[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7348AX1DWWGKY7403N4Z5S2":3,"skill-same:01M7348AX1DWWGKY7403N4Z5S2":73},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":23,"commitSha":24,"skillDirectory":25,"forksCount":26,"repositoryHtmlUrl":27,"repositoryHomepageUrl":6,"ownerHtmlUrl":28,"ownerBlogUrl":29,"ownerDescription":30,"updatedAt":31,"install":32,"resources":45},"01M7348AX1DWWGKY7403N4Z5S2","crawl",null,"Crawl a site with Screaming Frog and turn the output into findings a repo can act on. Use for SEO crawls and site audits, redirect or structured-data checks, rich-result eligibility questions, or any request that starts from crawl output.","notambourine\u002Fagent-plugins","notambourine","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F275093837?v=4","01M73473A77QWEA6JAW70BW4EV","01M73473AYDJYB0N74RR3B8YJS",2,"MIT","https:\u002F\u002Fgithub.com\u002Fnotambourine\u002Fagent-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fnt-seo-spider\u002Fskills\u002Fcrawl\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: crawl\ndescription: Crawl a site with Screaming Frog and turn the output into findings a repo can act on. Use for SEO crawls and site audits, redirect or structured-data checks, rich-result eligibility questions, or any request that starts from crawl output.\n---\n\n# SEO crawls with Screaming Frog\n\nProduce a list of findings a developer in this repo can fix. Each finding states how much of the\nsite the crawl covered, who owns the defect, and the source file that emits it.\n\n## Read the site supplement\n\nRead `.claude\u002Frefs\u002Fnt-seo-spider.md` first when the repo has one. It holds the domain, sitemap URLs,\nthe paths this repo serves, where SEO source lives, and site rules. Where it and this skill\ndisagree, follow the supplement.\n\nWithout it, settle two things before any finding: how much of the site the crawl reached, and which\nfailures come from a platform this repo doesn't ship.\n\n## Pick the lightest tool\n\n- For fewer than about 50 URLs, skip Screaming Frog. A curl loop returns status, redirect targets,\n  headers, and canonicals in less time than the app takes to start.\n- For a question about an earlier crawl (\"what did the last crawl say\"), load the saved crawl with\n  `sf_list_crawls` and `sf_load_crawl`. Say that you are doing so, unless the user wants fresh data.\n\n## Keep PageSpeed off\n\nLocal PageSpeed runs Lighthouse in headless Chrome for every URL, about 3 seconds each, and holds\nevery export until its queue drains. One redirect crawl queued 1,046 URLs and took most of an hour\nto answer a one-minute question. Never pass `--use-pagespeed`. Answer performance questions with\nthe chrome-devtools MCP on specific pages.\n\nBefore launching, grep `~\u002F.ScreamingFrogSEOSpider\u002Fspider.config` for `PSI.auto_connect`. When it is\n`true`, every run queues Lighthouse regardless of flags, and no `.seospiderconfig` overrides it. In\nthat case stop, and ask the user to disconnect PageSpeed under Configuration -> API Access and\nuntick connect-on-start.\n\n## Size the crawl to the task\n\nWith PageSpeed off, rendering mode decides the cost. Text Only is the default (`mCrawlerMode=STANDARD` in\nthe log). `RENDER` drives headless Chromium per page. `mCrawlJavaScript=true` only fetches JS files\nand costs nothing.\n\n| Task | Seed | Mode | Cost |\n| --- | --- | --- | --- |\n| Redirects, 404s, status codes, canonicals, titles, meta, robots, sitemap hygiene | `--crawl-sitemap` or a `--crawl` spider | `links.seospiderconfig` | ~1 min |\n| Structured data, rich-result eligibility | `--crawl-sitemap` of the section | `schema.seospiderconfig` | ~1 min |\n| Scope audit, client-rendered listings, \"is it in the hydrated DOM\" | `--crawl` | `render.seospiderconfig` | ~5-10 min |\n\nBefore a render run of more than 200 URLs, state the URL count and the estimated time and wait\nfor a go-ahead.