[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6FWRWSSGQJ56AAXFPPP5EFC":3,"skill-same:01M6FWRWSSGQJ56AAXFPPP5EFC":63},{"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":32,"linkOnly":33,"markdownContent":34,"markdownBody":35,"frontMatter":36,"refName":39,"commitSha":40,"skillDirectory":41,"forksCount":42,"repositoryHtmlUrl":43,"repositoryHomepageUrl":44,"ownerHtmlUrl":45,"ownerBlogUrl":46,"ownerDescription":47,"updatedAt":48,"install":49,"resources":62},"01M6FWRWSSGQJ56AAXFPPP5EFC","uat-guide",null,"Expand a UAT journey into click-by-click tester instructions, then update the result log on completion","GeorgeQLe\u002Fagentic-skills","GeorgeQLe","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F21134126?v=4","01M6D2JP418S0VGJGF8M93EC3H","George Le","01M6D2JPBAKYD82TA5FS6HKQ3D",1,"MIT","https:\u002F\u002Fgithub.com\u002FGeorgeQLe\u002Fagentic-skills\u002Fblob\u002Fmaster\u002Fpacks\u002Fguided-walkthrough\u002Fclaude\u002Fuat-guide\u002Farchive\u002Fv0.1\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31],"guide","uat guide","update","analysis","instructions","v0","log","tester","journey","next","click","expand","name","2026-11-10 10:12:30",false,"---\nname: uat-guide\ndescription: Expand a UAT journey into click-by-click tester instructions, then update the result log on completion\ntype: analysis\nversion: v0.1\nargument-hint: \"[optional: journey number, journey name, or 'next']\"\n---\n\n# UAT Guide\n\nInvoke as `\u002Fuat-guide`.\n\nExpand a single UAT journey from `research\u002Fuat-plan.md` into detailed, step-by-step tester instructions. UAT planning (`\u002Fuat`) produces high-level task sequences (\"sign up\", \"navigate to dashboard\"); this skill turns each step into click-by-click, command-by-command, or request-by-request guidance that a tester unfamiliar with the product can follow without ambiguity.\n\nDo not generate UAT journeys. If no UAT plan exists, stop and recommend `\u002Fuat` (product-testing pack).\n\n## Process\n\n1. **Locate UAT plan**\n   - Read `research\u002Fuat-plan.md`.\n   - If the file does not exist, stop and tell the user: \"No UAT plan found. Run `\u002Fuat` first to generate acceptance journeys.\"\n\n2. **Select journey**\n   - Parse all `### Journey N:` headings and their `#### UAT result log` status fields.\n   - If `$ARGUMENTS` is non-empty, match by journey number or name (case-insensitive substring match).\n   - If `$ARGUMENTS` is `next` or empty, pick the first journey whose status is `Not run`.\n   - If all journeys have status `Pass`, `Fail`, or `Blocked`, tell the user all journeys are complete and offer to re-run a specific one.\n\n3. **Gather project context**\n   - Read `.agents\u002Fproject.json`, `README.md`, `CLAUDE.md`, relevant `specs\u002F`, `docs\u002F`, and `tasks\u002F` files when present.\n   - Search the codebase for routes, UI components, CLI entry points, API endpoints, environment variables, configuration files, and navigation structure relevant to the selected journey's task sequence.\n\n4. **Detect product interface type**\n   - Classify the product surface the journey touches:\n     - **Web app** -> click-by-click instructions (buttons, links, forms, pages).\n     - **CLI** -> command-by-command instructions (exact commands, flags, expected output).\n     - **API** -> request-by-request instructions (method, URL, headers, body, expected response).\n     - **Hybrid** -> mixed instructions matching each step's surface.\n   - Use the detected type to shape the instruction style for step 6.\n\n5. **Research current instructions**\n   - Use web search to find up-to-date documentation for any external services or platforms referenced in the journey (OAuth providers, third-party dashboards, payment processors, DNS registrars, etc.).\n   - Prioritize official documentation over blog posts.\n   - Service UIs change frequently — never rely solely on prior knowledge; always search.\n\n6. **Expand task sequence**\n   - For each step in the journey's task sequence, produce:\n     - **Numbered sub-steps** with exact UI elements to click, commands to run, or requests to make. Use project-specific values (URLs, routes, field names, env vars) drawn from codebase context.\n     - **Checkpoint** tied to the journey's acceptance criteria — what the tester should observe to confirm the step succeeded.