[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7BRX4157NWMCYT6SZ2MVRD2":3,"skill-same:01M7BRX4157NWMCYT6SZ2MVRD2":44},{"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":6,"ownerDescription":6,"updatedAt":29,"install":30,"resources":43},"01M7BRX4157NWMCYT6SZ2MVRD2","career-ops-scraper-only",null,"Discover and ingest new career-ops job postings when the user explicitly asks to run the scraper only, with no triage or later stages. Separate from the broader career-ops scan mode.","srevilla55\u002Fcareer-ops-taste","srevilla55","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F79175774?v=4","01M7BRWGD5M0BM6YEET47YHKDG","Sebastián Revilla","01M7BRWGDVPZ748GXRM16Y5Q3Y",0,"MIT","https:\u002F\u002Fgithub.com\u002Fsrevilla55\u002Fcareer-ops-taste\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fcareer-ops-scraper-only\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: career-ops-scraper-only\ndescription: >-\n  Discover and ingest new career-ops job postings when the user explicitly asks\n  to run the scraper only, with no triage or later stages. Separate from the\n  broader career-ops scan mode.\n---\n\n# Career-ops scraper-only discovery\n\nUse the existing scraper from the career-ops checkout. This workflow requires\nno claude-mem service or external model; do not query or start claude-mem.\nFirst follow [root resolution and shared preflight](..\u002Fcareer-ops\u002FSKILL.md#project-root-resolution), including the local-controller data-root check. This selects no broader mode.\n\n## Before running\n\n1. Read the checkout's current `AGENTS.md`, `modes\u002F_custom.md`,\n   `config\u002Fprofile.yml`, `DATA_CONTRACT.md`, and\n   `local\u002Forchestration\u002Fscan-all.sh`. Current code and rules take precedence\n   over remembered commands or queue counts.\n2. Inspect `git status --short`, active scan and batch workers, locks and their\n   owners (including `data\u002Fpipeline.md.lock`), batch claims and `.eval-wave`.\n   Respect existing work; do not delete locks, rebuild batch input, or start a\n   competing scan.\n3. Inspect `data\u002Fpipeline.md`, `data\u002Fscan-all-last-success`, and\n   `data\u002Fscan-runs.tsv`. Record the pending count and completion marker before\n   running. Do not infer a current result from historical logs.\n4. Read `local\u002FREADME.md`, `local\u002Fpyproject.toml`, `local\u002Fuv.lock`, and the\n   effective `JOBSPY_SITES`. Read the installed version from the lock; use that\n   locked environment and preserve the adapter's metadata\u002Ffilter contracts.\n   If dependency setup is needed, sync the existing lock from `local\u002F` with\n   `UV_CACHE_DIR=\u002Ftmp\u002Fjob-agent-uv-cache uv sync --locked`; do not upgrade\n   dependencies or restore obsolete provider monkeypatches during a scan.\n\n## Run and wait\n\nRun the canonical script from the checkout root:\n\n```bash\nenv -u JOBSPY_HOURS UV_CACHE_DIR=\u002Ftmp\u002Fjob-agent-uv-cache .\u002Flocal\u002Forchestration\u002Fscan-all.sh\n```\n\nThe script calculates the window from the last successful full scrape. If its\ncompletion marker is absent, it uses the last broad completed scan in\n`data\u002Fscan-runs.tsv`, or its bootstrap default. Do not calculate routine hours\nmanually. The wrapper also respects an existing explicitly accepted cutoff\n(`data\u002Fscan-all-accepted-through.json`); never create or advance one merely to\nhide missing coverage. Clear an inherited `JOBSPY_HOURS` unless the user explicitly requests\nan override; only then supply their positive whole-number hours as\n`JOBSPY_HOURS` instead of unsetting it.\n\nThe script runs ATS discovery, JobSpy, ingestion, and built-in repair. Keep its\nprocess\u002Fsession handle and wait for that same process's final ingest and repair\noutput and exit status. It checks per-process native ATS and JobSpy health\nreceipts before advancing the success marker. Missing\u002Fstale receipts, provider\nerrors, an unavailable LinkedIn query, or request\u002Fpage budgets that truncate\ncoverage leave the marker unchanged. A file or exit code alone is insufficient. If interrupted or a stage fails,\nreport partial progress and preserve written state; do not claim a full scan.\nCheck the completion marker afterward as supporting evidence, never as a\nsubstitute for the current process's output.\nThe wrapper has no safe `--dry-run`\u002F`--help` preview; inspect its source instead.