\n\nAbout ten seconds in, grep `run.log` for `mCrawlerMode=` and `Connected to PageSpeed`. Kill the run\nif the mode is heavier than the task or PageSpeed connected.\n\nThe run is done when the CSVs exist in the output folder. Exports are written only at the end, so\na killed run leaves none.\n\n### Run headless\n\nThe CLI runs beside an open GUI, and only the CLI seeds from a sitemap. The launcher is\n`\u002FApplications\u002FScreaming Frog SEO Spider.app\u002FContents\u002FMacOS\u002FScreamingFrogSEOSpiderLauncher` on macOS\nand `ScreamingFrogSEOSpiderCli` in the install directory on Windows and Linux.\n\n```sh\nOUT=~\u002Fscreaming-frog\u002F\u003Ctask>-\u003Cyyyymmdd>\nmkdir -p \"$OUT\"\n\"$SF_LAUNCHER\" --headless [--config \u003Cmode>.seospiderconfig] \\\n  --crawl-sitemap $SITE\u002F\u003Csection-sitemap>.xml \\\n  --project-name \u003Csite> --task-name \u003Ctask>-\u003Cyyyymmdd> --save-crawl \\\n  --output-folder \"$OUT\" --overwrite --export-format csv \\\n  --export-tabs \"Internal:All,Response Codes:All\" --save-report \"Crawl Overview\" \\\n  > \"$OUT\u002Frun.log\" 2>&1\n```\n\nSaved crawls land in DB storage. Open them from File -> Crawls..., not \"Open Recent\".\n\n### Pass a mode config\n\n`sf_crawl` takes only url, name, project, and config_path. With no config, a run uses the user's\nsaved default, whose settings are unknown. Never edit that default. Always pass a mode config, via\n`--config` or `config_path`, from `${CLAUDE_PLUGIN_ROOT}\u002Fskills\u002Fcrawl\u002Fconfigs\u002F` or the directory the\nsite supplement names.\n\nA `.seospiderconfig` is Java-serialized binary. Never write or patch one by hand. To read one, run it\nheadless against `$SITE\u002Frobots.txt` and grep the config dump in the log.\n\nWhen a mode config is missing, ask the user to build it per\n[references\u002Fconfigs.md](references\u002Fconfigs.md).\n\nTwo runs on different configs measure different things, so never compare their numbers.\n\n## Audit scope before quoting a number\n\nA crawl reports only on the pages it reached and gives no sign of the ones it missed, so every\ncount covers just the pages this config could see. Before quoting a figure from a spidered crawl,\nrun the checks in [references\u002Fscope-audit.md](references\u002Fscope-audit.md). A sitemap-seeded run\nskips them, because it visits every URL in the sitemap.\n\n## Three data shapes\n\n| Tool | What it is | Use it when |\n| --- | --- | --- |\n| `sf_generate_report` | 61 pre-baked cross-cutting analyses | The question spans URLs: chains, reciprocity, rich-result eligibility, totals |\n| `sf_export_seo_element_urls` | The UI's tab and filter grid | \"Give me the URLs where X\", where X is a filter in a tab |\n| `sf_generate_bulk_export` | Edges and raw content | \"What links to the broken thing\", or \"dump the rendered HTML\" |\n\n## Work in this order\n\n0. Scope audit. Until it passes, treat every count as a lower bound.\n1. `Crawl Overview`: inventory, content types, indexable vs not.\n2. `Issues Overview`: the triage table, with priority, URL count, and How-To-Fix per row. It names\n   the next report worth running.\n3. Drill into whatever Issues Overview ranks High.\n4. Trace each candidate to a source file before it becomes a finding.\n\nFor the report or export that answers a specific question, read\n[references\u002Fcalls.md](references\u002Fcalls.md).