[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7E8HPCQJF7WPF6VZ5DC3XWZ":3,"skill-same:01M7E8HPCQJF7WPF6VZ5DC3XWZ":58},{"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":30,"commitSha":31,"skillDirectory":32,"forksCount":14,"repositoryHtmlUrl":33,"repositoryHomepageUrl":6,"ownerHtmlUrl":34,"ownerBlogUrl":35,"ownerDescription":36,"updatedAt":37,"install":38,"resources":51},"01M7E8HPCQJF7WPF6VZ5DC3XWZ","what",null,"Use when a user explicitly wants a five-line recap: session, branch, ticket, next options, narrowed to any named subject.","tony\u002Fskills","tony","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F26336?v=4","01M72E5RNJ7SQV8F9KBM5RKRMN","Tony Narlock","01M7E7MBN5C6YZ4JJJ5Y82KBJG",0,"MIT","https:\u002F\u002Fgithub.com\u002Ftony\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fsituate\u002Fskills\u002Fwhat\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: what\ndescription: \"Use when a user explicitly wants a five-line recap: session, branch, ticket, next options, narrowed to any named subject.\"\nallowed-tools: [\"Bash\", \"Read\", \"Grep\", \"Glob\"]\nargument-hint: \"[what you are confused about]\"\n---\n\n\n# What\n\nThe reader is disoriented. End that in five lines.\n\nRead `..\u002F..\u002Freferences\u002Fbrief.md` first — it defines the\nfive-line budget, what earns a line, the option lines, and the evidence\ntiers that keep this cheap enough to ask casually.\n\nUser arguments: $ARGUMENTS\n\n## Procedure\n\n### 1. Read what was actually asked\n\nEmpty `$ARGUMENTS` means the whole situation: what this session has been\ndoing, and where the repository stands.\n\nAn argument narrows it to that subject, and narrowing is the point —\n`\u002Fsituate:what the test failure` answers about the test failure and\nspends no lines on branch position.\n\n### 2. Answer from the session first\n\nWhen the confusion is about what just happened (a command that ran, a\ndecision taken, why the work moved), the answer is already in context\nand needs no tools.\n\nWhen the session's memory is thin, gather only the cheap evidence relevant\nto the question, per the brief reference. For a named file, inspect its\nstatus and diff; Git records what changed, not why someone left it\nuncommitted. Do not infer that motive.\n\nFor the whole situation or a branch-position question, gather:\n\n1. Position: run `python3 ..\u002F..\u002Fscripts\u002Fposition.py` for branch, trunk,\n   ahead\u002Fbehind, uncommitted work, and stashes. `..\u002F..\u002Fscripts\u002F` resolves\n   from this skill's directory: write the absolute path literally in the\n   command. A `dotfile_repo` or an\n   empty repository (`has_commits` false) gets one line saying so and no\n   file list; the script prints nothing else then.\n2. Commit subjects since the base:\n   `git log --no-merges --format='%h %s' \u003Ctrunk>..HEAD`.\n\nA null `trunk` or a failed command means that layer is unavailable; mention\nit only when the answer depends on that layer. Measuring from trunk is approximate on a\nbranch stacked over another branch, because the range carries the\nparent's commits; say so rather than re-resolving the base.\n\nGo beyond that only for the paid tier in the brief reference.\n\n### 3. Write the brief\n\nFive lines is a ceiling; a narrow question usually needs two. Rank lines\nas the brief reference sets out, then add numbered single-line options\nonly when there is a real fork; each option is a different action, never a\nrestatement of another. Stay read-only, per the contract in\n`..\u002F..\u002Freferences\u002Fsituation-sweep.md`, and write per\n`..\u002F..\u002Freferences\u002Fprose-rules.md`.\n\nBefore sending, hold each line to `..\u002F..\u002Freferences\u002Fbrief.md` (its\nBanned and Confidence sections), plus these:\n\n- One sentence per line, at most about 20 words.\n- A narrow question gets only the causal answer, with no branch or\n  trunk name inside an option (\"commit it\", not \"commit it on main\").