[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71EKYDRBAD8TK1K77ACW6CD":3,"skill-same:01M71EKYDRBAD8TK1K77ACW6CD":68},{"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":35,"linkOnly":36,"markdownContent":37,"markdownBody":38,"frontMatter":39,"refName":40,"commitSha":41,"skillDirectory":42,"forksCount":14,"repositoryHtmlUrl":43,"repositoryHomepageUrl":6,"ownerHtmlUrl":44,"ownerBlogUrl":45,"ownerDescription":46,"updatedAt":47,"install":48,"resources":61},"01M71EKYDRBAD8TK1K77ACW6CD","gather-evidence",null,"Gather direct evidence from the current target before responding to a human change request or QA finding. Use when human feedback needs confirmation or proof of resolution.","patinaproject\u002Fskills","patinaproject","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F229996889?v=4","01M71E58JKTDNY1138WYZK44TR","Patina Project","01M71E58K5GH4K16MV6A8BQ6NZ",1,"MIT","https:\u002F\u002Fgithub.com\u002Fpatinaproject\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fcode\u002Fskills\u002Fgather-evidence\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34],"evidence","gather","gather evidence","resolution","target","change","feedback","human","request","change request","qa","proof","use","confirmation","direct","when","2026-11-10 10:12:30",false,"---\nname: gather-evidence\ndescription: Gather direct evidence from the current target before responding to a human change request or QA finding. Use when human feedback needs confirmation or proof of resolution.\n---\n\n# Gather evidence\n\nTreat human feedback as a claim or requested outcome to investigate. Do not edit\ncode, reply to the person, resolve their thread, or change their review state.\n\n## Define the evidence cases\n\nRead the complete feedback and its nearby context. Split independent claims\ninto separate evidence cases. Record each case using\n[the evidence fields](references\u002Fevidence.md#evidence-case):\n\n- the exact feedback source\n- the requested behavior or result\n- the expected and reported behavior\n- the exact check and required environment\n- the current target, pull request, commit, build, or deployment\n\nDo not translate a concrete observation into a proxy. Ask for missing context\nonly when no direct check can resolve it.\n\n## Inspect the current target\n\nResolve the current target before gathering evidence. For pull request\nfeedback, record the current head SHA and confirm that the local checkout or\ndeployed build matches it. A later push invalidates the evidence.\n\nGather direct evidence from the interface named by the feedback. Inspect the code\nand diff for source claims. Run the exact interaction for behavioral claims.\nUse the applicable driver for a UI, CLI, or runtime. Before changing a mobile\nsimulator or running mobile automation, invoke `running-mobile-simulators`.\n\nFollow [the direct-evidence rules](references\u002Fevidence.md#direct-evidence).\nRecord the command or interaction, target identity, environment, observation,\nand artifact location. Do not use a passing check, internal call, element\npresence, or agent report as proof of a different property.\n\n## Return a verdict\n\nReturn one verdict for each evidence case:\n\n- `confirmed`. Direct evidence reproduces the reported failure or shows that the\n  requested outcome is absent from the current target.\n- `resolved`. Direct evidence shows the requested outcome on the current target\n  and does not reproduce the reported failure.\n- `blocked`. The required target, environment, capability, or observation is\n  unavailable.\n- `decision-needed`. The feedback requires a product or preference decision\n  that evidence cannot answer.\n\nFor `confirmed`, pass the evidence case to patina-mode's matching playbook. Use\nBug fix for a defect and Feature or Refactoring for a requested change. After\nthe target changes, run `gather-evidence` again before preparing a response.\n\n## Report\n\nReturn the feedback source, verdict, target identity, direct observation, and\nartifact or command for each case. State exactly what blocks a `blocked` case.\nLeave every human-authored conversation open for the operator.\n\nWhen a case has local video evidence, add a compact `Linear handoff` directly\nafter that case:\n\n- Write a short Markdown note the operator can paste without rewriting. Name\n  the verdict, tested target, observation, and video filename. Include build,\n  deployment, and device identity when available. Write one note per evidence\n  case and name every video that proves it.\n- Before cleanup, copy any video from a simulator, lease, or temporary directory\n  that cleanup will remove to a path the current run will preserve. Leave the\n  copy on disk at the reported path.\n- Put one clickable file link per video immediately after its note. Render it as\n  `[filename.mp4](\u002Fabsolute\u002Fpath\u002Ffilename.mp4)`. Wrap a target containing spaces\n  in angle brackets. Keep the local link outside the paste-ready note because a\n  Linear reader cannot open the operator's local path.