\n\n## Traps\n\n- The MCP needs the desktop app open and idle. Otherwise every tool throws\n  `IllegalStateException: Tool cannot be called currently`. That error reports the app's state and\n  says nothing about your arguments. The headless CLI runs beside the GUI.\n- Load a crawl before any report: `sf_list_crawls`, then `sf_load_crawl \u003Cid>`.\n- Output dirs aren't created for you. `file_path` is relative to `sf_list_allowed_base_directory`.\n  Run `sf_create_directory` first or get `NoSuchFileException`.\n- During a crawl only `sf_crawl_progress` responds. Crawl, poll, then export.\n- Pass `export_type: \"CSV\"`. The default NDJSON arrives as one giant line.\n- `sf_list_available_bulk_exports` overflows the token limit. Call it once and keep the list.\n- Always write to `file_path`, then read the part you need with shell. Inline content fills the\n  context window.\n\n## Report\n\nOpen every set of counts with coverage (\"238 of 727 sitemap URLs, 33%\") and call the counts lower\nbounds. For a sitemap-seeded run, \"117 of 117\" is enough.\n\nSort findings into three buckets, in order:\n\n1. Confirmed ours. This repo serves the URL, and you name the file and line that emits the defect.\n   Only these go in a PR.\n2. Real, untraced. Name the system not yet ruled out and the check that settles it.\n3. Untriaged rows, straight from `Issues Overview`, labelled uninvestigated.\n","# SEO crawls with Screaming Frog\n\nProduce a list of findings a developer in this repo can fix. Each finding states how much of the\nsite the crawl covered, who owns the defect, and the source file that emits it.\n\n## Read the site supplement\n\nRead `.claude\u002Frefs\u002Fnt-seo-spider.md` first when the repo has one. It holds the domain, sitemap URLs,\nthe paths this repo serves, where SEO source lives, and site rules. Where it and this skill\ndisagree, follow the supplement.\n\nWithout it, settle two things before any finding: how much of the site the crawl reached, and which\nfailures come from a platform this repo doesn't ship.\n\n## Pick the lightest tool\n\n- For fewer than about 50 URLs, skip Screaming Frog. A curl loop returns status, redirect targets,\n  headers, and canonicals in less time than the app takes to start.\n- For a question about an earlier crawl (\"what did the last crawl say\"), load the saved crawl with\n  `sf_list_crawls` and `sf_load_crawl`. Say that you are doing so, unless the user wants fresh data.\n\n## Keep PageSpeed off\n\nLocal PageSpeed runs Lighthouse in headless Chrome for every URL, about 3 seconds each, and holds\nevery export until its queue drains. One redirect crawl queued 1,046 URLs and took most of an hour\nto answer a one-minute question. Never pass `--use-pagespeed`. Answer performance questions with\nthe chrome-devtools MCP on specific pages.\n\nBefore launching, grep `~\u002F.ScreamingFrogSEOSpider\u002Fspider.config` for `PSI.auto_connect`. When it is\n`true`, every run queues Lighthouse regardless of flags, and no `.seospiderconfig` overrides it. In\nthat case stop, and ask the user to disconnect PageSpeed under Configuration -> API Access and\nuntick connect-on-start.\n\n## Size the crawl to the task\n\nWith PageSpeed off, rendering mode decides the cost. Text Only is the default (`mCrawlerMode=STANDARD` in\nthe log). `RENDER` drives headless Chromium per page. `mCrawlJavaScript=true` only fetches JS files\nand costs nothing.