\n\n## Report and stop\n\nReport the window, ATS additions, JobSpy ingested additions, pending queue\nchange, and repair results from this run. State observed coverage limits such\nas provider errors, NVIDIA page limits, LinkedIn per-query caps, or unrepaired\nmetadata. Do not claim exhaustive coverage. Keep the configured healthy source\ndefaults; probe quarantined Glassdoor only when explicitly requested.\nDefaults are Indeed and LinkedIn. LinkedIn requests have shared pacing and\nhard budgets; a 429 pauses that source. Do not add authenticated sessions or\nproxies, or start a separate recovery run without its requested scope. Existing\nrecovery helpers retain checkpoints when that work is requested. Captured rows remain\nusable even when the overall window is incomplete. Correlate `local\u002Fsource-health.json` and\nscan receipts with this run; distinguish a provider failure from zero matches\nor filtering. A partial ATS\u002Fprovider result remains partial even when the other\nsources add jobs.\n\nStop after discovery, ingestion, and the script's built-in repair. Do not run\nseparate hydration, triage, evaluation, packaging, updates, sending, or\nsubmissions. The script's `Next:` footer, the broader scan mode, and\n`next-step.mjs` do not authorize advancing to another stage.\n","# Career-ops scraper-only discovery\n\nUse the existing scraper from the career-ops checkout. This workflow requires\nno claude-mem service or external model; do not query or start claude-mem.\nFirst follow [root resolution and shared preflight](..\u002Fcareer-ops\u002FSKILL.md#project-root-resolution), including the local-controller data-root check. This selects no broader mode.\n\n## Before running\n\n1. Read the checkout's current `AGENTS.md`, `modes\u002F_custom.md`,\n   `config\u002Fprofile.yml`, `DATA_CONTRACT.md`, and\n   `local\u002Forchestration\u002Fscan-all.sh`. Current code and rules take precedence\n   over remembered commands or queue counts.\n2. Inspect `git status --short`, active scan and batch workers, locks and their\n   owners (including `data\u002Fpipeline.md.lock`), batch claims and `.eval-wave`.\n   Respect existing work; do not delete locks, rebuild batch input, or start a\n   competing scan.\n3. Inspect `data\u002Fpipeline.md`, `data\u002Fscan-all-last-success`, and\n   `data\u002Fscan-runs.tsv`. Record the pending count and completion marker before\n   running. Do not infer a current result from historical logs.\n4. Read `local\u002FREADME.md`, `local\u002Fpyproject.toml`, `local\u002Fuv.lock`, and the\n   effective `JOBSPY_SITES`. Read the installed version from the lock; use that\n   locked environment and preserve the adapter's metadata\u002Ffilter contracts.\n   If dependency setup is needed, sync the existing lock from `local\u002F` with\n   `UV_CACHE_DIR=\u002Ftmp\u002Fjob-agent-uv-cache uv sync --locked`; do not upgrade\n   dependencies or restore obsolete provider monkeypatches during a scan.\n\n## Run and wait\n\nRun the canonical script from the checkout root:\n\n```bash\nenv -u JOBSPY_HOURS UV_CACHE_DIR=\u002Ftmp\u002Fjob-agent-uv-cache .\u002Flocal\u002Forchestration\u002Fscan-all.sh\n```\n\nThe script calculates the window from the last successful full scrape. If its\ncompletion marker is absent, it uses the last broad completed scan in\n`data\u002Fscan-runs.tsv`, or its bootstrap default. Do not calculate routine hours\nmanually. The wrapper also respects an existing explicitly accepted cutoff\n(`data\u002Fscan-all-accepted-through.json`); never create or advance one merely to\nhide missing coverage. Clear an inherited `JOBSPY_HOURS` unless the user explicitly requests\nan override; only then supply their positive whole-number hours as\n`JOBSPY_HOURS` instead of unsetting it.\n\nThe script runs ATS discovery, JobSpy, ingestion, and built-in repair. Keep its\nprocess\u002Fsession handle and wait for that same process's final ingest and repair\noutput and exit status. It checks per-process native ATS and JobSpy health\nreceipts before advancing the success marker. Missing\u002Fstale receipts, provider\nerrors, an unavailable LinkedIn query, or request\u002Fpage budgets that truncate\ncoverage leave the marker unchanged. A file or exit code alone is insufficient. If interrupted or a stage fails,\nreport partial progress and preserve written state; do not claim a full scan.\nCheck the completion marker afterward as supporting evidence, never as a\nsubstitute for the current process's output.\nThe wrapper has no safe `--dry-run`\u002F`--help` preview; inspect its source instead.