\n- If the host cannot render a clickable local file, return the exact absolute\n  path and state that the operator must locate it manually. Report only actions\n  that occurred; a link or path is not a copy, attachment, or upload.\n","# Gather evidence\n\nTreat human feedback as a claim or requested outcome to investigate. Do not edit\ncode, reply to the person, resolve their thread, or change their review state.\n\n## Define the evidence cases\n\nRead the complete feedback and its nearby context. Split independent claims\ninto separate evidence cases. Record each case using\n[the evidence fields](references\u002Fevidence.md#evidence-case):\n\n- the exact feedback source\n- the requested behavior or result\n- the expected and reported behavior\n- the exact check and required environment\n- the current target, pull request, commit, build, or deployment\n\nDo not translate a concrete observation into a proxy. Ask for missing context\nonly when no direct check can resolve it.\n\n## Inspect the current target\n\nResolve the current target before gathering evidence. For pull request\nfeedback, record the current head SHA and confirm that the local checkout or\ndeployed build matches it. A later push invalidates the evidence.\n\nGather direct evidence from the interface named by the feedback. Inspect the code\nand diff for source claims. Run the exact interaction for behavioral claims.\nUse the applicable driver for a UI, CLI, or runtime. Before changing a mobile\nsimulator or running mobile automation, invoke `running-mobile-simulators`.\n\nFollow [the direct-evidence rules](references\u002Fevidence.md#direct-evidence).\nRecord the command or interaction, target identity, environment, observation,\nand artifact location. Do not use a passing check, internal call, element\npresence, or agent report as proof of a different property.\n\n## Return a verdict\n\nReturn one verdict for each evidence case:\n\n- `confirmed`. Direct evidence reproduces the reported failure or shows that the\n  requested outcome is absent from the current target.\n- `resolved`. Direct evidence shows the requested outcome on the current target\n  and does not reproduce the reported failure.\n- `blocked`. The required target, environment, capability, or observation is\n  unavailable.\n- `decision-needed`. The feedback requires a product or preference decision\n  that evidence cannot answer.\n\nFor `confirmed`, pass the evidence case to patina-mode's matching playbook. Use\nBug fix for a defect and Feature or Refactoring for a requested change. After\nthe target changes, run `gather-evidence` again before preparing a response.\n\n## Report\n\nReturn the feedback source, verdict, target identity, direct observation, and\nartifact or command for each case. State exactly what blocks a `blocked` case.\nLeave every human-authored conversation open for the operator.\n\nWhen a case has local video evidence, add a compact `Linear handoff` directly\nafter that case:\n\n- Write a short Markdown note the operator can paste without rewriting. Name\n  the verdict, tested target, observation, and video filename. Include build,\n  deployment, and device identity when available. Write one note per evidence\n  case and name every video that proves it.\n- Before cleanup, copy any video from a simulator, lease, or temporary directory\n  that cleanup will remove to a path the current run will preserve. Leave the\n  copy on disk at the reported path.\n- Put one clickable file link per video immediately after its note. Render it as\n  `[filename.mp4](\u002Fabsolute\u002Fpath\u002Ffilename.mp4)`. Wrap a target containing spaces\n  in angle brackets. Keep the local link outside the paste-ready note because a\n  Linear reader cannot open the operator's local path.\n- If the host cannot render a clickable local file, return the exact absolute\n  path and state that the operator must locate it manually. Report only actions\n  that occurred; a link or path is not a copy, attachment, or upload.\n",{"name":5,"description":7},"main","e6ee720f466a8344a52abd87679191fadde3b63f","plugins\u002Fcode\u002Fskills\u002Fgather-evidence","https:\u002F\u002Fgithub.com\u002Fpatinaproject\u002Fskills","https:\u002F\u002Fgithub.com\u002Fpatinaproject","https:\u002F\u002Fwww.patinaproject.com","The best way to pick your next pair of boots or shoes.","2026-11-12 00:44:02",{"source":8,"skillName":5,"commands":49,"prompt":59,"zipAvailable":60},[50,53,56],{"tool":51,"command":52},"npx","npx skills add patinaproject\u002Fskills --skill gather-evidence",{"tool":54,"command":55},"bunx","bunx skills add patinaproject\u002Fskills --skill gather-evidence",{"tool":57,"command":58},"pnpm","pnpm dlx skills add patinaproject\u002Fskills --skill