\n\n| Task | Seed | Mode | Cost |\n| --- | --- | --- | --- |\n| Redirects, 404s, status codes, canonicals, titles, meta, robots, sitemap hygiene | `--crawl-sitemap` or a `--crawl` spider | `links.seospiderconfig` | ~1 min |\n| Structured data, rich-result eligibility | `--crawl-sitemap` of the section | `schema.seospiderconfig` | ~1 min |\n| Scope audit, client-rendered listings, \"is it in the hydrated DOM\" | `--crawl` | `render.seospiderconfig` | ~5-10 min |\n\nBefore a render run of more than 200 URLs, state the URL count and the estimated time and wait\nfor a go-ahead.\n\nAbout ten seconds in, grep `run.log` for `mCrawlerMode=` and `Connected to PageSpeed`. Kill the run\nif the mode is heavier than the task or PageSpeed connected.\n\nThe run is done when the CSVs exist in the output folder. Exports are written only at the end, so\na killed run leaves none.\n\n### Run headless\n\nThe CLI runs beside an open GUI, and only the CLI seeds from a sitemap. The launcher is\n`\u002FApplications\u002FScreaming Frog SEO Spider.app\u002FContents\u002FMacOS\u002FScreamingFrogSEOSpiderLauncher` on macOS\nand `ScreamingFrogSEOSpiderCli` in the install directory on Windows and Linux.\n\n```sh\nOUT=~\u002Fscreaming-frog\u002F\u003Ctask>-\u003Cyyyymmdd>\nmkdir -p \"$OUT\"\n\"$SF_LAUNCHER\" --headless [--config \u003Cmode>.seospiderconfig] \\\n  --crawl-sitemap $SITE\u002F\u003Csection-sitemap>.xml \\\n  --project-name \u003Csite> --task-name \u003Ctask>-\u003Cyyyymmdd> --save-crawl \\\n  --output-folder \"$OUT\" --overwrite --export-format csv \\\n  --export-tabs \"Internal:All,Response Codes:All\" --save-report \"Crawl Overview\" \\\n  > \"$OUT\u002Frun.log\" 2>&1\n```\n\nSaved crawls land in DB storage. Open them from File -> Crawls..., not \"Open Recent\".\n\n### Pass a mode config\n\n`sf_crawl` takes only url, name, project, and config_path. With no config, a run uses the user's\nsaved default, whose settings are unknown. Never edit that default. Always pass a mode config, via\n`--config` or `config_path`, from `${CLAUDE_PLUGIN_ROOT}\u002Fskills\u002Fcrawl\u002Fconfigs\u002F` or the directory the\nsite supplement names.\n\nA `.seospiderconfig` is Java-serialized binary. Never write or patch one by hand. To read one, run it\nheadless against `$SITE\u002Frobots.txt` and grep the config dump in the log.\n\nWhen a mode config is missing, ask the user to build it per\n[references\u002Fconfigs.md](references\u002Fconfigs.md).\n\nTwo runs on different configs measure different things, so never compare their numbers.\n\n## Audit scope before quoting a number\n\nA crawl reports only on the pages it reached and gives no sign of the ones it missed, so every\ncount covers just the pages this config could see. Before quoting a figure from a spidered crawl,\nrun the checks in [references\u002Fscope-audit.md](references\u002Fscope-audit.md). A sitemap-seeded run\nskips them, because it visits every URL in the sitemap.\n\n## Three data shapes\n\n| Tool | What it is | Use it when |\n| --- | --- | --- |\n| `sf_generate_report` | 61 pre-baked cross-cutting analyses | The question spans URLs: chains, reciprocity, rich-result eligibility, totals |\n| `sf_export_seo_element_urls` | The UI's tab and filter grid | \"Give me the URLs where X\", where X is a filter in a tab |\n| `sf_generate_bulk_export` | Edges and raw content | \"What links to the broken thing\", or \"dump the rendered HTML\" |\n\n## Work in this order\n\n0. Scope audit. Until it passes, treat every count as a lower bound.\n1. `Crawl Overview`: inventory, content types, indexable vs not.\n2. `Issues Overview`: the triage table, with priority, URL count, and How-To-Fix per row. It names\n   the next report worth running.\n3. Drill into whatever Issues Overview ranks High.\n4. Trace each candidate to a source file before it becomes a finding.\n\nFor the report or export that answers a specific question, read\n[references\u002Fcalls.md](references\u002Fcalls.md).