\n     - **Evidence capture point** — what to screenshot, copy, or record at this step.\n     - **Gotchas** — common mistakes, timing issues, or easy-to-miss details.\n   - Begin the guide with a **Preparation** section drawn from the journey's Setup field (accounts, data, environment, permissions needed before starting).\n   - End the guide with a **Final verification** section drawn from the journey's acceptance criteria and expected success state.\n\n7. **Present guide**\n   - Output the guide directly in the conversation. Do not write it to a file.\n\n8. **Collect results**\n   - After presenting the guide, tell the user: \"When you've completed this journey, let me know the result (Pass \u002F Fail \u002F Blocked) and any notes, and I'll update the result log.\"\n   - When the user reports completion:\n     - Update the `#### UAT result log` section for this journey inline in `research\u002Fuat-plan.md` with the reported status, evidence, tester notes, and any follow-up tasks promoted.\n     - Check off the corresponding item in `tasks\u002Fmanual-todo.md`.\n     - If the result is `Fail` or `Blocked`, suggest follow-up routing: `\u002Fdebug` for reproducible failures, `\u002Fguide` for external blockers, `\u002Fux-variations` (product-design pack) for unclear acceptance criteria, or `\u002Fuat-guide [next]` for the next journey.\n\n## Output\n\n```\n## UAT Guide: Journey N — [Journey Name]\n\n**Target user**: [persona or role]\n**User goal**: [what the user is trying to accomplish]\n**Product surface**: [Web app | CLI | API | Hybrid]\n\n### Preparation\n\n- [Account, data, environment, or permission setup needed before starting]\n- [Pre-existing state or sample data to have ready]\n\n### Steps\n\n#### Step 1: [Task sequence step name]\n\n1. [Exact action — click, type, run, send]\n2. [Next action with specific UI element \u002F command \u002F request detail]\n3. ...\n\n**Checkpoint**: [What the tester should see or verify]\n**Evidence**: [What to capture — screenshot, output, response]\n**Gotchas**: [Common mistake or easy-to-miss detail, if any]\n\n#### Step 2: [Task sequence step name]\n\n1. ...\n\n...\n\n### Final Verification\n\n- [ ] [Acceptance criterion from the journey]\n- [ ] [Another acceptance criterion]\n- [ ] Expected success state: [observable user-visible result]\n\n### Non-Acceptance Signals\n\n- [Confusion, delay, missing affordance, incorrect result, trust issue, or blocker to watch for]\n\n### Tester Notes Prompt\n\n> [Question from the journey that captures whether the target user would accept this]\n\n---\n\nWhen you've completed this journey, let me know the result (Pass \u002F Fail \u002F Blocked) and any notes, and I'll update the result log.\n```\n\n## Alignment Page\n\nWhen this skill produces durable deliverables (research, specs, plans, reports, prototypes, or any document output), build a full-depth HTML alignment page following `ALIGNMENT-PAGE.md` in this skill's directory. Output: `alignment\u002Fuat-guide-{topic}.html`.\n\n## Constraints\n\n- **Always web search** for external services and platforms referenced in the journey. Service UIs change; stale steps are worse than none.\n- **Project-specific values** — never give generic placeholders when the codebase contains the actual values to use (URLs, routes, env vars, field names, commands).\n- **Read-only except result log** — this skill does not modify code. The only files it may edit are `research\u002Fuat-plan.md` (result log section) and `tasks\u002Fmanual-todo.md` (to check off a completed item), and only after the user reports completion.\n- **No shipping contract** — updating a result log and checking off a manual-todo item is minor bookkeeping, not a code change. Do not auto-commit just for that. If other tracked changes are present, leave them for a proper shipping skill.\n- **One journey at a time** — guide the user through one journey per invocation. They can run `\u002Fuat-guide next` for the next one.\n- **Don't execute the product** — produce instructions for the user to follow. Do not start dev servers, launch browsers, call APIs, create accounts, or perform CLI workflows.\n- **Don't mark complete unprompted** — only update the result log after the user explicitly reports the outcome.\n- **Don't invent acceptance criteria** — use only the criteria defined in the UAT plan. If criteria are missing or unclear, recommend `\u002Fux-variations` (product-design pack) to clarify them.