gather-evidence","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fpatinaproject\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fcode\u002Fskills\u002Fgather-evidence\u002FSKILL.md",true,[62],{"path":63,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":66,"sourceHtmlUrl":67},"references\u002Fevidence.md","REFERENCE","参考文档",1097,"https:\u002F\u002Fgithub.com\u002Fpatinaproject\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fcode\u002Fskills\u002Fgather-evidence\u002Freferences\u002Fevidence.md",[69,77,106,118,140,164],{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":76},"01M72KDQJR99954NE224VB3KZ2","code-review","Review the changes since a fixed point (commit, branch, tag, or merge-base) along five axes: Standards (does the code follow this repo's documented coding standards?), Spec (does the code match what the originating issue\u002Fspec asked for?), Evidence (does each claim in the pull request have evidence that shows it?), Bugs (does the changed code have logic errors, unhandled states, races, or regressions?), and Security (does the change open injection, auth, secret, input, or CI workflow holes?). Runs the reviews in parallel sub-agents, tags every finding Important, Nit, or Pre-existing, and reports them side by side with what blocks merge. Given an earlier reviewed head and its findings, it reviews only the newer commits, rechecks the earlier findings, and never repeats one. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to \"review since X\".","https:\u002F\u002Fgithub.com\u002Fpatinaproject\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fcode\u002Fskills\u002Fcode-review\u002FSKILL.md",[],[],"2026-11-10 22:39:42",{"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":93,"publishedAt":35},"01M71ESEDVHD9EXN6787XHP7HD","writing-for-pstack","Write or tighten an operator prompt for a patina-mode run. Use when the operator asks to write, revise, or review a prompt that will be passed to patina-mode.","https:\u002F\u002Fgithub.com\u002Fpatinaproject\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fwork\u002Fskills\u002Fwriting-for-pstack\u002FSKILL.md",[83,88],{"categoryNo":84,"categoryName":85,"taxonomyType":86,"taxonomyTypeDesc":87},"01JBSEEDCAT000000000000018","写作与文案","SCENARIO","使用场景",{"categoryNo":89,"categoryName":90,"taxonomyType":91,"taxonomyTypeDesc":92},"01JBSEEDCAT000000000000036","内容创作者","PROFESSION","适用职业",[94,95,96,97,98,99,100,101,102,31,103,104,34,105],"for","pstack","writing","writing for pstack","review","run","mode","write","operator","tighten","prompt","revise",{"skillNo":107,"name":108,"nameZh":6,"description":109,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":110,"categories":111,"keywords":114,"publishedAt":35},"01M71ESCJ0SSJFFENF8HYDKBTJ","writing-for-agents","Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.","https:\u002F\u002Fgithub.com\u002Fpatinaproject\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fwork\u002Fskills\u002Fwriting-for-agents\u002FSKILL.md",[112,113],{"categoryNo":84,"categoryName":85,"taxonomyType":86,"taxonomyTypeDesc":87},{"categoryNo":89,"categoryName":90,"taxonomyType":91,"taxonomyTypeDesc":92},[115,94,96,116,31,117,34],"writing for agents","editing","documents",{"skillNo":119,"name":120,"nameZh":6,"description":121,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":122,"categories":123,"keywords":124,"publishedAt":35},"01M71ESA1NN9WVMD2HA5Z1RRDY","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\u002Fpatinaproject\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fwork\u002Fskills\u002Fwizard\u002FSKILL.md",[],[120,125,126,127,128,129,34,130,131,132,26,133,31,134,135,136,94,137,138,139],"interactive","can","credentials","one","Bash","invoke","dashboard","generate","secrets","provisioning infrastructure","ci","up","setting","running","only",{"skillNo":141,"name":142,"nameZh":6,"description":143,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":144,"categories":145,"keywords":146,"publishedAt":35},"01M71ES8FAN567N3JEPG8W6AS1","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\u002Fpatinaproject\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fwork\u002Fskills\u002Fwayfinder\u002FSKILL.md",[],[142,147,148,149,150,151,152,153,154,155,156,157,158,159,160,161,162,126,163,128],"more","true","decision","session","time","chunk","as","shared","map","tickets","destination","at","tracker","plan","work","agent session","one at a time",{"skillNo":165,"name":166,"nameZh":6,"description":167,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":168,"categories":169,"keywords":170,"publishedAt":35},"01M71ES6PWJPKBW8R24YFH4PY6","wait-what","Stop. That last message did not land: re-pitch it.","https:\u002F\u002Fgithub.com\u002Fpatinaproject\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fwork\u002Fskills\u002Fwait-what\u002FSKILL.md",[],[171,172,173,174,175,176,177,178,148,179],"wait","wait what","stop","it","land","re","pitch","message","last"]