[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7EVH9BART92KT4KHFJFDAKZ":3,"skill-same:01M7EVH9BART92KT4KHFJFDAKZ":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},"01M7EVH9BART92KT4KHFJFDAKZ","prompt-engineering-guidance",null,"Team-level guidance for prompt engineering — standards, review processes, prompt libraries, versioning, and rollout practices. Use when standardizing how an organization writes and maintains prompts.","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-prompt-engineering-guidance\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: prompt-engineering-guidance\ndescription: Team-level guidance for prompt engineering — standards, review processes, prompt libraries, versioning, and rollout practices. Use when standardizing how an organization writes and maintains prompts.\ncategory: ai-research\n---\n\n# Prompt Engineering Guidance (Team Practice)\n\nIndividual prompt skill doesn't scale; teams need shared standards. This skill covers the \norganizational side: conventions, review, libraries, versioning, and rollout — so prompts become \nmaintained assets instead of tribal knowledge.\n\n## Overview\n\nTreat prompts like code: they live in version control, go through review, have tests, and follow \nstyle conventions. A prompt library gives teams reusable, vetted components (classifiers, \nextractors, summarizers) instead of everyone reinventing them. Rollout practices — staging, \ncanary, rollback — apply because prompt changes are behavior changes. The goal is a team where \nanyone can find, understand, and safely modify any prompt.\n\n## When to use\n\n- Multiple people or teams writing prompts for production systems.\n- Prompts scattered across codebases, notebooks, and chat logs with no ownership.\n- Inconsistent quality: some prompts tested, others written once and forgotten.\n- Preparing to scale LLM features: you need process before volume.\n\n## Core concepts\n\n- **Prompt standards**: conventions for structure (role\u002Ftask\u002Fformat sections), naming, and \ndocumentation headers. Consistency makes prompts reviewable.\n- **Review process**: prompt changes reviewed like code — for clarity, test coverage, cost \nimpact, and safety. A second pair of eyes catches what the author can't.\n- **Prompt library**: versioned, tested, reusable prompts for common jobs. Each entry has a purpose \nstatement, test set, and owner.\n- **Versioning and changelog**: prompts versioned alongside the code that calls them; changes \nlogged with rationale and measured impact.\n- **Staged rollout**: new prompts go to shadow\u002Fstaging first, then a canary slice of traffic, then \nfull rollout — with rollback ready.\n- **Ownership**: every production prompt has an owner responsible for its tests, performance, and \nperiodic re-validation.\n\n## Practical workflow\n\n1. Audit current state: inventory all production prompts, their owners (or lack thereof), and test \ncoverage.\n2. Establish the standard: structure template, documentation header, and review checklist. Keep it \nto one page.\n3. Migrate the highest-traffic prompts first: add tests, assign owners, version them.\n4. Build the library incrementally: extract reusable prompts as they're proven, with their test \nsets.\n5. Institute staged rollouts for prompt changes: shadow → canary → full, with success metrics \ndefined up front.\n6. Schedule re-validation: prompts re-tested on model updates and quarterly; owners accountable.\n\n```text\nPrompt header template:\n# \u003Cname> v\u003Cversion> — owner: \u003Cperson>\n# Purpose: \u003Cone line>\n# Inputs: \u003Cvariables>   Outputs: \u003Cformat\u002Fschema>\n# Tests: \u003Clink to test set>   Last validated: \u003Cdate> on \u003Cmodel>\n# Changelog: \u003Cversion>: \u003Cwhat changed, why>\n```\n\n## Common pitfalls\n\n- **Process without adoption**: a beautiful standard nobody follows. Start with the highest-impact \nprompts and prove value.\n- **Over-standardization**: rigid templates that don't fit creative tasks. Standards for structure \nand testing, freedom for content.\n- **No ownership**: \"everyone owns it\" means nobody maintains it. Name an owner per prompt.\n- **Skipping staging**: pushing prompt changes straight to production. Prompt changes are behavior \nchanges — roll them out like one.\n- **Library rot**: a prompt library nobody updates becomes a museum. Tie library entries to \nre-validation schedules.