-insurance expectations for testing human controls.\n- After a real phishing incident, to check whether the lesson stuck.\n\n## Core concepts\n\n- **Authorization and scope:** written approval from leadership and HR\u002Flegal; simulations target employees as part of an announced security program — never secret tests of individuals, never targeting personal accounts.\n- **Benign by design:** lures must be obviously fake on close inspection, contain no malware, harvest no real credentials (use clearly-labeled training landing pages), and cause no data loss.\n- **Proportionality:** lures should resemble realistic threats, not exploit personal trauma, financial fear, or HR consequences (fake layoffs, fake bonus cuts, fake disciplinary notices are off-limits).\n- **The metric that matters is reporting:** click rate tells you exposure; report rate and report speed tell you resilience. Optimize for reporting.\n- **Immediate micro-training:** a clicker lands on a 60-second \"here is what gave it away\" page — education at the teachable moment, not a walk of shame.\n- **Aggregate, don't single out:** report by department\u002Frole for coaching; individual data stays with security and managers for supportive follow-up only.\n\n- **Difficulty calibration.** Start with obvious lures and progress to sophisticated ones. A baseline that crushes morale with a nation-state-grade lure teaches nothing.\n- **Channel expansion with care.** Email first; SMS and voice simulations only with explicit additional approval, as they feel more invasive and carry higher trust risk.\n- **Control effectiveness signal.** Simulation results also test your email filtering — high click rates on lures that should have been filtered are a tooling problem, not a people problem.\n\n## Practical workflow\n\n1. **Get authorization:** leadership + HR + legal sign-off on the program charter: purpose, scope, lure boundaries, data handling, and no-punishment policy. Announce the program's existence (not the schedule).\n2. **Baseline:** run a neutral-difficulty simulation to establish click\u002Freport rates by department. This is your before picture.\n3. **Design lures responsibly:** model on current real-world themes (fake shared doc, password expiry, delivery notice); keep difficulty progressive; never use the prohibited themes above.\n4. **Execute safely:** send in waves during business hours; landing pages clearly branded as training; no credential storage — if a form is used, discard input and say so.\n5. **Measure:** click rate, credential-submit rate (if applicable), report rate, median time-to-report, and repeat-clicker rate. Compare against baseline.\n6. **Coach and improve:** immediate micro-training for clickers; targeted coaching for repeat clickers and high-risk roles; share anonymized trends org-wide (\"reporting up 40% — great work\"); feed results into the awareness program.\n\n### Program charter essentials\n\n- Purpose: measure and improve phishing resilience, not punish\n- Scope: which populations, which channels (email; SMS\u002Fvoice only with extra approval)\n- Prohibited lure themes (HR actions, layoffs, personal emergencies, financial threats)\n- Data handling: who sees individual results, retention period\n- No-punishment commitment and coaching approach\n- Success metrics: report rate and time-to-report trending up\n\n### Sustaining the practice\n\n- Vary themes each round; retire lures after a single use\n- Publish anonymized trends org-wide to normalize reporting as a shared win\n- Align simulation difficulty progression with training curriculum\n- Review the program charter annually with HR and legal\n\n### Metrics that prove it works\n\n- Click, submit, and report rates by department, trended per round\n- Median time-to-report (the resilience metric)\n- Repeat-clicker rate after coaching intervention\n- Coaching completion rate for clickers\n\n## Common pitfalls\n\n- **Gotcha culture.** Surprise tests with punishment destroy the trust that reporting culture needs. Announce the program; coach, don't punish.\n- **Cruel or manipulative lures.** Fake layoffs or bonus threats cause real distress and HR crises. Keep lures professional and proportional.\n- **Harvesting real credentials.** Never collect or store actual passwords, even \"for training.\" Use obviously-fake forms and discard input.\n- **Measuring only clicks.** A program that drives clicks down but never measures reporting is optimizing the wrong thing.\n- **Targeting personal accounts or non-employees.** Simulations stay inside the employment relationship and the announced program.\n- **No follow-through.** Simulations without coaching and control improvements are just surveillance. Every round should change training or tooling.\n- **Testing too frequently.** Monthly gotcha emails breed fatigue and resentment. Quarterly themed rounds with fresh lures beat constant low-grade testing.\n- **Reusing the same lure.** Teams learn the template, not the skepticism. Retire lures after one use and model new ones on current real-world campaigns.\n- **Naming and shaming departments.** Public leaderboards of 'worst clickers' destroy trust. Share trends, coach privately, celebrate reporting.