[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7E7NQFJAMTPB82SV78429B5":3,"skill-same:01M7E7NQFJAMTPB82SV78429B5":89},{"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":36,"commitSha":37,"skillDirectory":38,"forksCount":14,"repositoryHtmlUrl":39,"repositoryHomepageUrl":6,"ownerHtmlUrl":40,"ownerBlogUrl":41,"ownerDescription":42,"updatedAt":43,"install":44,"resources":56},"01M7E7NQFJAMTPB82SV78429B5","business-research",null,"Use when collecting evidence for the business value of an AI skill or workflow into a provenance-tagged research package.","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\u002F.agents\u002Fskills\u002Fbusiness-research\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: business-research\ndescription: >-\n  Use when collecting evidence for the business value of an AI skill or\n  workflow into a provenance-tagged research package.\ndisable-model-invocation: true\nallowed-tools: [\"Bash\", \"Read\", \"Write\", \"Grep\", \"AskUserQuestion\", \"EnterPlanMode\", \"ExitPlanMode\"]\nmetadata:\n  argument-hint: \"[skill or workflow to measure] [date range, e.g. 2026-04-01..2026-06-30]\"\n  source: \"plugins\u002Fbusiness\u002Fskills\u002Fresearch\u002FSKILL.md\"\n---\n\n# Business Research\n\nCollect the data behind a business-value claim for an AI skill or\nagentic workflow (productivity, time saved, quality, capacity,\ndelivery outcomes) into the interim run package the report skills\nrender from.\n\nRead these first; they bind every step:\n\n- `references\u002Finterim-format.md`: the run package layout, where\n  runs live, and the value units (never money).\n- `references\u002Fprovenance.md`: the four tags and the\n  anti-inflation rules.\n- `references\u002Finstruments.md`: per-instrument probes,\n  collection discipline, the pull-request query, and the targets to\n  collect.\n\nLoad `references\u002Fmeasurement.md` only for the counterfactual\nladder and the statistics discipline, which owns the n\u003C5 range rule.\nIntervals come from `references\u002Fbusiness.py stats` (absolute path).\n\nUser arguments: $ARGUMENTS\n\n## Procedure\n\n### 1. Scope and orchestration plan\n\nEnter plan mode before the first edit. In Claude Code call\n`EnterPlanMode`; in Cursor, Codex, or Gemini use `\u002Fplan` or\n`Shift+Tab`. Where plan mode is unavailable, present the plan as text.\n\nPresent the plan (shape below) and ask where to write the run,\ndefaulting per `interim-format.md` § Where runs live. Write nothing,\nincluding `index.md`, until the user approves. Exit plan mode, then\nopen the run at the approved root with `business.py init`, per\n`interim-format.md` § Where runs live. Pass `--date` when the request\nnames a dated run path; if `init` refuses, follow the same section.\n\nNon-interactive (no question tool, headless): print the plan with the\ndefault root and stop. A request that itself names the root approves\nthe plan; record the root in the run README and continue.\n\nReply in this shape (reply form per `interim-format.md` § Finished\nrun), with no greeting, naming roots as the user would type them:\n\n```text\nPlan: review-skill, window 2026-04-01..2026-06-30. Nothing is written yet.\n\n## Measure\n\n- Cycle time and first-review latency per PR; rework signals.\n- Adoption and per-task timing only from exports you provide.\n\n## Instruments\n\n- git and gh to probe; trackers and timing logs only from exports you provide.\n\n## Output\n\n- 2026-07-14\u002Fbusiness\u002Freview-skill under ~\u002FDocuments, the default root.\n- Questions: confirm the root and the repo paths.\n```\n\nThe `- Questions:` bullet is the last line: no closing paragraph that\nrestates it. One fact per bullet. Report what you will probe, not\nwhat the current directory happens to hold or what you have not yet\nprobed.\n\n### 2. Instrument discovery\n\nProbe each instrument per `instruments.md`; never assume one exists.\nRecord every instrument as available or unavailable in the run\nREADME (for `gh auth status`, only that it succeeded). Data an unavailable instrument would have provided is\n`unknown`, never fabricated and never silently skipped, unless the\nuser supplies an assumption, which is registered as ESTIMATED with\nrationale and owner (`provenance.md` gives its fields).\n\n### 3. Collect\n\nFor each available instrument, run pinned-window queries per\n`instruments.md` and snapshot raw output into `raw\u002F` before deriving\nanything. Collect the targets listed there; record the rest as\nunknown. Derive pull-request tables with `business.py collect-prs`,\npiping the query into it with `--output` so reviewer and author logins\nnever reach `raw\u002F`, rather than rewriting the query or the filter. Write\nevery `sources.md` entry with `business.py source \u003Crun> \u003Centry> \u003Cfile>\n--query \u003Ccommand> --tool-version \u003Cversion>` (absolute path) right after the\ncommand produces `\u003Cfile>`: the script writes the output path, the clock\ntime, and the sha256, so none is typed by hand. Record every `collect-prs`\nwarning, including \"rows lack\" ones, in that entry and in the README.