[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7DFV78F5DH17A9ZTY8ZZTC8":3,"skill-same:01M7DFV78F5DH17A9ZTY8ZZTC8":72},{"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":14,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":29,"ownerDescription":30,"updatedAt":31,"install":32,"resources":45},"01M7DFV78F5DH17A9ZTY8ZZTC8","qa-session",null,"Run a QA session for a unit of work (milestone, task, diff, PR) against any surface — Website, Docker Compose, HTTP API, gRPC, MCP, GraphQL. Derives the user experience the work should deliver, confirms it, probes the running surface, delivers a verdict report. Triggers include \"QA this\", \"QA session\", \"verify the milestone\", \"verify this PR\", \"acceptance check\", \"does this deliver\", \"check user experience\".","heynemann\u002Fomp-marketplace","heynemann","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F60965?v=4","01M7DFBD9ZDB2J2QE7R4AR0PES","Bernardo Heynemann","01M7DFBDAM3NXF540P210W3NYT",0,"MIT","https:\u002F\u002Fgithub.com\u002Fheynemann\u002Fomp-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Fbase\u002Fskills\u002Fqa-session\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: qa-session\ndescription: Run a QA session for a unit of work (milestone, task, diff, PR) against any surface — Website, Docker Compose, HTTP API, gRPC, MCP, GraphQL. Derives the user experience the work should deliver, confirms it, probes the running surface, delivers a verdict report. Triggers include \"QA this\", \"QA session\", \"verify the milestone\", \"verify this PR\", \"acceptance check\", \"does this deliver\", \"check user experience\".\n---\n\nRun the QA session as four steps. Each ends on its completion criterion; do not advance early.\n\n## 1. Bound the work\n\nIdentify the work unit and what changed in it: read the milestone\u002Ftask\u002Fdiff\u002FPR description and the actual changes (diff, files, commits). Ground facts in the repo; note claims the description makes that the diff does not show.\n\nCompletion: one paragraph — what changed, what it claims to deliver.\n\n## 2. Derive the UX contract\n\nFrom the work unit, state the user experiences that should be observable on the surface. For each expectation write: who the user is, what they do, what they must see or get. Expectations are outcome statements, not implementation steps.\n\nThen confirm with the user via `ask`: present the contract, ask them to correct, add, or drop expectations. Do not probe before confirmation — a QA session against the wrong contract produces a confident wrong verdict.\n\nCompletion: user-confirmed list of expectations. This list is the source of truth for the verdict.\n\n## 3. Probe the surface\n\nLoad the reference for the surface the user named, read it, then probe:\n\n- Website → `skill:\u002F\u002Fqa-session\u002Freferences\u002Fwebsite.md`\n- HTTP API → `skill:\u002F\u002Fqa-session\u002Freferences\u002Fhttp.md`\n- gRPC API → `skill:\u002F\u002Fqa-session\u002Freferences\u002Fgrpc.md`\n- MCP server → `skill:\u002F\u002Fqa-session\u002Freferences\u002Fmcp.md`\n- GraphQL API → `skill:\u002F\u002Fqa-session\u002Freferences\u002Fgraphql.md`\n- Docker Compose → `skill:\u002F\u002Fqa-session\u002Freferences\u002Fcompose.md`\n\nIf the surface is not running, bring it up first (compose.md covers startup for stack surfaces). Probe every confirmed expectation. Each expectation MUST end with a verdict and captured evidence — a screenshot, a response body, a log line, a measured value. An expectation without evidence is unprobed, not passed.\n\nCompletion: every expectation has verdict + evidence, or is explicitly marked blocked with the reason (surface unreachable, prerequisite missing).\n\n## 4. Verdict report\n\nDeliver:\n\n```\n## QA Verdict: \u003Cwork unit> — \u003CN>\u002F\u003Ctotal> pass\n\nPASS \u003Cexpectation> — \u003Cevidence one-liner>\nFAIL \u003Cexpectation> — \u003Cwhat diverged>, \u003Cevidence one-liner>\nBLOCKED \u003Cexpectation> — \u003Cwhy>\n\nBlocking: \u003Ccount> — \u003Cthe failures that break the core experience>\n```\n\nClassify a failure blocking when it breaks the experience a normal user hits on the happy path. Divergences on edge cases, cosmetics, or contract details are non-blocking unless the work unit explicitly claims them. Cite evidence verbatim; never summarize a response you did not capture.