[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M79RP0SMMP7SDR9C6GG2SBH7":3,"skill-same:01M79RP0SMMP7SDR9C6GG2SBH7":54},{"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":26,"commitSha":27,"skillDirectory":28,"forksCount":14,"repositoryHtmlUrl":29,"repositoryHomepageUrl":6,"ownerHtmlUrl":30,"ownerBlogUrl":31,"ownerDescription":32,"updatedAt":33,"install":34,"resources":47},"01M79RP0SMMP7SDR9C6GG2SBH7","scrape",null,"Finds new job postings matching your profile via installed portal-search CLIs (LinkedIn, local job boards, and any skills added with \u002Fadd-portal). Deduplicates across runs. Triggers on: job scrape, find jobs, search jobs, new jobs, job search, scrape jobs, \u002Fscrape","Project516\u002Fjob-search-opencode","Project516","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F138796702?v=4","01M79RKWZYV1Z9PEB6YFXH97A7","project516","01M79RKX0NP2Y1BG8GJJ3ZSZSC",0,"MIT","https:\u002F\u002Fgithub.com\u002FProject516\u002Fjob-search-opencode\u002Fblob\u002Fmaster\u002F.claude\u002Fskills\u002Fjob-scraper\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: scrape\ndescription: >\n  Finds new job postings matching your profile via installed portal-search CLIs\n  (LinkedIn, local job boards, and any skills added with \u002Fadd-portal). Deduplicates\n  across runs. Triggers on: job scrape, find jobs, search jobs, new jobs, job search,\n  scrape jobs, \u002Fscrape\nallowed-tools: Read, Write, Edit, Glob, Grep, Bash(bun --version), Bash(bun run .agents\u002Fskills\u002F*\u002Fcli\u002Fsrc\u002Fcli.ts *), WebFetch, WebSearch, Agent, AskUserQuestion\n---\n\n# Job Scraper\n\n---\n\n## How It Works\n\nThis skill searches job portals using the **installed portal-search CLIs** in\n`.agents\u002Fskills\u002F` (plus WebSearch as a fallback), using queries from your profile.\nIt deduplicates against previously seen jobs and the application tracker, and\npresents new matches with a quick fit assessment.\n\n## Invocation\n\nThe user triggers this skill by saying things like:\n- \"Find new jobs\"\n- \"Scrape for jobs\"\n- \"Any new positions?\"\n- \"\u002Fscrape\"\n\nOptional arguments:\n- A focus area, e.g. \"\u002Fscrape data science\" or \"\u002Fscrape geophysics\"\n- \"broad\" to run all search categories, e.g. \"\u002Fscrape broad\"\n- \"health\" to run the portal health check only (Step 4.75), without searching, deduplicating, or presenting jobs - e.g. \"\u002Fscrape health\", or \"\u002Fscrape health jobnet\" to probe one portal even if disabled\n\n---\n\n## Execution Steps\n\n### Step 0: Load State\n\n1. Read `job_scraper\u002Fseen_jobs.json` (create if missing - start with `{\"seen\": {}}`)\n2. Read `job_search_tracker.csv` to extract already-applied companies+roles\n3. Read `search-queries.md` (this directory) for the search strategy\n\n### Step 1: Search\n\nRead `search-queries.md` (this directory) for the search strategy. By default, run the top 3 priority query categories. If the user said \"broad\", run all categories. If the user specified a focus area (e.g. \"data science\"), prioritize queries from that category.\n\n**Use the installed CLI tools as the primary search mechanism.** Fall back to `WebSearch` only for portals that do not have a CLI skill, or if `bun` is unavailable on the system.\n\n#### 1a. Check bun availability\n\n```bash\nbun --version\n```\n\nIf this fails (bun not installed), skip to **1c (WebSearch fallback)** for all portals and note the fallback in the Step 5 output.\n\n#### 1b. Run CLI tools (primary — run these in parallel where possible)\n\nDiscover all installed portal CLI skills by reading every `SKILL.md` found under `.agents\u002Fskills\u002F*\u002FSKILL.md`. Each file documents that portal's exact CLI flags and usage examples. **Use each portal's own documented interface — do not guess flags.** This approach automatically includes any new portals added via `\u002Fadd-portal` without requiring changes to this file.\n\n**Honor the `enabled` toggle.** A portal is enabled unless its `SKILL.md` frontmatter sets `enabled: false` (a missing key means enabled — the default). Skip each disabled portal and record it for the Step 5 summary. A fork can thus keep a portal installed but sit out a run without deleting its directory.\n\nFor each **enabled** portal skill:\n\n1. Read its `SKILL.md` to find the correct `bun run …` invocation and supported flags.\n2. Translate the query terms from `search-queries.md` into that portal's flag format (e.g. `--key`, `--search-string`, `--query`, filter codes — whatever the portal's SKILL.md specifies).\n3. Scope to the last 14 days using the portal's supported recency flag (`--jobage`, `--since \u003CYYYY-MM-DD>`, `--order PublicationDate`, etc. — as documented per portal).\n4. Cap results to ~20 per call using the portal's limit flag.\n5. Use `--format json` for machine-readable output.\n\nRun all portal CLI calls in parallel where possible using the Agent tool. Collect all `results` arrays into a single pool for Step 2, keeping each result tagged with its source portal skill (for Step 2 `detail` lookups).