\n\n### 4. Write the package\n\nFill the package `init` started, per `interim-format.md`: run README,\nsource manifest with verbatim queries, assumptions register, raw\nsnapshots, per-topic measurements, and `findings.md`. Tag every figure\nper `provenance.md`; list every unknown with what data would resolve it.\nList every organization, repository, team, and workflow name the run\ntouched on the README `Names:` line, and every individual on the\n`People:` line (never on both); the scans depend on both.\nCompute medians, quartiles, and intervals with `business.py stats`\n(`--csv \u003Cfile> --column \u003Ca-b>` for a CSV column); copy its `n`, `rows`,\nand `dropped_blank` beside each statistic. Give each MEASURED\nfigure computed from a `raw\u002F` CSV a `check:` line. Run\n`business.py gate \u003Crun>` and fix every problem before reporting.\nWrite prose per `references\u002Fprose-rules.md`.\n\n## Output\n\nHero success form: `✓ Run written: \u003Cdate>\u002Fbusiness\u002F\u003Cworkflow>, window\n\u003Cstart>..\u003Cend>`; a stopped run follows `interim-format.md` §\nRendering a report. Then exactly these sections:\n\n1. `## Scope`: what was measured and the pinned window.\n2. `## Instruments`: available vs unavailable, and what each\n   unavailable one leaves unknown.\n3. `## Collected`: per instrument, what the data shows and what landed\n   in `raw\u002F` and `measurements\u002F`; one fact per bullet, one sentence per\n   bullet, with no clause defending a choice or restating the hero.\n4. `## Package`: the run location, the count of registered assumptions\n   (0 is valid; a measured count is not an assumption), and the count\n   of open unknowns; the unknowns themselves stay in\n   `findings.md`.\n\nEnd with an `ask-user-choice` panel: generate a report (ask which\ntier), collect more, or stop.\nPanel rules as in `interim-format.md` § Finished run.\n\nReply in this shape:\n\n```text\n✓ Run written: 2026-07-14\u002Fbusiness\u002Freview-skill, window 2026-04-01..2026-06-30\n\n## Scope\n\n- Review latency and rework rate for the review skill, 41 PRs.\n\n## Instruments\n\n- Available: git history, gh pull-request data.\n- Unavailable: timing logs; per-use verification time stays unknown.\n\n## Collected\n\n- raw\u002F holds 2 snapshots; measurements\u002F holds latency and rework.\n\n## Package\n\n- Run at 2026-07-14\u002Fbusiness\u002Freview-skill, 3 assumptions, 1 open unknown.\n\nNext, you can:\n- Generate a report (leadership, org-wide, internal or public case study).\n- Collect more data.\n- Stop here.\n```\n\nThe last list is the non-interactive form; with a question tool it is\nthe panel instead.\n\n\n## Portability notes\n\n- `ask-user-choice` — present the listed options and wait for the user to pick one. Hosts with a structured multiple-choice tool (Claude Code's `AskUserQuestion`) should use it; otherwise print a numbered list and wait for a numbered reply. Never proceed on an assumed answer.\n- `$ARGUMENTS` — the text the user passed when invoking this skill. If your host does not substitute it, read it as the user's request in the current turn, and ask when there is none.\n- Bundled files — every relative path in this skill points at a file shipped inside this skill directory. Read them from here, not from the host's plugin tree.\n","# Business Research\n\nCollect the data behind a business-value claim for an AI skill or\nagentic workflow (productivity, time saved, quality, capacity,\ndelivery outcomes) into the interim run package the report skills\nrender from.\n\nRead these first; they bind every step:\n\n- `references\u002Finterim-format.md`: the run package layout, where\n  runs live, and the value units (never money).\n- `references\u002Fprovenance.md`: the four tags and the\n  anti-inflation rules.\n- `references\u002Finstruments.md`: per-instrument probes,\n  collection discipline, the pull-request query, and the targets to\n  collect.\n\nLoad `references\u002Fmeasurement.md` only for the counterfactual\nladder and the statistics discipline, which owns the n\u003C5 range rule.\nIntervals come from `references\u002Fbusiness.py stats` (absolute path).\n\nUser arguments: $ARGUMENTS\n\n## Procedure\n\n### 1. Scope and orchestration plan\n\nEnter plan mode before the first edit. In Claude Code call\n`EnterPlanMode`; in Cursor, Codex, or Gemini use `\u002Fplan` or\n`Shift+Tab`. Where plan mode is unavailable, present the plan as text.\n\nPresent the plan (shape below) and ask where to write the run,\ndefaulting per `interim-format.md` § Where runs live. Write nothing,\nincluding `index.md`, until the user approves. Exit plan mode, then\nopen the run at the approved root with `business.py init`, per\n`interim-format.md` § Where runs live. Pass `--date` when the request\nnames a dated run path; if `init` refuses, follow the same section.