\n- **Simulations during layoffs or crises.** Testing stressed employees facing real uncertainty is cruel and produces meaningless data. Pause the program when the org is under strain.\n","## Overview\n\nPhishing simulations send benign, clearly-controlled mock lures to employees to measure how many click, how many report, and how fast. Done well, they are a training tool that builds the reporting habit. Done badly, they are a trust-destroying gotcha exercise. The difference is entirely in program design: transparency, proportionality, and blameless follow-up.\n\nThis skill covers running an ethical simulation program: authorization, safe lure design, measurement, and coaching. It contains no real phishing tradecraft.\n\nA simulation program lives or dies on trust: employees must believe it exists to protect them, not to trap them. Announce the program, explain the no-punishment policy in plain language, and make every touchpoint educational. The day employees forward real phish to security without being asked, the program has worked — regardless of what the click-rate dashboard says.\n\n## When to use\n\n- Establishing a baseline of phishing susceptibility for awareness planning.\n- Validating that training and technical controls (email filtering, reporting button) work.\n- Meeting compliance or cyber-insurance expectations for testing human controls.\n- After a real phishing incident, to check whether the lesson stuck.\n\n## Core concepts\n\n- **Authorization and scope:** written approval from leadership and HR\u002Flegal; simulations target employees as part of an announced security program — never secret tests of individuals, never targeting personal accounts.\n- **Benign by design:** lures must be obviously fake on close inspection, contain no malware, harvest no real credentials (use clearly-labeled training landing pages), and cause no data loss.\n- **Proportionality:** lures should resemble realistic threats, not exploit personal trauma, financial fear, or HR consequences (fake layoffs, fake bonus cuts, fake disciplinary notices are off-limits).\n- **The metric that matters is reporting:** click rate tells you exposure; report rate and report speed tell you resilience. Optimize for reporting.\n- **Immediate micro-training:** a clicker lands on a 60-second \"here is what gave it away\" page — education at the teachable moment, not a walk of shame.\n- **Aggregate, don't single out:** report by department\u002Frole for coaching; individual data stays with security and managers for supportive follow-up only.\n\n- **Difficulty calibration.** Start with obvious lures and progress to sophisticated ones. A baseline that crushes morale with a nation-state-grade lure teaches nothing.\n- **Channel expansion with care.** Email first; SMS and voice simulations only with explicit additional approval, as they feel more invasive and carry higher trust risk.\n- **Control effectiveness signal.** Simulation results also test your email filtering — high click rates on lures that should have been filtered are a tooling problem, not a people problem.\n\n## Practical workflow\n\n1. **Get authorization:** leadership + HR + legal sign-off on the program charter: purpose, scope, lure boundaries, data handling, and no-punishment policy. Announce the program's existence (not the schedule).\n2. **Baseline:** run a neutral-difficulty simulation to establish click\u002Freport rates by department. This is your before picture.\n3. **Design lures responsibly:** model on current real-world themes (fake shared doc, password expiry, delivery notice); keep difficulty progressive; never use the prohibited themes above.\n4. **Execute safely:** send in waves during business hours; landing pages clearly branded as training; no credential storage — if a form is used, discard input and say so.\n5. **Measure:** click rate, credential-submit rate (if applicable), report rate, median time-to-report, and repeat-clicker rate. Compare against baseline.\n6. **Coach and improve:** immediate micro-training for clickers; targeted coaching for repeat clickers and high-risk roles; share anonymized trends org-wide (\"reporting up 40% — great work\"); feed results into the awareness program.\n\n### Program charter essentials\n\n- Purpose: measure and improve phishing resilience, not punish\n- Scope: which populations, which channels (email; SMS\u002Fvoice only with extra approval)\n- Prohibited lure themes (HR actions, layoffs, personal emergencies, financial threats)\n- Data handling: who sees individual results, retention period\n- No-punishment commitment and coaching approach\n- Success metrics: report rate and time-to-report trending up\n\n### Sustaining the practice\n\n- Vary themes each round; retire lures after a single use\n- Publish anonymized trends org-wide to normalize reporting as a shared win\n- Align simulation difficulty progression with training curriculum\n- Review the program charter annually with HR and legal\n\n### Metrics that prove it works\n\n- Click, submit, and report rates by department, trended per round\n- Median time-to-report (the resilience metric)\n- Repeat-clicker rate after coaching intervention\n- Coaching completion rate for clickers\n\n## Common pitfalls\n\n- **Gotcha culture.