\n\nIf a CLI tool exits with a non-zero code, log the error message and continue — do not abort the whole search.\n\n#### 1c. WebSearch fallback\n\nUse `WebSearch` for:\n- Portals listed in `search-queries.md` that do **not** have a corresponding directory under `.agents\u002Fskills\u002F`\n- Any portal whose CLI fails at runtime\n- When bun is unavailable (Step 1a failed)\n\nUse the site-specific query strings from `search-queries.md` directly as WebSearch queries for these portals.\n\n### Step 2: Fetch & Parse\n\nFor each promising result from Step 1:\n\n**From CLI results:** Search output already includes title, company, location, date,\nand URL. For jobs worth a deeper look, fetch full detail with that portal's `detail`\ncommand (see its SKILL.md — do not guess flags) to extract **key requirements**,\n**application deadline**, and a brief description snippet.\n\n**From WebSearch results:** Use `WebFetch` on the posting URL and extract the same\nfields manually.\n\nFor every candidate:\n- Skip if the URL or company+title combo already exists in `seen_jobs.json`\n- Skip if the company+role already appears in `job_search_tracker.csv`\n\n### Step 2.5: Mass-Posting Detection (within this run)\n\nA distribution pattern worth flagging to the user as a caution signal, not as an accusation against the employer - it describes how a listing is being distributed, not a verdict on whether the company is legitimate. It alone proves nothing is wrong (companies do legitimately hire the same role across several cities); flag it so the user can factor it in when deciding whether to invest time, don't downgrade fit or silently exclude the result because of it.\n\nIf two or more results in this run's pool (from the same company, or sharing the same req\u002Fjob ID visible in the URL or title) have substantially the same description and differ only in city\u002Flocation\u002Ftitle, don't present them as separate rows. Consolidate into a single row and note the spread, e.g. \"posted identically across 6 cities (BR, MX, GT)\".\n\n### Step 3: Quick Fit Assessment\n\nFor each new job, do a rapid fit check (NOT the full evaluation from `04-job-evaluation.md` - just a quick signal):\n\n- **High match**: Role directly involves your core skills\n- **Medium match**: Role is adjacent to your experience\n- **Low match**: Role requires significant skills you lack\n\n### Step 4: Deduplicate & Store\n\n1. Add ALL fetched jobs (new and skipped) to `seen_jobs.json` with structure:\n```json\n{\n  \"seen\": {\n    \"\u003Curl_or_company_title_key>\": {\n      \"title\": \"...\",\n      \"company\": \"...\",\n      \"url\": \"...\",\n      \"first_seen\": \"YYYY-MM-DD\",\n      \"fit\": \"high\u002Fmedium\u002Flow\",\n      \"status\": \"new\u002Fskipped\u002Fevaluated\u002Franked\u002Fexpired\",\n      \"portal\": \"\u003Csource portal skill, e.g. jobindex-search>\"\n    }\n  }\n}\n```\n\nThe `portal` field records which CLI skill produced the job (results are already tagged per portal in Step 1b - persist that tag here). Entries written before this field existed lack it; the health check (Step 4.75) attributes those by matching the URL's domain against each portal's base URL, so do not backfill.\n\n`\u002Frank` extends this schema additively: ranked entries also carry `rank_score` (0–100 overall score), `rank_verdict` (fit band, e.g. \"strong fit\"), and `rank_date` (ISO date of ranking). The `status` field is set to `\"ranked\"`. Do not drop any of these fields when re-writing entries.\n\n2. Only present jobs NOT already in the seen list or tracker.\n\n### Step 4.5: Generate Referral Contact Links (High & Medium Fit Only)\n\nFor every job from this run with `fit` of **high** or **medium** (skip low-fit jobs),\nbuild two LinkedIn people-search URLs so the user can find a recruiter or team member to\nreach out to for a referral or a warm intro. This is deliberately a link-generation step,\nnot an automated lookup: no scraping, no third-party API, zero runtime dependencies or\ncredentials required.\n\n**A. Recruiters \u002F Talent Acquisition (the referral path)**\n```\nhttps:\u002F\u002Fwww.linkedin.com\u002Fsearch\u002Fresults\u002Fpeople\u002F?keywords=\u003Curl-encoded \"\u003CCompany Name> recruiter\">&origin=GLOBAL_SEARCH_HEADER\n```\n\n**B. Role\u002Fteam peers (informational-outreach \u002F warm-intro path)**\n```\nhttps:\u002F\u002Fwww.linkedin.com\u002Fsearch\u002Fresults\u002Fpeople\u002F?keywords=\u003Curl-encoded \"\u003CCompany Name> \u003Crole keyword>\">&origin=GLOBAL_SEARCH_HEADER\n```\nUse a short keyword drawn from the posting's title for `\u003Crole keyword>` - e.g. a posting\ntitled \"AI Program Manager\" becomes `\"\u003CCompany Name> AI Program Manager\"`.\n\nBoth links are for the user to open and browse themselves - never fetch or scrape the\nLinkedIn people-search result pages programmatically. Never fabricate contacts or claim a\nspecific person was found; these are search links, not results.