\n\n## Traps\n\n- The MCP needs the desktop app open and idle. Otherwise every tool throws\n  `IllegalStateException: Tool cannot be called currently`. That error reports the app's state and\n  says nothing about your arguments. The headless CLI runs beside the GUI.\n- Load a crawl before any report: `sf_list_crawls`, then `sf_load_crawl \u003Cid>`.\n- Output dirs aren't created for you. `file_path` is relative to `sf_list_allowed_base_directory`.\n  Run `sf_create_directory` first or get `NoSuchFileException`.\n- During a crawl only `sf_crawl_progress` responds. Crawl, poll, then export.\n- Pass `export_type: \"CSV\"`. The default NDJSON arrives as one giant line.\n- `sf_list_available_bulk_exports` overflows the token limit. Call it once and keep the list.\n- Always write to `file_path`, then read the part you need with shell. Inline content fills the\n  context window.\n\n## Report\n\nOpen every set of counts with coverage (\"238 of 727 sitemap URLs, 33%\") and call the counts lower\nbounds. For a sitemap-seeded run, \"117 of 117\" is enough.\n\nSort findings into three buckets, in order:\n\n1. Confirmed ours. This repo serves the URL, and you name the file and line that emits the defect.\n   Only these go in a PR.\n2. Real, untraced. Name the system not yet ruled out and the check that settles it.\n3. Untriaged rows, straight from `Issues Overview`, labelled uninvestigated.\n",{"name":5,"description":7},"main","4a72cb32978e2633c4e0679572968456dff47707","plugins\u002Fnt-seo-spider\u002Fskills\u002Fcrawl",0,"https:\u002F\u002Fgithub.com\u002Fnotambourine\u002Fagent-plugins","https:\u002F\u002Fgithub.com\u002Fnotambourine","https:\u002F\u002Fnotambourine.com\u002F","A boutique AI-native engineering agency","2026-11-12 23:38:28",{"source":8,"skillName":5,"commands":33,"prompt":43,"zipAvailable":44},[34,37,40],{"tool":35,"command":36},"npx","npx skills add notambourine\u002Fagent-plugins --skill crawl",{"tool":38,"command":39},"bunx","bunx skills add notambourine\u002Fagent-plugins --skill crawl",{"tool":41,"command":42},"pnpm","pnpm dlx skills add notambourine\u002Fagent-plugins --skill crawl","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fnotambourine\u002Fagent-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fnt-seo-spider\u002Fskills\u002Fcrawl\u002FSKILL.md",true,[46,52,56,59,65,69],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"configs\u002Flinks.seospiderconfig","OTHER","其他",38397,"https:\u002F\u002Fgithub.com\u002Fnotambourine\u002Fagent-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fnt-seo-spider\u002Fskills\u002Fcrawl\u002Fconfigs\u002Flinks.seospiderconfig",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"configs\u002Frender.seospiderconfig",38253,"https:\u002F\u002Fgithub.com\u002Fnotambourine\u002Fagent-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fnt-seo-spider\u002Fskills\u002Fcrawl\u002Fconfigs\u002Frender.seospiderconfig",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":58},"configs\u002Fschema.seospiderconfig","https:\u002F\u002Fgithub.com\u002Fnotambourine\u002Fagent-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fnt-seo-spider\u002Fskills\u002Fcrawl\u002Fconfigs\u002Fschema.seospiderconfig",{"path":60,"resourceType":61,"resourceTypeDesc":62,"sizeBytes":63,"sourceHtmlUrl":64},"references\u002Fcalls.md","REFERENCE","参考文档",1777,"https:\u002F\u002Fgithub.com\u002Fnotambourine\u002Fagent-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fnt-seo-spider\u002Fskills\u002Fcrawl\u002Freferences\u002Fcalls.md",{"path":66,"resourceType":61,"resourceTypeDesc":62,"sizeBytes":67,"sourceHtmlUrl":68},"references\u002Fconfigs.md",791,"https:\