\n\nNon-interactive (no question tool, headless): print the plan with the\ndefault root and stop. A request that itself names the root approves\nthe plan; record the root in the run README and continue.\n\nReply in this shape (reply form per `interim-format.md` § Finished\nrun), with no greeting, naming roots as the user would type them:\n\n```text\nPlan: review-skill, window 2026-04-01..2026-06-30. Nothing is written yet.\n\n## Measure\n\n- Cycle time and first-review latency per PR; rework signals.\n- Adoption and per-task timing only from exports you provide.\n\n## Instruments\n\n- git and gh to probe; trackers and timing logs only from exports you provide.\n\n## Output\n\n- 2026-07-14\u002Fbusiness\u002Freview-skill under ~\u002FDocuments, the default root.\n- Questions: confirm the root and the repo paths.\n```\n\nThe `- Questions:` bullet is the last line: no closing paragraph that\nrestates it. One fact per bullet. Report what you will probe, not\nwhat the current directory happens to hold or what you have not yet\nprobed.\n\n### 2. Instrument discovery\n\nProbe each instrument per `instruments.md`; never assume one exists.\nRecord every instrument as available or unavailable in the run\nREADME (for `gh auth status`, only that it succeeded). Data an unavailable instrument would have provided is\n`unknown`, never fabricated and never silently skipped, unless the\nuser supplies an assumption, which is registered as ESTIMATED with\nrationale and owner (`provenance.md` gives its fields).\n\n### 3. Collect\n\nFor each available instrument, run pinned-window queries per\n`instruments.md` and snapshot raw output into `raw\u002F` before deriving\nanything. Collect the targets listed there; record the rest as\nunknown. Derive pull-request tables with `business.py collect-prs`,\npiping the query into it with `--output` so reviewer and author logins\nnever reach `raw\u002F`, rather than rewriting the query or the filter. Write\nevery `sources.md` entry with `business.py source \u003Crun> \u003Centry> \u003Cfile>\n--query \u003Ccommand> --tool-version \u003Cversion>` (absolute path) right after the\ncommand produces `\u003Cfile>`: the script writes the output path, the clock\ntime, and the sha256, so none is typed by hand. Record every `collect-prs`\nwarning, including \"rows lack\" ones, in that entry and in the README.\n\n### 4. Write the package\n\nFill the package `init` started, per `interim-format.md`: run README,\nsource manifest with verbatim queries, assumptions register, raw\nsnapshots, per-topic measurements, and `findings.md`. Tag every figure\nper `provenance.md`; list every unknown with what data would resolve it.\nList every organization, repository, team, and workflow name the run\ntouched on the README `Names:` line, and every individual on the\n`People:` line (never on both); the scans depend on both.\nCompute medians, quartiles, and intervals with `business.py stats`\n(`--csv \u003Cfile> --column \u003Ca-b>` for a CSV column); copy its `n`, `rows`,\nand `dropped_blank` beside each statistic. Give each MEASURED\nfigure computed from a `raw\u002F` CSV a `check:` line. Run\n`business.py gate \u003Crun>` and fix every problem before reporting.\nWrite prose per `references\u002Fprose-rules.md`.\n\n## Output\n\nHero success form: `✓ Run written: \u003Cdate>\u002Fbusiness\u002F\u003Cworkflow>, window\n\u003Cstart>..\u003Cend>`; a stopped run follows `interim-format.md` §\nRendering a report. Then exactly these sections:\n\n1. `## Scope`: what was measured and the pinned window.\n2. `## Instruments`: available vs unavailable, and what each\n   unavailable one leaves unknown.\n3. `## Collected`: per instrument, what the data shows and what landed\n   in `raw\u002F` and `measurements\u002F`; one fact per bullet, one sentence per\n   bullet, with no clause defending a choice or restating the hero.\n4. `## Package`: the run location, the count of registered assumptions\n   (0 is valid; a measured count is not an assumption), and the count\n   of open unknowns; the unknowns themselves stay in\n   `findings.md`.\n\nEnd with an `ask-user-choice` panel: generate a report (ask which\ntier), collect more, or stop.\nPanel rules as in `interim-format.md` § Finished run.\n\nReply in this shape:\n\n```text\n✓ Run written: 2026-07-14\u002Fbusiness\u002Freview-skill, window 2026-04-01..2026-06-30\n\n## Scope\n\n- Review latency and rework rate for the review skill, 41 PRs.\n\n## Instruments\n\n- Available: git history, gh pull-request data.\n- Unavailable: timing logs; per-use verification time stays unknown.\n\n## Collected\n\n- raw\u002F holds 2 snapshots; measurements\u002F holds latency and rework.\n\n## Package\n\n- Run at 2026-07-14\u002Fbusiness\u002Freview-skill, 3 assumptions, 1 open unknown.