\n\n### Step 4.75: Portal Health Check\n\nScraper-based portal CLIs rot silently: when a portal changes its markup, the parser usually exits 0 with zero results or with null\u002Fgarbled fields, and the Step 1c fallback never fires because it only triggers on hard failure. This step catches that from evidence the run already holds.\n\n**Free pass (no extra requests).** For each enabled portal that ran in Step 1b:\n\n- **Degraded scan:** inspect the results it returned this run. Flags: `company` null or empty on every result, empty titles, undecoded entities (`&amp;`) or HTML fragments in titles, URLs that do not point at the portal. Any of these means the parser is half-working and `\u002Fscrape` is silently collecting junk.\n- **Yield history:** if the portal returned zero results across all of this run's queries, check whether `seen_jobs.json` holds prior entries from it (via the `portal` field, or by matching URL domains for entries predating the field). A portal that produced jobs on earlier runs and produces nothing now is suspect - the same queries worked before.\n\n**Escalation (bounded, on suspicion only).** A suspect portal gets **one** sentinel probe: run its documented `search` with the example query from its own SKILL.md (that query provably worked when the skill was registered), the portal's limit flag capped at 3, `--format json`. If that returns nothing, retry **once** with a single common word. Only then is the verdict **broken**. A 429 or block page is **never** evidence of breakage - record the portal as **inconclusive (rate-limited)**, back off, and do not retry.\n\n**Verdicts.** Healthy portals get silence - no table, no line. Anything else surfaces in the Step 5 summary as a health line.\n\n**Probe-only mode (`\u002Fscrape health`).** Skip Steps 1-4 and this step's free pass (there is no fresh run to scan); instead probe every installed portal directly - enabled ones by default, a disabled one only when named explicitly (e.g. `\u002Fscrape health jobnet`). Each portal gets the sentinel probe above, the degraded criteria applied to whatever it returns, and - since the user explicitly asked for diagnosis - one `detail` fetch on the first result of each healthy portal (description must be readable decoded text; a failure downgrades to degraded). Report all statuses in this mode, including healthy. Volume stays bounded: one search, at most one retry, at most one detail per portal.\n\n### Step 5: Present Results\n\nPresent new jobs in a table sorted by fit (high first). When Step 1b skipped\nportals (`enabled: false`), report them with the `skipped (disabled):` line below\nso opting one out stays visible rather than silent; omit the line when nothing\nwas skipped. When Step 4.75 found a portal degraded, broken, or inconclusive,\nadd one `health:` line per suspect portal (healthy portals get no line); after\nthe report, offer to set that portal's `enabled: false` so `\u002Fscrape` stops\nrunning it (and covers it via the Step 1c fallback) until it is fixed - only\nedit the toggle with the user's confirmation, and never edit anything else in\nthe skill.\n\n```\n## New Job Matches - YYYY-MM-DD\n\nFound X new positions (Y high, Z medium, W low match).\n\nskipped (disabled): \u003Cportal-name>, \u003Cportal-name>\n\nhealth: \u003Cportal-name> - degraded (company null on all 12 results); parsing anchors in .agents\u002Fskills\u002F\u003Cportal-name>\u002Furl-reference.md\nhealth: \u003Cportal-name> - broken (0 results for the SKILL.md test query and a broader retry); parsing anchors in .agents\u002Fskills\u002F\u003Cportal-name>\u002Furl-reference.md\n\n| # | Fit | Title | Company | Location | Deadline | URL |\n|---|-----|-------|---------|----------|----------|-----|\n| 1 | High | ... | ... | ... | ... | [Link](...) |\n\nIf Step 2.5 flagged a mass-posting pattern, note it in the Title cell (e.g. \"Frontend Developer (posted in 6 cities)\") rather than burying it - it's a signal the user should see at a glance, not just in the detail highlights below.\n\n### High-Match Highlights\nFor each high-match job, add 2-3 bullet points:\n- Why it matches your profile\n- Key requirements to check\n- Any red flags (including mass-posting signals from Step 2.5)\n\n### Contacts\nFor each high\u002Fmedium-fit job from Step 4.5, add a short contacts block with the two\nLinkedIn search links:\n- Recruiters\u002FTA search link, for the referral path\n- Role\u002Fteam-peer search link, for the warm-intro \u002F informational-outreach path\n```\n\nAfter presenting, ask:\n> \"Want me to evaluate any of these in detail? Just give me the number(s).\"\n\nIf the user picks a number, invoke the **job-application-assistant** skill workflow (fit evaluation first, then CV + cover letter if approved).\n\nIf the run found many new jobs (roughly 8+), also suggest `\u002Frank` - it batch-scores all new postings against the full fit framework and returns a ranked shortlist, which beats eyeballing a long table. (`\u002Frank` sets the `ranked` and `expired` status values in `seen_jobs.json`; treat both as already-seen for dedup purposes.)