** Surprise tests with punishment destroy the trust that reporting culture needs. Announce the program; coach, don't punish.\n- **Cruel or manipulative lures.** Fake layoffs or bonus threats cause real distress and HR crises. Keep lures professional and proportional.\n- **Harvesting real credentials.** Never collect or store actual passwords, even \"for training.\" Use obviously-fake forms and discard input.\n- **Measuring only clicks.** A program that drives clicks down but never measures reporting is optimizing the wrong thing.\n- **Targeting personal accounts or non-employees.** Simulations stay inside the employment relationship and the announced program.\n- **No follow-through.** Simulations without coaching and control improvements are just surveillance. Every round should change training or tooling.\n- **Testing too frequently.** Monthly gotcha emails breed fatigue and resentment. Quarterly themed rounds with fresh lures beat constant low-grade testing.\n- **Reusing the same lure.** Teams learn the template, not the skepticism. Retire lures after one use and model new ones on current real-world campaigns.\n- **Naming and shaming departments.** Public leaderboards of 'worst clickers' destroy trust. Share trends, coach privately, celebrate reporting.\n- **Simulations during layoffs or crises.** Testing stressed employees facing real uncertainty is cruel and produces meaningless data. Pause the program when the org is under strain.\n",{"name":5,"category":24,"description":7},"security","main","af388a77c2fe5e0b4fd879cca4300a0ffa9a6579","skills\u002Fams-phishing-tester",1,"https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis","https:\u002F\u002Fgithub.com\u002FTanNhatCMS","https:\u002F\u002Fmrkiet.name.vn","2026-11-07 14:23:08",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add TanNhatCMS\u002Fjarvis --skill phishing-tester",{"tool":39,"command":40},"bunx","bunx skills add TanNhatCMS\u002Fjarvis --skill phishing-tester",{"tool":42,"command":43},"pnpm","pnpm dlx skills add TanNhatCMS\u002Fjarvis --skill phishing-tester","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fams-phishing-tester\u002FSKILL.md",true,[],[48,55,63,70,77,84],{"skillNo":49,"name":50,"nameZh":6,"description":51,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":52,"categories":53,"keywords":54,"publishedAt":19},"01M7EWYJR0J8DARY7E59Z6Y9MV","web-scrape","Turn web pages into LLM-ready markdown via the Firecrawl API (renders JS, anti-bot handling). Use when browser_open\u002Ffetch fails on JS-heavy pages, or when you need clean markdown\u002Fstructured extraction from a site. Requires FIRECRAWL_API_KEY.","https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fweb-scrape\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":15,"licenseFileUrl":59,"sourceHtmlUrl":60,"categories":61,"keywords":62,"publishedAt":19},"01M7EWYBN5P6F2AJG3FR24T9BP","design-taste-frontend","tasteskill v2, the anti-slop frontend skill. Art direction for websites, distilled from a study of 247 curated gallery sites (One Page Love, Awwwards Sites of the Day). Deals researched directions (idea, composition, type, palette, photographs, section blueprints) from a library, enforces a strict no-slop house style with a real-browser inspector, and runs a look-and-fix loop on screenshots. Use this whenever you build, design, redesign, restyle, polish or review a landing page, marketing site, portfolio, product page, one-pager, hero or any public-facing web page, in any stack (HTML\u002FCSS, React, Next.js, Vue, Svelte, Astro, Tailwind) — also when the user says a page looks generic, templated, \"AI-made\", sloppy, or asks to make it look designed, premium, award-level or less like every other site. Not for dashboards or app screens.","https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Ftaste-design\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Ftaste-design\u002FSKILL.md",[],[],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":69,"publishedAt":19},"01M7EWY8FQFNQ2GB7NZZWGSSDX","test-driven-development","Use when implementing any feature or bugfix, before writing implementation code","https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fsuperpowers-tdd\u002FSKILL.md",[],[],{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":19},"01M7EWY5SHBFRH1HDHVWM9K7TV","systematic-debugging","Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes","https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fsuperpowers-debugging\u002FSKILL.md",[],[],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":19},"01M7EWY3NM0Z0JAKS7HDZ24K66","requesting-code-review","Use when completing tasks, implementing major features, or before merging to verify work meets requirements","https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fsuperpowers-code-review\u002FSKILL.md",[],[],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":19},"01M7EWY0WRMWX4M9ZFY0WKC593","brainstorming","You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or planning anything new, in software or out of it (a talk, a business, a renovation).","https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fsuperpowers-brainstorming\u002FSKILL.md",[],[]]