\n\nNext, you can:\n- Generate a report (leadership, org-wide, internal or public case study).\n- Collect more data.\n- Stop here.\n```\n\nThe last list is the non-interactive form; with a question tool it is\nthe panel instead.\n\n\n## Portability notes\n\n- `ask-user-choice` — present the listed options and wait for the user to pick one. Hosts with a structured multiple-choice tool (Claude Code's `AskUserQuestion`) should use it; otherwise print a numbered list and wait for a numbered reply. Never proceed on an assumed answer.\n- `$ARGUMENTS` — the text the user passed when invoking this skill. If your host does not substitute it, read it as the user's request in the current turn, and ask when there is none.\n- Bundled files — every relative path in this skill points at a file shipped inside this skill directory. Read them from here, not from the host's plugin tree.\n",{"name":5,"metadata":24,"description":7,"allowed-tools":27,"disable-model-invocation":35},{"source":25,"argument-hint":26},"plugins\u002Fbusiness\u002Fskills\u002Fresearch\u002FSKILL.md","[skill or workflow to measure] [date range, e.g. 2026-04-01..2026-06-30]",[28,29,30,31,32,33,34],"Bash","Read","Write","Grep","AskUserQuestion","EnterPlanMode","ExitPlanMode",true,"main","5fbeb3b47beedea13813be7b7023f736a8d97a65",".agents\u002Fskills\u002Fbusiness-research","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":45,"prompt":55,"zipAvailable":35},[46,49,52],{"tool":47,"command":48},"npx","npx skills add tony\u002Fskills --skill business-research",{"tool":50,"command":51},"bunx","bunx skills add tony\u002Fskills --skill business-research",{"tool":53,"command":54},"pnpm","pnpm dlx skills add tony\u002Fskills --skill business-research","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Ftony\u002Fskills\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fbusiness-research\u002FSKILL.md",[57,63,69,73,77,81,85],{"path":58,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":61,"sourceHtmlUrl":62},"agents\u002Fopenai.yaml","REFERENCE","参考文档",292,"https:\u002F\u002Fgithub.com\u002Ftony\u002Fskills\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fbusiness-research\u002Fagents\u002Fopenai.yaml",{"path":64,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":67,"sourceHtmlUrl":68},"references\u002Fbusiness.py","SCRIPT","脚本",80988,"https:\u002F\u002Fgithub.com\u002Ftony\u002Fskills\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fbusiness-research\u002Freferences\u002Fbusiness.py",{"path":70,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":71,"sourceHtmlUrl":72},"references\u002Finstruments.md",8507,"https:\u002F\u002Fgithub.com\u002Ftony\u002Fskills\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fbusiness-research\u002Freferences\u002Finstruments.md",{"path":74,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":75,"sourceHtmlUrl":76},"references\u002Finterim-format.md",14514,"https:\u002F\u002Fgithub.com\u002Ftony\u002Fskills\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fbusiness-research\u002Freferences\u002Finterim-format.md",{"path":78,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":79,"sourceHtmlUrl":80},"references\u002Fmeasurement.md",7028,"https:\u002F\u002Fgithub.com\u002Ftony\u002Fskills\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fbusiness-research\u002Freferences\u002Fmeasurement.md",{"path":82,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":83,"sourceHtmlUrl":84},"references\u002Fprose-rules.md",4644,"https:\u002F\u002Fgithub.com\u002Ftony\u002Fskills\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fbusiness-research\u002Freferences\u002Fprose-rules.md",{"path":86,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":87,"sourceHtmlUrl":88},"references\u002Fprovenance.md",4425,"https:\u002F\u002Fgithub.com\u002Ftony\u002Fskills\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fbusiness-research\u002Freferences\u002Fprovenance.md",[90,97,104,111,118,125],{"skillNo":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"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":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":103,"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":105,"name":106,"nameZh":6,"description":107,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":108,"categories":109,"keywords":110,"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":112,"name":113,"nameZh":6,"description":114,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":115,"categories":116,"keywords":117,"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":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":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":126,"name":127,"nameZh":6,"description":128,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":129,"categories":130,"keywords":131,"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",[],[]]