\n\n### Step 6: Update Tracker (Optional)\n\nIf the user decides to apply to any job, add a row to `job_search_tracker.csv`.\n\n---\n\n## Important Rules\n\n1. **Never fabricate job postings.** Only present jobs from actual CLI search\u002Fdetail output or WebSearch\u002FWebFetch results.\n2. **Respect deduplication.** Always check seen_jobs.json AND job_search_tracker.csv before presenting.\n3. **Focus on configured geographic area.** Skip jobs that require relocation or are clearly outside commute range.\n4. **Only open positions.** Skip postings with expired deadlines or those marked as closed.\n5. **Be efficient with detail fetches.** Don't run `detail` or WebFetch on every search hit — pre-filter by title\u002Fsnippet, then fetch only promising matches.\n6. **Parallel searches.** Run portal CLI searches in parallel; use WebSearch only for gaps the CLIs don't cover.\n7. **No automated people lookups.** Referral contacts (Step 4.5) are LinkedIn search links only - never fetch or scrape LinkedIn people-search result pages programmatically.\n8. **Health checks are bounded and honest.** Step 4.75 spends at most one probe, one retry, and (in `health` mode) one detail fetch per portal - a diagnosis, not a crawl. A rate-limit is never evidence of breakage. Health verdicts come only from observed CLI output; a portal that could not be tested is reported as inconclusive, never guessed. The `enabled` toggle is the only thing the health check may edit, and only with confirmation.\n9. **Flag distribution patterns, never accuse.** The mass-posting signal (Step 2.5) describes how a listing is being distributed, not a claim that the employer is a scam. Never name a company as fraudulent or untrustworthy - present the observation and let the user decide.\n","# Job Scraper\n\n---\n\n## How It Works\n\nThis skill searches job portals using the **installed portal-search CLIs** in\n`.agents\u002Fskills\u002F` (plus WebSearch as a fallback), using queries from your profile.\nIt deduplicates against previously seen jobs and the application tracker, and\npresents new matches with a quick fit assessment.\n\n## Invocation\n\nThe user triggers this skill by saying things like:\n- \"Find new jobs\"\n- \"Scrape for jobs\"\n- \"Any new positions?\"\n- \"\u002Fscrape\"\n\nOptional arguments:\n- A focus area, e.g. \"\u002Fscrape data science\" or \"\u002Fscrape geophysics\"\n- \"broad\" to run all search categories, e.g. \"\u002Fscrape broad\"\n- \"health\" to run the portal health check only (Step 4.75), without searching, deduplicating, or presenting jobs - e.g. \"\u002Fscrape health\", or \"\u002Fscrape health jobnet\" to probe one portal even if disabled\n\n---\n\n## Execution Steps\n\n### Step 0: Load State\n\n1. Read `job_scraper\u002Fseen_jobs.json` (create if missing - start with `{\"seen\": {}}`)\n2. Read `job_search_tracker.csv` to extract already-applied companies+roles\n3. Read `search-queries.md` (this directory) for the search strategy\n\n### Step 1: Search\n\nRead `search-queries.md` (this directory) for the search strategy. By default, run the top 3 priority query categories. If the user said \"broad\", run all categories. If the user specified a focus area (e.g. \"data science\"), prioritize queries from that category.\n\n**Use the installed CLI tools as the primary search mechanism.** Fall back to `WebSearch` only for portals that do not have a CLI skill, or if `bun` is unavailable on the system.\n\n#### 1a. Check bun availability\n\n```bash\nbun --version\n```\n\nIf this fails (bun not installed), skip to **1c (WebSearch fallback)** for all portals and note the fallback in the Step 5 output.\n\n#### 1b. Run CLI tools (primary — run these in parallel where possible)\n\nDiscover all installed portal CLI skills by reading every `SKILL.md` found under `.agents\u002Fskills\u002F*\u002FSKILL.md`. Each file documents that portal's exact CLI flags and usage examples. **Use each portal's own documented interface — do not guess flags.** This approach automatically includes any new portals added via `\u002Fadd-portal` without requiring changes to this file.\n\n**Honor the `enabled` toggle.** A portal is enabled unless its `SKILL.md` frontmatter sets `enabled: false` (a missing key means enabled — the default). Skip each disabled portal and record it for the Step 5 summary. A fork can thus keep a portal installed but sit out a run without deleting its directory.\n\nFor each **enabled** portal skill:\n\n1. Read its `SKILL.md` to find the correct `bun run …` invocation and supported flags.\n2. Translate the query terms from `search-queries.md` into that portal's flag format (e.g. `--key`, `--search-string`, `--query`, filter codes — whatever the portal's SKILL.md specifies).\n3. Scope to the last 14 days using the portal's supported recency flag (`--jobage`, `--since \u003CYYYY-MM-DD>`, `--order PublicationDate`, etc. — as documented per portal).\n4. Cap results to ~20 per call using the portal's limit flag.