\n- **Handle all product surface types** — web apps get click-by-click, CLIs get command-by-command, APIs get request-by-request, hybrids get mixed. Detect from codebase context; don't assume web.\n- **Prerequisite: UAT plan must exist** — if `research\u002Fuat-plan.md` is missing, stop immediately and recommend `\u002Fuat` (product-testing pack).\n- When recommending a skill from another pack, verify the pack is installed via `.agents\u002Fproject.json` `enabled_packs`. If not installed, prepend `\u002Fpack install \u003Cpack-name>` to the recommendation.\n\n## Default Shipping Contract\n\nFollow the shared shipping contract convention in CLAUDE.md.\n","# UAT Guide\n\nInvoke as `\u002Fuat-guide`.\n\nExpand a single UAT journey from `research\u002Fuat-plan.md` into detailed, step-by-step tester instructions. UAT planning (`\u002Fuat`) produces high-level task sequences (\"sign up\", \"navigate to dashboard\"); this skill turns each step into click-by-click, command-by-command, or request-by-request guidance that a tester unfamiliar with the product can follow without ambiguity.\n\nDo not generate UAT journeys. If no UAT plan exists, stop and recommend `\u002Fuat` (product-testing pack).\n\n## Process\n\n1. **Locate UAT plan**\n   - Read `research\u002Fuat-plan.md`.\n   - If the file does not exist, stop and tell the user: \"No UAT plan found. Run `\u002Fuat` first to generate acceptance journeys.\"\n\n2. **Select journey**\n   - Parse all `### Journey N:` headings and their `#### UAT result log` status fields.\n   - If `$ARGUMENTS` is non-empty, match by journey number or name (case-insensitive substring match).\n   - If `$ARGUMENTS` is `next` or empty, pick the first journey whose status is `Not run`.\n   - If all journeys have status `Pass`, `Fail`, or `Blocked`, tell the user all journeys are complete and offer to re-run a specific one.\n\n3. **Gather project context**\n   - Read `.agents\u002Fproject.json`, `README.md`, `CLAUDE.md`, relevant `specs\u002F`, `docs\u002F`, and `tasks\u002F` files when present.\n   - Search the codebase for routes, UI components, CLI entry points, API endpoints, environment variables, configuration files, and navigation structure relevant to the selected journey's task sequence.\n\n4. **Detect product interface type**\n   - Classify the product surface the journey touches:\n     - **Web app** -> click-by-click instructions (buttons, links, forms, pages).\n     - **CLI** -> command-by-command instructions (exact commands, flags, expected output).\n     - **API** -> request-by-request instructions (method, URL, headers, body, expected response).\n     - **Hybrid** -> mixed instructions matching each step's surface.\n   - Use the detected type to shape the instruction style for step 6.\n\n5. **Research current instructions**\n   - Use web search to find up-to-date documentation for any external services or platforms referenced in the journey (OAuth providers, third-party dashboards, payment processors, DNS registrars, etc.).\n   - Prioritize official documentation over blog posts.\n   - Service UIs change frequently — never rely solely on prior knowledge; always search.\n\n6. **Expand task sequence**\n   - For each step in the journey's task sequence, produce:\n     - **Numbered sub-steps** with exact UI elements to click, commands to run, or requests to make. Use project-specific values (URLs, routes, field names, env vars) drawn from codebase context.\n     - **Checkpoint** tied to the journey's acceptance criteria — what the tester should observe to confirm the step succeeded.\n     - **Evidence capture point** — what to screenshot, copy, or record at this step.\n     - **Gotchas** — common mistakes, timing issues, or easy-to-miss details.\n   - Begin the guide with a **Preparation** section drawn from the journey's Setup field (accounts, data, environment, permissions needed before starting).\n   - End the guide with a **Final verification** section drawn from the journey's acceptance criteria and expected success state.\n\n7. **Present guide**\n   - Output the guide directly in the conversation. Do not write it to a file.\n\n8. **Collect results**\n   - After presenting the guide, tell the user: \"When you've completed this journey, let me know the result (Pass \u002F Fail \u002F Blocked) and any notes, and I'll update the result log.