seekter-run
Run a daily job search and auto-apply session for the candidate in profile/profile.md. Use when the user runs /seekter-run or asks to start applications, search for jobs, run today's scan, or apply to postings.
selfishprimate · 已有静态检查记录
安装与使用
运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。
npx skills add selfishprimate/seekter --skill seekter-run技能说明
name: seekter-run description: Run a daily job search and auto-apply session for the candidate in profile/profile.md. Use when the user runs /seekter-run or asks to start applications, search for jobs, run today's scan, or apply to postings.
/seekter-run — search and auto-apply
A template engine. Everything personal lives in profile/; this file holds only procedure, judgment rules and guardrails.
0. Load context (every run, before anything else)
| File | What it holds | When to read |
|---|---|---|
profile/profile.md | Identity, email, standard answers, salary bands, targets, location rules, blacklist, fact bank, voice | Always, in full, first |
profile/search.json | Queries, regions, geoIds, title filters, boards | Always |
reference/sources/_core.md | Index of the source files, plus the rules that belong to no single source | Always, before Step 1 |
reference/sources/linkedin.md · freehire.md | Steps 1-4: the two sources that run every time | Always, before Step 1 |
reference/sources/<board>.md | One file per board | Only for the boards in play this run (profile/search.json) |
reference/ats/_core.md | Universal form rules, the URL-to-vendor table, and what makes a hand-off | Before the first form of the run |
reference/ats/<vendor>.md | One file per application system | Before filling each form, for that form's vendor only |
Placeholders in the reference docs (<FIRST_NAME>, <EMAIL>, <PHONE_LOCAL>, <CV_NAME>, PROFILE_QUERIES, PROFILE_REGIONS, PROFILE_HOME_COUNTRY…) resolve from the profile.
If profile/profile.md is missing or still contains {{, stop and run /seekter-init.
Then:
python3 scripts/seekter.py statsto see the tracker's size. Dedup ispython3 scripts/seekter.py check <url> --company <name>: exit code 1 = already tracked.- Open a task list in this order: the five source steps below, then "Filter and rank", then "Apply", then "Log to tracker" and "Report". Applying is one task at the end, not something interleaved with the sweeping, for the reason in §1.
- Load the Claude in Chrome tools in one ToolSearch call; check
tabs_context_mcp. Without the extension, only step 1 and the API parts of step 5 can run: say so.
1. Source order: mandatory, all five, every run
Alerts, notifications and searches are separate channels. None is a backup for another. Measured twice, in both directions: one day's notification page had 24 jobs, 13 of which never appeared in that day's 9 searches; and on 22 Sept the 16 searches returned 55 title-matched postings of which 53 had not appeared in that day's notification harvest, an overlap of 2. On 23 Sept the same 16 searches returned 59 title-matched postings and the overlap with that day's 65 notification IDs was zero. Dropping step 3 drops almost the whole day.
Harvest all five before filling a single form. Steps 1 to 5 are cheap; forms are not. A run that fills a form in step 1 and triages step 2 in detail will run out of room before step 3, and the step that gets lost is the one carrying most of the day's new postings. Sweep every source, dedup and filter to a candidate list, then start applying in the §3 priority order. If the session ends early the report still shows a complete picture of the market, and the queue survives into the next run.
| # | Step | Method in reference/sources/ |
|---|---|---|
| 1 | freehire API sweep (+ Jobicy) | python3 scripts/freehire_sweep.py, then --detail <n> per candidate |
| 2 | LinkedIn job-alert notifications | Harvest originToLandingJobPostings IDs → Voyager detail |
| 3 | LinkedIn searches (every row of linkedin.searches in profile/search.json, unquoted, relevance order, never sortBy DD) | Voyager REST search, max 3 per JS call |
| 4 | LinkedIn tracker (saved + drafts) | jobs-tracker/?stage=draft, "Continue" on the job page |
| 5 | Other boards at the cadence in the profile | One file per board in reference/sources/ |
Rules:
- Unquoted keywords always. Quotes kill recall in both search and alerts. Search wide, filter by title and description.
- Relevance order, never date order.
sortBy=DD/sortBy:List(DD)reorders a loose multi-word query by posting time, and LinkedIn's loose matching means the newest thing matching any word wins. Keep freshness withtimePostedRangeinstead, which is a filter, not an ordering. Measured 23 Sept on one query, one geography, one 3-day window: relevance returned 25 results of which 25 were on-discipline;sortBy DDreturned 25 of which 1 was. The same day's full sweep ran 16 searches under DD and got 342 raw down to 59 title matches, a 17% hit rate, while a single relevance query surfaced 19 design postings that had never been in the tracker at all. This is the same lesson already written down for the freehire API ordering; it was never carried across to LinkedIn. - Exhaust the chain before saying "nothing found". Don't invent new sources to rescue a thin day; sometimes the market is empty.
- The report must end with this table filled in (step, ran?, jobs seen, candidates, applications). A skipped step must be visible without the user asking.
- A skipped source step is a failed run, not a short one. If room is running out, cut the number of applications, never the number of sources.
2. Filter every candidate (in this order)
- Dedup by Job URL / job ID, right before opening each form, not only at run start. Same company + different role is fine; same URL = stop. Repeat for every source added mid-run. LinkedIn's
applyingInfo.appliedis unreliable (undefined);scripts/seekter.py checkis the truth.- Run
checkon the apply URL, not only on the source's own job id. A record is keyed on whichever URL it was first applied through, so a job found on LinkedIn today may be stored under its Ashby/Lever UUID from a board three weeks ago. A bulk grep of source ids
- Run