\n5. Use `--format json` for machine-readable output.\n\nRun all portal CLI calls in parallel where possible using the Agent tool. Collect all `results` arrays into a single pool for Step 2, keeping each result tagged with its source portal skill (for Step 2 `detail` lookups).\n\nIf a CLI tool exits with a non-zero code, log the error message and continue — do not abort the whole search.\n\n#### 1c. WebSearch fallback\n\nUse `WebSearch` for:\n- Portals listed in `search-queries.md` that do **not** have a corresponding directory under `.agents\u002Fskills\u002F`\n- Any portal whose CLI fails at runtime\n- When bun is unavailable (Step 1a failed)\n\nUse the site-specific query strings from `search-queries.md` directly as WebSearch queries for these portals.\n\n### Step 2: Fetch & Parse\n\nFor each promising result from Step 1:\n\n**From CLI results:** Search output already includes title, company, location, date,\nand URL. For jobs worth a deeper look, fetch full detail with that portal's `detail`\ncommand (see its SKILL.md — do not guess flags) to extract **key requirements**,\n**application deadline**, and a brief description snippet.\n\n**From WebSearch results:** Use `WebFetch` on the posting URL and extract the same\nfields manually.\n\nFor every candidate:\n- Skip if the URL or company+title combo already exists in `seen_jobs.json`\n- Skip if the company+role already appears in `job_search_tracker.csv`\n\n### Step 2.5: Mass-Posting Detection (within this run)\n\nA distribution pattern worth flagging to the user as a caution signal, not as an accusation against the employer - it describes how a listing is being distributed, not a verdict on whether the company is legitimate. It alone proves nothing is wrong (companies do legitimately hire the same role across several cities); flag it so the user can factor it in when deciding whether to invest time, don't downgrade fit or silently exclude the result because of it.\n\nIf two or more results in this run's pool (from the same company, or sharing the same req\u002Fjob ID visible in the URL or title) have substantially the same description and differ only in city\u002Flocation\u002Ftitle, don't present them as separate rows. Consolidate into a single row and note the spread, e.g. \"posted identically across 6 cities (BR, MX, GT)\".\n\n### Step 3: Quick Fit Assessment\n\nFor each new job, do a rapid fit check (NOT the full evaluation from `04-job-evaluation.md` - just a quick signal):\n\n- **High match**: Role directly involves your core skills\n- **Medium match**: Role is adjacent to your experience\n- **Low match**: Role requires significant skills you lack\n\n### Step 4: Deduplicate & Store\n\n1. Add ALL fetched jobs (new and skipped) to `seen_jobs.json` with structure:\n```json\n{\n  \"seen\": {\n    \"\u003Curl_or_company_title_key>\": {\n      \"title\": \"...\",\n      \"company\": \"...\",\n      \"url\": \"...\",\n      \"first_seen\": \"YYYY-MM-DD\",\n      \"fit\": \"high\u002Fmedium\u002Flow\",\n      \"status\": \"new\u002Fskipped\u002Fevaluated\u002Franked\u002Fexpired\",\n      \"portal\": \"\u003Csource portal skill, e.g. jobindex-search>\"\n    }\n  }\n}\n```\n\nThe `portal` field records which CLI skill produced the job (results are already tagged per portal in Step 1b - persist that tag here). Entries written before this field existed lack it; the health check (Step 4.75) attributes those by matching the URL's domain against each portal's base URL, so do not backfill.\n\n`\u002Frank` extends this schema additively: ranked entries also carry `rank_score` (0–100 overall score), `rank_verdict` (fit band, e.g. \"strong fit\"), and `rank_date` (ISO date of ranking). The `status` field is set to `\"ranked\"`. Do not drop any of these fields when re-writing entries.\n\n2. Only present jobs NOT already in the seen list or tracker.\n\n### Step 4.5: Generate Referral Contact Links (High & Medium Fit Only)\n\nFor every job from this run with `fit` of **high** or **medium** (skip low-fit jobs),\nbuild two LinkedIn people-search URLs so the user can find a recruiter or team member to\nreach out to for a referral or a warm intro. This is deliberately a link-generation step,\nnot an automated lookup: no scraping, no third-party API, zero runtime dependencies or\ncredentials required.\n\n**A. Recruiters \u002F Talent Acquisition (the referral path)**\n```\nhttps:\u002F\u002Fwww.linkedin.com\u002Fsearch\u002Fresults\u002Fpeople\u002F?keywords=\u003Curl-encoded \"\u003CCompany Name> recruiter\">&origin=GLOBAL_SEARCH_HEADER\n```\n\n**B. Role\u002Fteam peers (informational-outreach \u002F warm-intro path)**\n```\nhttps:\u002F\u002Fwww.linkedin.com\u002Fsearch\u002Fresults\u002Fpeople\u002F?keywords=\u003Curl-encoded \"\u003CCompany Name> \u003Crole keyword>\">&origin=GLOBAL_SEARCH_HEADER\n```\nUse a short keyword drawn from the posting's title for `\u003Crole keyword>` - e.g. a posting\ntitled \"AI Program Manager\" becomes `\"\u003CCompany Name> AI Program Manager\"`.