\n- **Review theater**: rubber-stamping. Reviewers need the test set and before\u002Fafter outputs, not \njust the prompt text.\n","# Prompt Engineering Guidance (Team Practice)\n\nIndividual prompt skill doesn't scale; teams need shared standards. This skill covers the \norganizational side: conventions, review, libraries, versioning, and rollout — so prompts become \nmaintained assets instead of tribal knowledge.\n\n## Overview\n\nTreat prompts like code: they live in version control, go through review, have tests, and follow \nstyle conventions. A prompt library gives teams reusable, vetted components (classifiers, \nextractors, summarizers) instead of everyone reinventing them. Rollout practices — staging, \ncanary, rollback — apply because prompt changes are behavior changes. The goal is a team where \nanyone can find, understand, and safely modify any prompt.\n\n## When to use\n\n- Multiple people or teams writing prompts for production systems.\n- Prompts scattered across codebases, notebooks, and chat logs with no ownership.\n- Inconsistent quality: some prompts tested, others written once and forgotten.\n- Preparing to scale LLM features: you need process before volume.\n\n## Core concepts\n\n- **Prompt standards**: conventions for structure (role\u002Ftask\u002Fformat sections), naming, and \ndocumentation headers. Consistency makes prompts reviewable.\n- **Review process**: prompt changes reviewed like code — for clarity, test coverage, cost \nimpact, and safety. A second pair of eyes catches what the author can't.\n- **Prompt library**: versioned, tested, reusable prompts for common jobs. Each entry has a purpose \nstatement, test set, and owner.\n- **Versioning and changelog**: prompts versioned alongside the code that calls them; changes \nlogged with rationale and measured impact.\n- **Staged rollout**: new prompts go to shadow\u002Fstaging first, then a canary slice of traffic, then \nfull rollout — with rollback ready.\n- **Ownership**: every production prompt has an owner responsible for its tests, performance, and \nperiodic re-validation.\n\n## Practical workflow\n\n1. Audit current state: inventory all production prompts, their owners (or lack thereof), and test \ncoverage.\n2. Establish the standard: structure template, documentation header, and review checklist. Keep it \nto one page.\n3. Migrate the highest-traffic prompts first: add tests, assign owners, version them.\n4. Build the library incrementally: extract reusable prompts as they're proven, with their test \nsets.\n5. Institute staged rollouts for prompt changes: shadow → canary → full, with success metrics \ndefined up front.\n6. Schedule re-validation: prompts re-tested on model updates and quarterly; owners accountable.\n\n```text\nPrompt header template:\n# \u003Cname> v\u003Cversion> — owner: \u003Cperson>\n# Purpose: \u003Cone line>\n# Inputs: \u003Cvariables>   Outputs: \u003Cformat\u002Fschema>\n# Tests: \u003Clink to test set>   Last validated: \u003Cdate> on \u003Cmodel>\n# Changelog: \u003Cversion>: \u003Cwhat changed, why>\n```\n\n## Common pitfalls\n\n- **Process without adoption**: a beautiful standard nobody follows. Start with the highest-impact \nprompts and prove value.\n- **Over-standardization**: rigid templates that don't fit creative tasks. Standards for structure \nand testing, freedom for content.\n- **No ownership**: \"everyone owns it\" means nobody maintains it. Name an owner per prompt.\n- **Skipping staging**: pushing prompt changes straight to production. Prompt changes are behavior \nchanges — roll them out like one.\n- **Library rot**: a prompt library nobody updates becomes a museum. Tie library entries to \nre-validation schedules.\n- **Review theater**: rubber-stamping. Reviewers need the test set and before\u002Fafter outputs, not \njust the prompt text.\n",{"name":5,"category":24,"description":7},"ai-research","main","af388a77c2fe5e0b4fd879cca4300a0ffa9a6579","skills\u002Fams-prompt-engineering-guidance",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 prompt-engineering-guidance",{"tool":39,"command":40},"bunx","bunx skills add TanNhatCMS\u002Fjarvis --skill prompt-engineering-guidance",{"tool":42,"command":43},"pnpm","pnpm dlx skills add TanNhatCMS\u002Fjarvis --skill prompt-engineering-guidance","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fams-prompt-engineering-guidance\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",[],[]]