\n","Run the QA session as four steps. Each ends on its completion criterion; do not advance early.\n\n## 1. Bound the work\n\nIdentify the work unit and what changed in it: read the milestone\u002Ftask\u002Fdiff\u002FPR description and the actual changes (diff, files, commits). Ground facts in the repo; note claims the description makes that the diff does not show.\n\nCompletion: one paragraph — what changed, what it claims to deliver.\n\n## 2. Derive the UX contract\n\nFrom the work unit, state the user experiences that should be observable on the surface. For each expectation write: who the user is, what they do, what they must see or get. Expectations are outcome statements, not implementation steps.\n\nThen confirm with the user via `ask`: present the contract, ask them to correct, add, or drop expectations. Do not probe before confirmation — a QA session against the wrong contract produces a confident wrong verdict.\n\nCompletion: user-confirmed list of expectations. This list is the source of truth for the verdict.\n\n## 3. Probe the surface\n\nLoad the reference for the surface the user named, read it, then probe:\n\n- Website → `skill:\u002F\u002Fqa-session\u002Freferences\u002Fwebsite.md`\n- HTTP API → `skill:\u002F\u002Fqa-session\u002Freferences\u002Fhttp.md`\n- gRPC API → `skill:\u002F\u002Fqa-session\u002Freferences\u002Fgrpc.md`\n- MCP server → `skill:\u002F\u002Fqa-session\u002Freferences\u002Fmcp.md`\n- GraphQL API → `skill:\u002F\u002Fqa-session\u002Freferences\u002Fgraphql.md`\n- Docker Compose → `skill:\u002F\u002Fqa-session\u002Freferences\u002Fcompose.md`\n\nIf the surface is not running, bring it up first (compose.md covers startup for stack surfaces). Probe every confirmed expectation. Each expectation MUST end with a verdict and captured evidence — a screenshot, a response body, a log line, a measured value. An expectation without evidence is unprobed, not passed.\n\nCompletion: every expectation has verdict + evidence, or is explicitly marked blocked with the reason (surface unreachable, prerequisite missing).\n\n## 4. Verdict report\n\nDeliver:\n\n```\n## QA Verdict: \u003Cwork unit> — \u003CN>\u002F\u003Ctotal> pass\n\nPASS \u003Cexpectation> — \u003Cevidence one-liner>\nFAIL \u003Cexpectation> — \u003Cwhat diverged>, \u003Cevidence one-liner>\nBLOCKED \u003Cexpectation> — \u003Cwhy>\n\nBlocking: \u003Ccount> — \u003Cthe failures that break the core experience>\n```\n\nClassify a failure blocking when it breaks the experience a normal user hits on the happy path. Divergences on edge cases, cosmetics, or contract details are non-blocking unless the work unit explicitly claims them. Cite evidence verbatim; never summarize a response you did not capture.\n",{"name":5,"description":7},"main","2147d79c9cd764770418b462c29634bcdc710096","plugins\u002Fbase\u002Fskills\u002Fqa-session","https:\u002F\u002Fgithub.com\u002Fheynemann\u002Fomp-marketplace","https:\u002F\u002Fgithub.com\u002Fheynemann","http:\u002F\u002Fwww.thumbor.org","CTO @ Flutter Brazil | Former Meta & Coinbase","2026-09-29 21:26:05",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add heynemann\u002Fomp-marketplace --skill qa-session",{"tool":38,"command":39},"bunx","bunx skills add heynemann\u002Fomp-marketplace --skill qa-session",{"tool":41,"command":42},"pnpm","pnpm dlx skills add heynemann\u002Fomp-marketplace --skill qa-session","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fheynemann\u002Fomp-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Fbase\u002Fskills\u002Fqa-session\u002FSKILL.md",true,[46,52,56,60,64,68],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fcompose.md","REFERENCE","参考文档",1259,"https:\u002F\u002Fgithub.com\u002Fheynemann\u002Fomp-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Fbase\u002Fskills\u002Fqa-session\u002Freferences\u002Fcompose.