\n- No absolute paths, and tool state (`gh` signed out) is never a line.\n- If the work has wandered from its purpose, offer `\u002Fsituate:refocus`\n  as an option; do not diagnose it here.\n\n## Output\n\nThe body, then the options. Nothing else: no title, no framing\nsentence, no offer to go deeper.\n\nReply in this shape, as plain text outside any code fence, without bullets,\nbold, or local paths:\n\n```text\n⚠ CI is red on PR #12: the type-check job fails on three files this branch added.\nfeat-brief-mode, 4 commits ahead of main, 2 files uncommitted.\nThis session rewrote the output contract and has not re-run the gates since.\nThe ticket asks for a terse mode; the terse mode works, the failing types do not.\n\n1. Fix the three type errors and push\n2. Show the failing job output\n3. Stash the uncommitted work and check whether the branch alone is green\n```\n","# What\n\nThe reader is disoriented. End that in five lines.\n\nRead `..\u002F..\u002Freferences\u002Fbrief.md` first — it defines the\nfive-line budget, what earns a line, the option lines, and the evidence\ntiers that keep this cheap enough to ask casually.\n\nUser arguments: $ARGUMENTS\n\n## Procedure\n\n### 1. Read what was actually asked\n\nEmpty `$ARGUMENTS` means the whole situation: what this session has been\ndoing, and where the repository stands.\n\nAn argument narrows it to that subject, and narrowing is the point —\n`\u002Fsituate:what the test failure` answers about the test failure and\nspends no lines on branch position.\n\n### 2. Answer from the session first\n\nWhen the confusion is about what just happened (a command that ran, a\ndecision taken, why the work moved), the answer is already in context\nand needs no tools.\n\nWhen the session's memory is thin, gather only the cheap evidence relevant\nto the question, per the brief reference. For a named file, inspect its\nstatus and diff; Git records what changed, not why someone left it\nuncommitted. Do not infer that motive.\n\nFor the whole situation or a branch-position question, gather:\n\n1. Position: run `python3 ..\u002F..\u002Fscripts\u002Fposition.py` for branch, trunk,\n   ahead\u002Fbehind, uncommitted work, and stashes. `..\u002F..\u002Fscripts\u002F` resolves\n   from this skill's directory: write the absolute path literally in the\n   command. A `dotfile_repo` or an\n   empty repository (`has_commits` false) gets one line saying so and no\n   file list; the script prints nothing else then.\n2. Commit subjects since the base:\n   `git log --no-merges --format='%h %s' \u003Ctrunk>..HEAD`.\n\nA null `trunk` or a failed command means that layer is unavailable; mention\nit only when the answer depends on that layer. Measuring from trunk is approximate on a\nbranch stacked over another branch, because the range carries the\nparent's commits; say so rather than re-resolving the base.\n\nGo beyond that only for the paid tier in the brief reference.\n\n### 3. Write the brief\n\nFive lines is a ceiling; a narrow question usually needs two. Rank lines\nas the brief reference sets out, then add numbered single-line options\nonly when there is a real fork; each option is a different action, never a\nrestatement of another. Stay read-only, per the contract in\n`..\u002F..\u002Freferences\u002Fsituation-sweep.md`, and write per\n`..\u002F..\u002Freferences\u002Fprose-rules.md`.\n\nBefore sending, hold each line to `..\u002F..\u002Freferences\u002Fbrief.md` (its\nBanned and Confidence sections), plus these:\n\n- One sentence per line, at most about 20 words.\n- A narrow question gets only the causal answer, with no branch or\n  trunk name inside an option (\"commit it\", not \"commit it on main\").\n- No absolute paths, and tool state (`gh` signed out) is never a line.\n- If the work has wandered from its purpose, offer `\u002Fsituate:refocus`\n  as an option; do not diagnose it here.