u002F\u002Fgithub.com\u002Fnotambourine\u002Fagent-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fnt-seo-spider\u002Fskills\u002Fcrawl\u002Freferences\u002Fconfigs.md",{"path":70,"resourceType":61,"resourceTypeDesc":62,"sizeBytes":71,"sourceHtmlUrl":72},"references\u002Fscope-audit.md",1979,"https:\u002F\u002Fgithub.com\u002Fnotambourine\u002Fagent-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fnt-seo-spider\u002Fskills\u002Fcrawl\u002Freferences\u002Fscope-audit.md",[74,81,88,95,102,109],{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":18},"01M7348W9QJ1YT3H1M1VR90K4P","human-voice","Humanize prose by choosing a surgical voice edit or a structural rewrite. Use for AI-sounding drafts, anti-slop passes, editorial reviews, and requests to preserve an author's voice.","https:\u002F\u002Fgithub.com\u002Fnotambourine\u002Fagent-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fnt-voice\u002Fskills\u002Fhuman-voice\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":18},"01M7348RS0WWS16MTEHKHV54JP","install-anti-slop","Install and configure the anti-slop Oxlint plugin in a local TypeScript or JavaScript repository. Use whenever a user asks to add anti-slop lint rules, copy the anti-slop plugin, configure opinionated Oxlint rules, or migrate an existing local anti-slop setup.","https:\u002F\u002Fgithub.com\u002Fnotambourine\u002Fagent-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fnt-vendor\u002Fskills\u002Finstall-anti-slop\u002FSKILL.md",[],[],{"skillNo":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":94,"publishedAt":18},"01M7348Q2FDZX3EBHYSDXGZSBQ","improve-codebase-architecture","Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.","https:\u002F\u002Fgithub.com\u002Fnotambourine\u002Fagent-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fnt-vendor\u002Fskills\u002Fimprove-codebase-architecture\u002FSKILL.md",[],[],{"skillNo":96,"name":97,"nameZh":6,"description":98,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":99,"categories":100,"keywords":101,"publishedAt":18},"01M7348NKZ61680RWM1RW8WDBZ","eli5","Explain a topic like I'm a 5 year old. Use when the user types \u002Feli5 \u003Ctopic> or asks for a dead-simple picture explainer of how something works.","https:\u002F\u002Fgithub.com\u002Fnotambourine\u002Fagent-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fnt-vendor\u002Fskills\u002Feli5\u002FSKILL.md",[],[],{"skillNo":103,"name":104,"nameZh":6,"description":105,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":106,"categories":107,"keywords":108,"publishedAt":18},"01M7348J36D3P7A73TPW0AJQ3Z","codebase-design","Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.","https:\u002F\u002Fgithub.com\u002Fnotambourine\u002Fagent-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fnt-vendor\u002Fskills\u002Fcodebase-design\u002FSKILL.md",[],[],{"skillNo":110,"name":111,"nameZh":6,"description":112,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":113,"categories":114,"keywords":115,"publishedAt":18},"01M7348F5KM8PGZFCAAJGM8HFS","audit-codebase","Read-only whole-codebase audit for simplifications in data structures, state representation, control flow, algorithms, and ownership. Inventories every subsystem as a coverage contract, reviews each one in a bounded subagent, verifies each finding against the repo, then audits its own coverage. Never edits, runs tests, commits, or pushes. Use for \"audit this codebase\", \"find simplifications\", or a pre-refactor survey.","https:\u002F\u002Fgithub.com\u002Fnotambourine\u002Fagent-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fnt-vendor\u002Fskills\u002Faudit-codebase\u002FSKILL.md",[],[]]