\"\n   - When the user reports completion:\n     - Update the `#### UAT result log` section for this journey inline in `research\u002Fuat-plan.md` with the reported status, evidence, tester notes, and any follow-up tasks promoted.\n     - Check off the corresponding item in `tasks\u002Fmanual-todo.md`.\n     - If the result is `Fail` or `Blocked`, suggest follow-up routing: `\u002Fdebug` for reproducible failures, `\u002Fguide` for external blockers, `\u002Fux-variations` (product-design pack) for unclear acceptance criteria, or `\u002Fuat-guide [next]` for the next journey.\n\n## Output\n\n```\n## UAT Guide: Journey N — [Journey Name]\n\n**Target user**: [persona or role]\n**User goal**: [what the user is trying to accomplish]\n**Product surface**: [Web app | CLI | API | Hybrid]\n\n### Preparation\n\n- [Account, data, environment, or permission setup needed before starting]\n- [Pre-existing state or sample data to have ready]\n\n### Steps\n\n#### Step 1: [Task sequence step name]\n\n1. [Exact action — click, type, run, send]\n2. [Next action with specific UI element \u002F command \u002F request detail]\n3. ...\n\n**Checkpoint**: [What the tester should see or verify]\n**Evidence**: [What to capture — screenshot, output, response]\n**Gotchas**: [Common mistake or easy-to-miss detail, if any]\n\n#### Step 2: [Task sequence step name]\n\n1. ...\n\n...\n\n### Final Verification\n\n- [ ] [Acceptance criterion from the journey]\n- [ ] [Another acceptance criterion]\n- [ ] Expected success state: [observable user-visible result]\n\n### Non-Acceptance Signals\n\n- [Confusion, delay, missing affordance, incorrect result, trust issue, or blocker to watch for]\n\n### Tester Notes Prompt\n\n> [Question from the journey that captures whether the target user would accept this]\n\n---\n\nWhen you've completed this journey, let me know the result (Pass \u002F Fail \u002F Blocked) and any notes, and I'll update the result log.\n```\n\n## Alignment Page\n\nWhen this skill produces durable deliverables (research, specs, plans, reports, prototypes, or any document output), build a full-depth HTML alignment page following `ALIGNMENT-PAGE.md` in this skill's directory. Output: `alignment\u002Fuat-guide-{topic}.html`.\n\n## Constraints\n\n- **Always web search** for external services and platforms referenced in the journey. Service UIs change; stale steps are worse than none.\n- **Project-specific values** — never give generic placeholders when the codebase contains the actual values to use (URLs, routes, env vars, field names, commands).\n- **Read-only except result log** — this skill does not modify code. The only files it may edit are `research\u002Fuat-plan.md` (result log section) and `tasks\u002Fmanual-todo.md` (to check off a completed item), and only after the user reports completion.\n- **No shipping contract** — updating a result log and checking off a manual-todo item is minor bookkeeping, not a code change. Do not auto-commit just for that. If other tracked changes are present, leave them for a proper shipping skill.\n- **One journey at a time** — guide the user through one journey per invocation. They can run `\u002Fuat-guide next` for the next one.\n- **Don't execute the product** — produce instructions for the user to follow. Do not start dev servers, launch browsers, call APIs, create accounts, or perform CLI workflows.\n- **Don't mark complete unprompted** — only update the result log after the user explicitly reports the outcome.\n- **Don't invent acceptance criteria** — use only the criteria defined in the UAT plan. If criteria are missing or unclear, recommend `\u002Fux-variations` (product-design pack) to clarify them.\n- **Handle all product surface types** — web apps get click-by-click, CLIs get command-by-command, APIs get request-by-request, hybrids get mixed. Detect from codebase context; don't assume web.\n- **Prerequisite: UAT plan must exist** — if `research\u002Fuat-plan.md` is missing, stop immediately and recommend `\u002Fuat` (product-testing pack).\n- When recommending a skill from another pack, verify the pack is installed via `.agents\u002Fproject.json` `enabled_packs`. If not installed, prepend `\u002Fpack install \u003Cpack-name>` to the recommendation.