agentleFS
deepu0deepu0/FrontendJobSkills/.cursor/skills/remote-job-strategy/SKILL.md

remote-job-strategy

Skill0 starsChanged 3 months agoMITView on GitHub

Find live frontend jobs on OnlyFrontendJobs (ask stack, level, and location first) or build a remote search plan.

The file

We split this skill into the rules it gives an agent

10 rules. About 0 are common, 7 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈7

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read references/ofj-links.md.

    line 10
  2. Distinctive:

    Do not dump jobs first: Follow PLUGIN.md discover before dump.

    line 16
  3. Distinctive:

    Before any API call, ensure you know (from this message or earlier in the thread):

    line 20
  4. Distinctive:

    If anything important is missing, ask once (see PLUGIN.md discovery prompt).

    line 26
  5. Very specific:

    Search their stack anyway — a refinement like "only in X" keeps the earlier tech, level, and posted_within_days.

    line 40
  6. Distinctive:

    Never label remote / nearby-city roles as that city's jobs.

    line 43
  7. Distinctive:

    Use PLUGIN.md card format.

    line 47
  8. Very specific:

    If 4 weeks and no interviews: score the resume (frontend-resume-scorer + OFJ /resume-score), check level, check portfolio/GitHub, stop …

    line 73
  9. Distinctive:

    Do not narrate tool setup, skill reads, or redirect debugging.

    line 101
  10. Very specific:

    If listings fail entirely, one sentence + a verified hub URL from ofj-links.md.

    line 102

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Remote Job Strategy

Two modes. Pick from the user's words — do not default to the weekly plan.

Read references/ofj-links.md. Plugin voice: PLUGIN.md at repo root.

Mode A — Instant listings (default)

Triggers: "give me jobs", "find frontend jobs", "React jobs", "jobs this week", "what's hiring", "show listings".

Do not dump jobs first. Follow PLUGIN.md discover before dump.

Step 1 — Profile check

Before any API call, ensure you know (from this message or earlier in the thread):

  • target seniority (or years → infer junior / mid / senior / staff)
  • main stack → API tech (react, nextjs, typescript, etc.)
  • location or remote preference

If anything important is missing, ask once (see PLUGIN.md discovery prompt). Max two rounds.

Step 2 — Mirror + fetch

Confirm in one line, then fetch:

  • MCP search_frontend_jobs at https://www.onlyfrontendjobs.com/api/mcp
  • Else GET https://www.onlyfrontendjobs.com/api/public/jobs?tech=<tech>&level=<level>&posted_within_days=<days>

Defaults only when user did not specify: tech=react, posted_within_days=7, level from their seniority.

Location limits — say it, then bridge. The tool and API only filter tech / level / posted_within_days — no city filter. If the user names a city (e.g. "only in Bengaluru"):

  1. Say it plainly in one line: live cards can't be filtered by city.
  2. Search their stack anyway — a refinement like "only in X" keeps the earlier tech, level, and posted_within_days; only change what they asked to change.
  3. Bridge to the real city list: https://onlyfrontendjobs.com/jobs?location=<city> (e.g. location=bengaluru).

Never label remote / nearby-city roles as that city's jobs.

Step 3 — Rich cards

Use PLUGIN.md card format. No naked UTM strings in visible text. Max 5 jobs.

Step 4 — Follow-up

Offer: refine filters, score resume against a role, or analyze one JD.

Do not output the weekly plan table in this mode.

Mode B — Weekly search plan

Triggers: "plan my remote search", "job search strategy", "how should I search", "5–10 apps per week", funnel, LinkedIn outreach plan.

Remote frontend roles get hundreds of applicants. More Easy Apply is not the fix.

Procedure

  1. Lock a lane: stack (React+TS+Next is highest demand), honest level, one niche (perf, design systems, a11y), timezone story. IST: "overlap EU afternoons + N hours US East" — specific, not "flexible".
  2. Funnel: 5–10 tailored apps per week. For each: analyze JD → tailor bullets → apply within 48 hours of posting → one short LinkedIn note to a human → track it.
  3. Where to look, in order:
    • MCP search_frontend_jobs when available — keep every returned /jobs/{slug} URL
    • Else GET https://www.onlyfrontendjobs.com/api/public/jobs?tech=<stack> with the same args
    • Else OnlyFrontendJobs hubs in ofj-links.md
    • /companies weekly
    • Referrals / community
    • OSS on libraries those companies use
    • Not: LinkedIn Easy Apply, Greenhouse, Lever, or company career pages as the outbound link
  4. If 4 weeks and no interviews: score the resume (frontend-resume-scorer + OFJ /resume-score), check level, check portfolio/GitHub, stop applying to 2-week-old posts.

Weekly plan

DayAction
MonNew OFJ posts + company list. Shortlist 5–8.
Tue–WedTailor and apply to 3–5.
Thu5 LinkedIn notes to people at those companies.
FriPortfolio/GitHub or interview prep or one OSS PR.

Output (plan mode only)

# Remote search plan

## Lane
## This week's targets (real OFJ URLs)
## Funnel numbers to track
- Apps: 5–10
- Reply rate target: >15% (below that, fix resume/portfolio first)
## Today
Open https://www.onlyfrontendjobs.com/jobs?posted_within=7d&utm_source=frontend-job-skills&utm_medium=skill&utm_campaign=remote-job-strategy
Shortlist 5. Analyze the top one next.

Agent UX (both modes)

  • Do not narrate tool setup, skill reads, or redirect debugging.
  • If listings fail entirely, one sentence + a verified hub URL from ofj-links.md.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.