\n\nBoth links are for the user to open and browse themselves - never fetch or scrape the\nLinkedIn people-search result pages programmatically. Never fabricate contacts or claim a\nspecific person was found; these are search links, not results.\n\n### Step 4.75: Portal Health Check\n\nScraper-based portal CLIs rot silently: when a portal changes its markup, the parser usually exits 0 with zero results or with null\u002Fgarbled fields, and the Step 1c fallback never fires because it only triggers on hard failure. This step catches that from evidence the run already holds.\n\n**Free pass (no extra requests).** For each enabled portal that ran in Step 1b:\n\n- **Degraded scan:** inspect the results it returned this run. Flags: `company` null or empty on every result, empty titles, undecoded entities (`&amp;`) or HTML fragments in titles, URLs that do not point at the portal. Any of these means the parser is half-working and `\u002Fscrape` is silently collecting junk.\n- **Yield history:** if the portal returned zero results across all of this run's queries, check whether `seen_jobs.json` holds prior entries from it (via the `portal` field, or by matching URL domains for entries predating the field). A portal that produced jobs on earlier runs and produces nothing now is suspect - the same queries worked before.\n\n**Escalation (bounded, on suspicion only).** A suspect portal gets **one** sentinel probe: run its documented `search` with the example query from its own SKILL.md (that query provably worked when the skill was registered), the portal's limit flag capped at 3, `--format json`. If that returns nothing, retry **once** with a single common word. Only then is the verdict **broken**. A 429 or block page is **never** evidence of breakage - record the portal as **inconclusive (rate-limited)**, back off, and do not retry.\n\n**Verdicts.** Healthy portals get silence - no table, no line. Anything else surfaces in the Step 5 summary as a health line.\n\n**Probe-only mode (`\u002Fscrape health`).** Skip Steps 1-4 and this step's free pass (there is no fresh run to scan); instead probe every installed portal directly - enabled ones by default, a disabled one only when named explicitly (e.g. `\u002Fscrape health jobnet`). Each portal gets the sentinel probe above, the degraded criteria applied to whatever it returns, and - since the user explicitly asked for diagnosis - one `detail` fetch on the first result of each healthy portal (description must be readable decoded text; a failure downgrades to degraded). Report all statuses in this mode, including healthy. Volume stays bounded: one search, at most one retry, at most one detail per portal.\n\n### Step 5: Present Results\n\nPresent new jobs in a table sorted by fit (high first). When Step 1b skipped\nportals (`enabled: false`), report them with the `skipped (disabled):` line below\nso opting one out stays visible rather than silent; omit the line when nothing\nwas skipped. When Step 4.75 found a portal degraded, broken, or inconclusive,\nadd one `health:` line per suspect portal (healthy portals get no line); after\nthe report, offer to set that portal's `enabled: false` so `\u002Fscrape` stops\nrunning it (and covers it via the Step 1c fallback) until it is fixed - only\nedit the toggle with the user's confirmation, and never edit anything else in\nthe skill.\n\n```\n## New Job Matches - YYYY-MM-DD\n\nFound X new positions (Y high, Z medium, W low match).\n\nskipped (disabled): \u003Cportal-name>, \u003Cportal-name>\n\nhealth: \u003Cportal-name> - degraded (company null on all 12 results); parsing anchors in .agents\u002Fskills\u002F\u003Cportal-name>\u002Furl-reference.md\nhealth: \u003Cportal-name> - broken (0 results for the SKILL.md test query and a broader retry); parsing anchors in .agents\u002Fskills\u002F\u003Cportal-name>\u002Furl-reference.md\n\n| # | Fit | Title | Company | Location | Deadline | URL |\n|---|-----|-------|---------|----------|----------|-----|\n| 1 | High | ... | ... | ... | ... | [Link](...) |\n\nIf Step 2.5 flagged a mass-posting pattern, note it in the Title cell (e.g. \"Frontend Developer (posted in 6 cities)\") rather than burying it - it's a signal the user should see at a glance, not just in the detail highlights below.\n\n### High-Match Highlights\nFor each high-match job, add 2-3 bullet points:\n- Why it matches your profile\n- Key requirements to check\n- Any red flags (including mass-posting signals from Step 2.5)\n\n### Contacts\nFor each high\u002Fmedium-fit job from Step 4.5, add a short contacts block with the two\nLinkedIn search links:\n- Recruiters\u002FTA search link, for the referral path\n- Role\u002Fteam-peer search link, for the warm-intro \u002F informational-outreach path\n```\n\nAfter presenting, ask:\n> \"Want me to evaluate any of these in detail? Just give me the number(s).\"\n\nIf the user picks a number, invoke the **job-application-assistant** skill workflow (fit evaluation first, then CV + cover letter if approved).