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Fgraphql.md",1101,"https:\u002F\u002Fgithub.com\u002Fheynemann\u002Fomp-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Fbase\u002Fskills\u002Fqa-session\u002Freferences\u002Fgraphql.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Fgrpc.md",995,"https:\u002F\u002Fgithub.com\u002Fheynemann\u002Fomp-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Fbase\u002Fskills\u002Fqa-session\u002Freferences\u002Fgrpc.md",{"path":61,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":62,"sourceHtmlUrl":63},"references\u002Fhttp.md",1031,"https:\u002F\u002Fgithub.com\u002Fheynemann\u002Fomp-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Fbase\u002Fskills\u002Fqa-session\u002Freferences\u002Fhttp.md",{"path":65,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":66,"sourceHtmlUrl":67},"references\u002Fmcp.md",1062,"https:\u002F\u002Fgithub.com\u002Fheynemann\u002Fomp-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Fbase\u002Fskills\u002Fqa-session\u002Freferences\u002Fmcp.md",{"path":69,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":70,"sourceHtmlUrl":71},"references\u002Fwebsite.md",1219,"https:\u002F\u002Fgithub.com\u002Fheynemann\u002Fomp-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Fbase\u002Fskills\u002Fqa-session\u002Freferences\u002Fwebsite.md",[73,80,87,94,101,108],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":19},"01M7DFXDYP0N6P8KR0AF7C0TDK","writing-for-agents","Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.","https:\u002F\u002Fgithub.com\u002Fheynemann\u002Fomp-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Fbase\u002Fskills\u002Fwriting-for-agents\u002FSKILL.md",[],[],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":19},"01M7DFX9C5B0T1T0AVDCWNR5P2","write-skill","Use when creating, designing, or fixing an agent skill (SKILL.md pack) — triggers include \"write a skill\", \"make me a skill\", \"create a skill\", skill directories, and skills that fail to trigger or fire on the wrong tasks.","https:\u002F\u002Fgithub.com\u002Fheynemann\u002Fomp-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Fbase\u002Fskills\u002Fwrite-skill\u002FSKILL.md",[],[],{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":19},"01M7DFX64VSTQV0CSGYR76MPZF","write-agent","Use when creating, designing, or fixing an omp subagent (task agent) — triggers include \"write an agent\", \"make me an agent\", \"create a subagent\", agent `.md` definitions, and agents that misbehave when spawned via task.","https:\u002F\u002Fgithub.com\u002Fheynemann\u002Fomp-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Fbase\u002Fskills\u002Fwrite-agent\u002FSKILL.md",[],[],{"skillNo":95,"name":96,"nameZh":6,"description":97,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":100,"publishedAt":19},"01M7DFX22JEY7ZN9EDESM732K5","wizard","Generate an interactive bash wizard that walks a human through steps only they can perform. Use when provisioning infrastructure, setting up credentials or CI secrets, walking an unfamiliar third-party dashboard, or running a one-off migration or cutover. Don't invoke this for steps the agent can perform itself.","https:\u002F\u002Fgithub.com\u002Fheynemann\u002Fomp-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Fbase\u002Fskills\u002Fwizard\u002FSKILL.md",[],[],{"skillNo":102,"name":103,"nameZh":6,"description":104,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":105,"categories":106,"keywords":107,"publishedAt":19},"01M7DFWYXR5V2CY2BPDAAS19R1","wayfinder","Plan a huge chunk of work (more than one agent session can hold) as a shared map of decision tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear.","https:\u002F\u002Fgithub.com\u002Fheynemann\u002Fomp-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Fbase\u002Fskills\u002Fwayfinder\u002FSKILL.md",[],[],{"skillNo":109,"name":110,"nameZh":6,"description":111,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":112,"categories":113,"keywords":114,"publishedAt":19},"01M7DFWXFFMBKV294WS66S475V","wait-what","Stop. That last message did not land: re-pitch it.","https:\u002F\u002Fgithub.com\u002Fheynemann\u002Fomp-marketplace\u002Fblob\u002Fmain\u002Fplugins\u002Fbase\u002Fskills\u002Fwait-what\u002FSKILL.md",[],[]]