\n\n## Output\n\nThe body, then the options. Nothing else: no title, no framing\nsentence, no offer to go deeper.\n\nReply in this shape, as plain text outside any code fence, without bullets,\nbold, or local paths:\n\n```text\n⚠ CI is red on PR #12: the type-check job fails on three files this branch added.\nfeat-brief-mode, 4 commits ahead of main, 2 files uncommitted.\nThis session rewrote the output contract and has not re-run the gates since.\nThe ticket asks for a terse mode; the terse mode works, the failing types do not.\n\n1. Fix the three type errors and push\n2. Show the failing job output\n3. Stash the uncommitted work and check whether the branch alone is green\n```\n",{"name":5,"description":7,"allowed-tools":24,"argument-hint":29},[25,26,27,28],"Bash","Read","Grep","Glob","[what you are confused about]","main","5fbeb3b47beedea13813be7b7023f736a8d97a65","plugins\u002Fsituate\u002Fskills\u002Fwhat","https:\u002F\u002Fgithub.com\u002Ftony\u002Fskills","https:\u002F\u002Fgithub.com\u002Ftony","https:\u002F\u002Ftony.sh","lighthouse keeper","2026-11-08 17:57:34",{"source":8,"skillName":5,"commands":39,"prompt":49,"zipAvailable":50},[40,43,46],{"tool":41,"command":42},"npx","npx skills add tony\u002Fskills --skill what",{"tool":44,"command":45},"bunx","bunx skills add tony\u002Fskills --skill what",{"tool":47,"command":48},"pnpm","pnpm dlx skills add tony\u002Fskills --skill what","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Ftony\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fsituate\u002Fskills\u002Fwhat\u002FSKILL.md",true,[52],{"path":53,"resourceType":54,"resourceTypeDesc":55,"sizeBytes":56,"sourceHtmlUrl":57},"agents\u002Fopenai.yaml","REFERENCE","参考文档",248,"https:\u002F\u002Fgithub.com\u002Ftony\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fsituate\u002Fskills\u002Fwhat\u002Fagents\u002Fopenai.yaml",[59,66,73,80,87,94],{"skillNo":60,"name":61,"nameZh":6,"description":62,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":65,"publishedAt":19},"01M7E8NCSHXV2JPW4J61R0TQS7","serene-bliss","Use when asked to make a CLI --help, docs page, error message, or tooling UX more serene or calmer for developer experience; returns text, no edits.","https:\u002F\u002Fgithub.com\u002Ftony\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fweave\u002Fskills\u002Fserene-bliss\u002FSKILL.md",[],[],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":19},"01M7E8N87MAVJD8RRQKQB1ZPS6","review","Weave code review: run independent adversarial reviews in parallel, then synthesize findings","https:\u002F\u002Fgithub.com\u002Ftony\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fweave\u002Fskills\u002Freview\u002FSKILL.md",[],[],{"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},"01M7E8N402XG4ZBFNACQ413163","refine","Use when asked to refine a draft, iterate on code until cleaner, or polish a README through repeated critique and improvement.","https:\u002F\u002Fgithub.com\u002Ftony\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fweave\u002Fskills\u002Frefine\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},"01M7E8N01KB86A7136P00GVKJW","prompt","Weave prompt: compare independent adversarial implementations, then adopt the single best one","https:\u002F\u002Fgithub.com\u002Ftony\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fweave\u002Fskills\u002Fprompt\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},"01M7E8MW7YJW2PCMDW3G9RTGNK","plan","Weave planning: compare independent adversarial plans, then synthesize the best one","https:\u002F\u002Fgithub.com\u002Ftony\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fweave\u002Fskills\u002Fplan\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},"01M7E8MSBYXNCV4ZYWDS4PFJXK","fix-review","Fix weave review findings: validate, add test coverage, fix, and commit each as atomic changes","https:\u002F\u002Fgithub.com\u002Ftony\u002Fskills\u002Fblob\u002Fmain\u002Fplugins\u002Fweave\u002Fskills\u002Ffix-review\u002FSKILL.md",[],[]]