\n\n## Default Shipping Contract\n\nFollow the shared shipping contract convention in CLAUDE.md.\n",{"name":5,"type":22,"version":37,"description":7,"argument-hint":38},"v0.1","[optional: journey number, journey name, or 'next']","master","96e2912af886dd1606b1b97df707715aef062b02","packs\u002Fguided-walkthrough\u002Fclaude\u002Fuat-guide\u002Farchive\u002Fv0.1",0,"https:\u002F\u002Fgithub.com\u002FGeorgeQLe\u002Fagentic-skills","https:\u002F\u002Fagentic-skills-blush.vercel.app","https:\u002F\u002Fgithub.com\u002FGeorgeQLe","georgeqle.com","George Le is a futurist and serial tech entrepreneur who wants to work toward a world where humanity is free from robotic tasks.","2026-11-10 04:07:24",{"source":8,"skillName":5,"commands":50,"prompt":60,"zipAvailable":61},[51,54,57],{"tool":52,"command":53},"npx","npx skills add GeorgeQLe\u002Fagentic-skills --skill uat-guide",{"tool":55,"command":56},"bunx","bunx skills add GeorgeQLe\u002Fagentic-skills --skill uat-guide",{"tool":58,"command":59},"pnpm","pnpm dlx skills add GeorgeQLe\u002Fagentic-skills --skill uat-guide","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FGeorgeQLe\u002Fagentic-skills\u002Fblob\u002Fmaster\u002Fpacks\u002Fguided-walkthrough\u002Fclaude\u002Fuat-guide\u002Farchive\u002Fv0.1\u002FSKILL.md",true,[],[64,76,86,98,113,124],{"skillNo":65,"name":66,"nameZh":6,"description":67,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":68,"categories":69,"keywords":70,"publishedAt":32},"01M6G0NJES15RJKZE6YZ0TSYGF","source-checkout-allowed","Valid source-checkout-only fixture.","https:\u002F\u002Fgithub.com\u002FGeorgeQLe\u002Fagentic-skills\u002Fblob\u002Fmaster\u002Ftests\u002Ffixtures\u002Fskill-install-routing\u002Fvalid\u002Fsource-checkout-allowed\u002FSKILL.md",[],[71,72,73,74,24,75],"source checkout allowed","checkout","fixture","only","valid",{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":32},"01M6G0NFZ3R1MNB1E3DVTM0WB7","deck-install-valid","Valid deck install fixture.","https:\u002F\u002Fgithub.com\u002FGeorgeQLe\u002Fagentic-skills\u002Fblob\u002Fmaster\u002Ftests\u002Ffixtures\u002Fskill-install-routing\u002Fvalid\u002Fdeck-install\u002FSKILL.md",[],[83,84,85,75,73,24],"deck install valid","deck","install",{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":32},"01M6G0ND3QZQC4MDZ9NVB97PT2","codex-pack-guard-valid","Valid Codex Pack Availability Guard fixture.","https:\u002F\u002Fgithub.com\u002FGeorgeQLe\u002Fagentic-skills\u002Fblob\u002Fmaster\u002Ftests\u002Ffixtures\u002Fskill-install-routing\u002Fvalid\u002Fcodex-pack-guard\u002FSKILL.md",[],[93,94,95,75,96,97,73,24],"codex pack guard valid","pack","guard","codex","availability",{"skillNo":99,"name":100,"nameZh":6,"description":101,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":102,"categories":103,"keywords":109,"publishedAt":32},"01M6G0NA9YB3NKGZKD3S96JMNB","codex-missing-skill-valid","Valid Codex missing skill fallback fixture.","https:\u002F\u002Fgithub.com\u002FGeorgeQLe\u002Fagentic-skills\u002Fblob\u002Fmaster\u002Ftests\u002Ffixtures\u002Fskill-install-routing\u002Fvalid\u002Fcodex-missing-skill-fallback\u002FSKILL.md",[104],{"categoryNo":105,"categoryName":106,"taxonomyType":107,"taxonomyTypeDesc":108},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[110,111,75,96,24,112,73],"codex missing skill valid","missing","fallback",{"skillNo":114,"name":115,"nameZh":6,"description":116,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":117,"categories":118,"keywords":120,"publishedAt":32},"01M6G0N7PC0EKFD40ZWQAXSAQ9","codex-base-skill-fallback-valid","Valid Codex base skill fallback fixture.","https:\u002F\u002Fgithub.com\u002FGeorgeQLe\u002Fagentic-skills\u002Fblob\u002Fmaster\u002Ftests\u002Ffixtures\u002Fskill-install-routing\u002Fvalid\u002Fcodex-base-skill-fallback\u002FSKILL.md",[119],{"categoryNo":105,"categoryName":106,"taxonomyType":107,"taxonomyTypeDesc":108},[75,96,112,121,122,123,24,73],"base skill","codex base skill fallback valid","base",{"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":32},"01M6G0N4VRR2YKZQ6N3Y6S2BQA","claude-pack-guard-valid","Valid Claude Pack Availability Guard fixture.","https:\u002F\u002Fgithub.com\u002FGeorgeQLe\u002Fagentic-skills\u002Fblob\u002Fmaster\u002Ftests\u002Ffixtures\u002Fskill-install-routing\u002Fvalid\u002Fclaude-pack-guard\u002FSKILL.md",[],[75,95,94,131,97,24,73],"claude pack guard valid"]