\n\nIf the run found many new jobs (roughly 8+), also suggest `\u002Frank` - it batch-scores all new postings against the full fit framework and returns a ranked shortlist, which beats eyeballing a long table. (`\u002Frank` sets the `ranked` and `expired` status values in `seen_jobs.json`; treat both as already-seen for dedup purposes.)\n\n### Step 6: Update Tracker (Optional)\n\nIf the user decides to apply to any job, add a row to `job_search_tracker.csv`.\n\n---\n\n## Important Rules\n\n1. **Never fabricate job postings.** Only present jobs from actual CLI search\u002Fdetail output or WebSearch\u002FWebFetch results.\n2. **Respect deduplication.** Always check seen_jobs.json AND job_search_tracker.csv before presenting.\n3. **Focus on configured geographic area.** Skip jobs that require relocation or are clearly outside commute range.\n4. **Only open positions.** Skip postings with expired deadlines or those marked as closed.\n5. **Be efficient with detail fetches.** Don't run `detail` or WebFetch on every search hit — pre-filter by title\u002Fsnippet, then fetch only promising matches.\n6. **Parallel searches.** Run portal CLI searches in parallel; use WebSearch only for gaps the CLIs don't cover.\n7. **No automated people lookups.** Referral contacts (Step 4.5) are LinkedIn search links only - never fetch or scrape LinkedIn people-search result pages programmatically.\n8. **Health checks are bounded and honest.** Step 4.75 spends at most one probe, one retry, and (in `health` mode) one detail fetch per portal - a diagnosis, not a crawl. A rate-limit is never evidence of breakage. Health verdicts come only from observed CLI output; a portal that could not be tested is reported as inconclusive, never guessed. The `enabled` toggle is the only thing the health check may edit, and only with confirmation.\n9. **Flag distribution patterns, never accuse.** The mass-posting signal (Step 2.5) describes how a listing is being distributed, not a claim that the employer is a scam. Never name a company as fraudulent or untrustworthy - present the observation and let the user decide.\n",{"name":5,"description":24,"allowed-tools":25},"Finds new job postings matching your profile via installed portal-search CLIs (LinkedIn, local job boards, and any skills added with \u002Fadd-portal). Deduplicates across runs. Triggers on: job scrape, find jobs, search jobs, new jobs, job search, scrape jobs, \u002Fscrape\n","Read, Write, Edit, Glob, Grep, Bash(bun --version), Bash(bun run .agents\u002Fskills\u002F*\u002Fcli\u002Fsrc\u002Fcli.ts *), WebFetch, WebSearch, Agent, AskUserQuestion","master","add88976e52b214ae7ae74f0c3b1d4da0da7fd4f",".claude\u002Fskills\u002Fjob-scraper","https:\u002F\u002Fgithub.com\u002FProject516\u002Fjob-search-opencode","https:\u002F\u002Fgithub.com\u002FProject516","https:\u002F\u002Fproject516.dev","I eat open source, I breathe open source, and I build open source.","2026-07-28 05:37:50",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":46},[36,39,42],{"tool":37,"command":38},"npx","npx skills add Project516\u002Fjob-search-opencode --skill scrape",{"tool":40,"command":41},"bunx","bunx skills add Project516\u002Fjob-search-opencode --skill scrape",{"tool":43,"command":44},"pnpm","pnpm dlx skills add Project516\u002Fjob-search-opencode --skill scrape","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FProject516\u002Fjob-search-opencode\u002Fblob\u002Fmaster\u002F.claude\u002Fskills\u002Fjob-scraper\u002FSKILL.md",true,[48],{"path":49,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":52,"sourceHtmlUrl":53},"search-queries.md","REFERENCE","参考文档",3283,"https:\u002F\u002Fgithub.com\u002FProject516\u002Fjob-search-opencode\u002Fblob\u002Fmaster\u002F.claude\u002Fskills\u002Fjob-scraper\u002Fsearch-queries.md",[55,62,69,76,83,90],{"skillNo":56,"name":57,"nameZh":6,"description":58,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":59,"categories":60,"keywords":61,"publishedAt":19},"01M79RP64VEZ1K63GCCHQ23JZF","upskill","Compares tracked job postings against the candidate profile to identify skill gaps and generate a prioritized learning plan with study resources. Triggers on: \u002Fupskill, upskill, skill gaps, what should I learn, learning plan","https:\u002F\u002Fgithub.com\u002FProject516\u002Fjob-search-opencode\u002Fblob\u002Fmaster\u002F.claude\u002Fskills\u002Fupskill\u002FSKILL.md",[],[],{"skillNo":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"publishedAt":19},"01M79RNW6320JDMAWSSNK7RY4D","job-application-assistant","Assists with job applications: evaluating job postings, tailoring CVs, writing cover letters, and preparing for interviews. Triggers on keywords like: job posting, job application, CV, cover letter, resume, interview prep, job fit, career, application, apply, ansøgning, stilling","https:\u002F\u002Fgithub.com\u002FProject516\u002Fjob-search-opencode\u002Fblob\u002Fmaster\u002F.claude\u002Fskills\u002Fjob-application-assistant\u002FSKILL.md",[],[],{"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":19},"01M79RNPN4AVJWTP3ZCFX2GGNK","linkedin-search","Use