\n\n## Report and stop\n\nReport the window, ATS additions, JobSpy ingested additions, pending queue\nchange, and repair results from this run. State observed coverage limits such\nas provider errors, NVIDIA page limits, LinkedIn per-query caps, or unrepaired\nmetadata. Do not claim exhaustive coverage. Keep the configured healthy source\ndefaults; probe quarantined Glassdoor only when explicitly requested.\nDefaults are Indeed and LinkedIn. LinkedIn requests have shared pacing and\nhard budgets; a 429 pauses that source. Do not add authenticated sessions or\nproxies, or start a separate recovery run without its requested scope. Existing\nrecovery helpers retain checkpoints when that work is requested. Captured rows remain\nusable even when the overall window is incomplete. Correlate `local\u002Fsource-health.json` and\nscan receipts with this run; distinguish a provider failure from zero matches\nor filtering. A partial ATS\u002Fprovider result remains partial even when the other\nsources add jobs.\n\nStop after discovery, ingestion, and the script's built-in repair. Do not run\nseparate hydration, triage, evaluation, packaging, updates, sending, or\nsubmissions. The script's `Next:` footer, the broader scan mode, and\n`next-step.mjs` do not authorize advancing to another stage.\n",{"name":5,"description":7},"main","634df9f57f300ee52538397b6a81cef915ea7886",".agents\u002Fskills\u002Fcareer-ops-scraper-only","https:\u002F\u002Fgithub.com\u002Fsrevilla55\u002Fcareer-ops-taste","https:\u002F\u002Fgithub.com\u002Fsrevilla55","2026-11-13 23:06:48",{"source":8,"skillName":5,"commands":31,"prompt":41,"zipAvailable":42},[32,35,38],{"tool":33,"command":34},"npx","npx skills add srevilla55\u002Fcareer-ops-taste --skill career-ops-scraper-only",{"tool":36,"command":37},"bunx","bunx skills add srevilla55\u002Fcareer-ops-taste --skill career-ops-scraper-only",{"tool":39,"command":40},"pnpm","pnpm dlx skills add srevilla55\u002Fcareer-ops-taste --skill career-ops-scraper-only","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fsrevilla55\u002Fcareer-ops-taste\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fcareer-ops-scraper-only\u002FSKILL.md",true,[],[45,52,58,65,72,79],{"skillNo":46,"name":47,"nameZh":6,"description":48,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":49,"categories":50,"keywords":51,"publishedAt":19},"01M7BRYZFN4HG54W5QZRDMX0P0","career-ops-plugin-notion","How to mirror the career-ops tracker to a Notion database and read records back as job leads.","https:\u002F\u002Fgithub.com\u002Fsrevilla55\u002Fcareer-ops-taste\u002Fblob\u002Fmain\u002Fplugins\u002Fnotion\u002Fskill.md",[],[],{"skillNo":53,"name":54,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":55,"categories":56,"keywords":57,"publishedAt":19},"01M7BRYY136Q35C7VGCWKMRGTB","h1b-sponsor","https:\u002F\u002Fgithub.com\u002Fsrevilla55\u002Fcareer-ops-taste\u002Fblob\u002Fmain\u002Fplugins\u002Fh1b-sponsor\u002Fskill.md",[],[],{"skillNo":59,"name":60,"nameZh":6,"description":61,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":62,"categories":63,"keywords":64,"publishedAt":19},"01M7BRYWK0CNFCGCPR82XW0D5P","career-ops-plugin-gmail","How to pull job leads from a Gmail label into the career-ops pipeline.","https:\u002F\u002Fgithub.com\u002Fsrevilla55\u002Fcareer-ops-taste\u002Fblob\u002Fmain\u002Fplugins\u002Fgmail\u002Fskill.md",[],[],{"skillNo":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":19},"01M7BRYV719RQ0KCCEQ3KJE579","career-ops-plugin-apify","How to scan a job source through an Apify actor as a keyed provider.","https:\u002F\u002Fgithub.com\u002Fsrevilla55\u002Fcareer-ops-taste\u002Fblob\u002Fmain\u002Fplugins\u002Fapify\u002Fskill.md",[],[],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":19},"01M7BRYMQ3C5G7Y49T3D52B50P","career-ops","Route career-ops job-search requests to the existing pipeline skills and modes. Use for job URLs\u002FJDs, discovery, triage, evaluation, package liveness, CVs, application drafts, tracking, interviews, or a named career-ops mode. Preserve the user's requested stage when choosing a workflow.","https:\u002F\u002Fgithub.com\u002Fsrevilla55\u002Fcareer-ops-taste\u002Fblob\u002Fmain\u002Fopenai-directory\u002Fskills\u002Fcareer-ops\u002FSKILL.md",[],[],{"skillNo":80,"name":74,"nameZh":6,"description":75,"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":83,"publishedAt":19},"01M7BRYE533SXPY1S6RN4M0RSF","https:\u002F\u002Fgithub.com\u002Fsrevilla55\u002Fcareer-ops-taste\u002Fblob\u002Fmain\u002Fcursor-directory\u002Fskills\u002Fcareer-ops\u002FSKILL.md",[],[]]