this skill whenever the user wants to search for jobs in any location or market, find job listings, or look up a specific job posting — in any country, city, or remotely. Invoke for open positions, vacancies, and hiring across any sector or role (software, data, design, marketing, finance, legal, operations, etc.). The location is always supplied explicitly by the user. Trigger phrases: find a job, job search, search for jobs, job openings, vacancies, hiring, positions open, remote jobs, \"are there any X jobs in \u003Cplace>\", look up this job posting.","https:\u002F\u002Fgithub.com\u002FProject516\u002Fjob-search-opencode\u002Fblob\u002Fmaster\u002F.agents\u002Fskills\u002Flinkedin-search\u002FSKILL.md",[],[],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":19},"01M79RN8MMN387Q31HXGQ7G1DG","jobnet-search","Make sure to use this skill whenever the user mentions anything related to Danish job searching, job listings, job vacancies, employment opportunities in Denmark, or the Danish government job portal — even if they don't mention jobnet.dk explicitly. Also invoke this skill for questions about specific job titles, occupations, employers, or regions in a Danish employment context. This skill covers the official Danish public job portal operated by STAR (Styrelsen for Arbejdsmarked og Rekruttering). Trigger phrases include: danish jobs, danish job search, jobnet, jobnet.dk, find job denmark, danish employment, job i danmark, job på jobnet, offentlige job, stillinger i det offentlige, public sector jobs denmark, government jobs denmark, STAR jobs, job ledige stillinger, ledig stilling, søg job, job opslag, job vacancy denmark, stillingopslag, jobopslag, sygepleje job, ingeniør job, lærer job, pædagog job, it-job denmark, jobs in copenhagen, jobs in aarhus, jobs in odense, deltidsjob, fuldtidsjob, fastansættelse, tidsbegrænset ansættelse, fleksjob, sygeplejerske job, social worker job denmark, occupation search denmark, esco occupation, job deadline, ansøgningsfrist, søg efter job, full time job denmark, part time job denmark.","https:\u002F\u002Fgithub.com\u002FProject516\u002Fjob-search-opencode\u002Fblob\u002Fmaster\u002F.agents\u002Fskills\u002Fjobnet-search\u002FSKILL.md",[],[],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":19},"01M79RMZNHAM10PF4Y31DPH45D","jobindex-search","Make sure to use this skill whenever the user wants to search for jobs in Denmark, find Danish job listings, look up a specific job posting, or asks anything about the Danish job market — even if they don't mention jobindex.dk explicitly. Invoke this skill for questions about open positions, job vacancies, hiring in Denmark, job opportunities in Danish cities or sectors, or when the user wants to find work in Denmark. Also trigger for phrases like \"find me a job\", \"are there any jobs for X in Copenhagen\", or \"what jobs are available in Aarhus\" when the context is Denmark. Trigger phrases include: jobindex, jobsøgning, job i Danmark, ledige stillinger, job opslag, find job, stillingopslag, jobannonce, job vacancy denmark, danish jobs, jobs in denmark, job search denmark, work in denmark, find work denmark, IT jobs denmark, engineer jobs denmark, developer jobs copenhagen, marketing jobs aarhus, jobs aarhus, jobs copenhagen, jobs odense, jobs aalborg, job openings denmark, hiring denmark, job listings denmark, python jobs denmark, grafisk designer job, data engineer job, softwareudvikler job, full stack developer job danmark.","https:\u002F\u002Fgithub.com\u002FProject516\u002Fjob-search-opencode\u002Fblob\u002Fmaster\u002F.agents\u002Fskills\u002Fjobindex-search\u002FSKILL.md",[],[],{"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},"01M79RMMS5F07ZSBZHNFDR7BFQ","jobdanmark-search","Make sure to use this skill whenever the user mentions anything related to Danish job listings, job search in Denmark, finding work in Denmark, or job vacancies on Jobdanmark — even if they don't explicitly mention jobdanmark.dk. Also invoke this skill for questions about specific Danish job categories, municipalities, job types, or salaries in a job-search context. Trigger phrases include: danish jobs, jobs in denmark, find job denmark, job search denmark, danish job listings, jobdanmark, job opslag, find job, jobsøgning, ledige stillinger, stillingsopslag, job i Danmark, fuldtidsjob, deltidsjob, studiejob, praktikplads, elev, fleksjob, IT job denmark, sygeplejersker job, håndværker job, ingeniør job, pædagog job, kontor job, leder job, salg job, hotel job, kirke job, job aarhus, job københavn, job odense, job aalborg, job sjælland, job jylland, job fyn, jobkategorier denmark, ledige job, ansøgningsfrist, søg job, job opslaget, jobopslag, danish vacancies, work in denmark, employment denmark, job denmark, jobs near me denmark, apprentice denmark, internship denmark, part-time denmark, full-time denmark.","https:\u002F\u002Fgithub.com\u002FProject516\u002Fjob-search-opencode\u002Fblob\u002Fmaster\u002F.agents\u002Fskills\u002Fjobdanmark-search\u002FSKILL.md",[],[]]