Auto Job Applier Skill

This skill connects to the user's resumex.dev account, reads their resume data, matches them to relevant jobs via web search, presents an approval list, then automatically applies to approved jobs using browser automation — filling forms, answering screening questions, and submitting applications. All applications are logged to the resumex.dev job tracker.

Architecture: ResumeX stores resume data and the job tracker. OpenClaw's built-in AI does all the thinking and text generation (cover letters, screening answers, scoring). Web search finds jobs. Browser tool fills and submits applications.

user_preferences.json

remembers extra info between sessions.

No third-party AI API keys required. This skill uses only OpenClaw's built-in LLM for all AI tasks (cover letter drafting, screening question answers, job scoring). The only external API key needed is

RESUMEX_API_KEY

.

Required Environment Variable

RESUMEX_API_KEY

JOB_SEARCH_LOCATION

JOB_TYPE

full-time

part-time

contract

internship

REMOTE_ONLY

true

false

false

MAX_APPLICATIONS

5

How to set

RESUMEX_API_KEY

1. Go to resumex.dev → Dashboard → Resumex API
2. Click Generate API Key
3. In OpenClaw, go to Settings → Environment Variables
4. Add

   RESUMEX_API_KEY

   with the copied key value

No other keys are needed. There is no Anthropic key, no OpenAI key, no other third-party service.

Privacy & Data Handling

Read this before using the skill.

What data leaves your device

Data sent to resumex.dev is governed by the resumex.dev Privacy Policy.

What stays local on your device

data/user_preferences.json

⚠️

user_preferences.json

may contain sensitive personal data including date of birth, gender, ethnicity, veteran status, and disability status (only if you choose to save these when prompted during a form fill). This file is stored locally only and is never sent to resumex.dev or any other server. Review and restrict its filesystem permissions if needed:

chmod 600 data/user_preferences.json

To clear all saved preferences at any time:

python3 scripts/manage_preferences.py reset

Sensitive fields in preferences

The following fields are only saved if you explicitly provide them when the agent encounters a form field that requires them. You can decline to answer, skip the field, or delete a saved value at any time:

• gender

  — only for diversity/EEO forms

• ethnicity

  — only for diversity/EEO forms (optional, you may leave blank)

• veteran_status

  — only for U.S. government/contractor compliance forms

• disability_status

  — only for compliance forms (optional)

• date_of_birth

  — only for forms that legally require it

The agent will always tell you which form requires a sensitive field before asking for the value.

Auto-submit safeguard

The agent NEVER submits an application without your explicit approval. Step 6 of the workflow always presents a formatted approval list and waits for your response before any browser interaction begins. If you are testing, set

MAX_APPLICATIONS=1

Workflow Overview

1. Fetch resume data from resumex.dev API
2. Load saved user preferences (salary, visa, screening answers)
3. Build a job-match profile (skills, roles, seniority, preferences)
4. Search the web for matching jobs (3–5 query permutations)
5. Score & rank each job against the resume (0–100)
6. ⛔ APPROVAL GATE — Present formatted list → wait for user selection
7. For each approved job:
   a. Generate a tailored cover letter (via OpenClaw's built-in AI)
   b. Navigate to application page via browser
   c. Fill form fields using resume data + preferences
   d. If a required field is unknown → ask the user → save to preferences
   e. Submit the application
   f. Log to resumex.dev job tracker
8. Present final summary with statuses

Step 1 — Fetch Resume from resumex.dev

Use the agent endpoint. All calls require

Authorization: Bearer $RESUMEX_API_KEY

# Fetch full resume data (GET /api/v1/agent — the correct endpoint)
curl -s -X GET "https://resumex.dev/api/v1/agent" \
  -H "Authorization: Bearer $RESUMEX_API_KEY" \
  -H "Content-Type: application/json"

Note: The endpoint is

/api/v1/agent

(NOT

/api/v1/agent/resume

, which is deprecated). The helper scripts handle retries with exponential backoff automatically. Install dependencies first:

pip3 install -r requirements.txt

Or via the helper script:

# Full resume JSON
python3 scripts/fetch_resume.py

# Extract a specific field for form filling
python3 scripts/fetch_resume.py --field email
python3 scripts/fetch_resume.py --json-path profile.phone

Expected response shape:

{
  "success": true,
  "data": {
    "activeResumeId": "...",
    "resumes": [{
      "id": "...",
      "data": {
        "profile": {
          "fullName": "...", "email": "...", "phone": "...",
          "location": "...", "summary": "...",
          "linkedin": "...", "github": "...", "website": "..."
        },
        "skills": [{"category": "...", "skills": ["...", "..."]}],
        "experience": [
          {
            "role": "...", "company": "...", "location": "...",
            "startDate": "...", "endDate": "...", "description": "..."
          }
        ],
        "education": [{"degree": "...", "institution": "...", "endDate": "...", "score": "..."}],
        "projects": [{"name": "...", "description": "...", "tags": ["..."]}],
        "achievements": [{"title": "...", "year": "..."}]
      }
    }]
  }
}

Parse the active resume:

workspace = response.data
activeResume = workspace.resumes.find(r => r.id === workspace.activeResumeId)
resumeData = activeResume.data

Error handling:

401

RESUMEX_API_KEY

404

429

Step 2 — Load Saved User Preferences

Check for previously saved preferences that supplement the resume data:

python3 scripts/manage_preferences.py list

This returns any saved answers like salary expectation, visa status, notice period, etc. If

user_preferences.json

Preference fields to look for:

• salary_expectation

  — e.g. "8-12 LPA" or "$80,000-$100,000"

• currency

  — e.g. "INR" or "USD"

• notice_period

  — e.g. "30 days" or "Immediate"

• visa_status

  — e.g. "No visa required (Indian citizen)"

• work_authorization

  — e.g. "Authorized to work in India"

• willing_to_relocate

  — true/false

• preferred_work_type

  — "remote" | "hybrid" | "onsite"

• screening_answers

  — dict of previously answered screening questions

Step 3 — Build Job-Match Profile

From the resume JSON and user preferences, extract and infer:

experience[0].role

skills[].skills

experience[].description

startDate

profile.location

JOB_SEARCH_LOCATION

JOB_TYPE

preferred_work_type

REMOTE_ONLY

Example derived profile:

Roles: Software Engineer, Backend Developer, Full Stack Developer
Skills: Python, Django, React, PostgreSQL, Docker, AWS
Seniority: Mid-level (3 years)
Location: Pune, India
Type: Full-time
Remote: No preference
Salary: 8-12 LPA (from preferences)

Step 4 — Search for Matching Jobs

Use web_search to find real, current job postings. Run 3–5 targeted searches using different query permutations to maximize coverage.

Query templates:

"{role}" "{top_skill}" jobs "{location}" site:linkedin.com OR site:naukri.com OR site:indeed.com
"{role}" "{top_skill}" "{second_skill}" hiring 2026
"{role}" remote jobs "{top_skill}" "{seniority}"
"{role}" "{top_skill}" jobs "{location}" "apply now" site:wellfound.com OR site:internshala.com

See

references/job_boards.md

For each search result URL, use web_fetch to extract:

• Job title
• Company name
• Location (or Remote)
• Job URL (apply link)
• Required skills (from description)
• Nice-to-have skills
• Experience required
• Salary range (if visible)
• Application method:

  form

  |

  easy-apply

  |

  email

  |

  redirect

Aim to collect 10–20 raw job postings before scoring.

Step 5 — Score & Rank Jobs

Score each job 0–100 against the resume profile:

Formula:

score = (skills_matched / skills_required) * 40
      + role_title_match * 20    # 20 if exact, 10 if adjacent, 0 if unrelated
      + seniority_match * 15     # 15 if exact, 8 if ±1 level, 0 if 2+ off
      + location_match * 15      # 15 if match, 8 if remote, 0 if mismatch
      + industry_match * 10      # 10 if same industry, 5 if adjacent

Step 6 — Present Approval List to User ⛔

Present the top 10 matches in a formatted table. The user MUST approve before any applications are submitted. Never auto-apply without explicit approval. Never skip this step.

Format:

🎯 Job Match Results for [Name]
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

#   Score  Company          Role                     Location        Apply Method
──  ─────  ───────          ────                     ────────        ────────────
1   92     Acme Corp        Software Engineer        Pune (On-site)  🤖 Auto-apply
2   87     TechStartup      Backend Developer        Remote          🤖 Auto-apply
3   81     MegaCorp India   Full Stack Engineer      Mumbai          🤖 Auto-apply
4   76     DevShop          Python Developer         Pune (Hybrid)   🤖 Auto-apply
5   73     CloudCo          API Engineer             Remote          🤖 Auto-apply
6   70     DataInc          Backend Engineer         Bangalore       🔗 Manual (LinkedIn)
7   68     StartupXYZ       Software Developer       Remote          🤖 Auto-apply
8   65     BigTech          Junior SWE               Hyderabad       🤖 Auto-apply
9   62     ConsultFirm      Technical Consultant     Pune            📧 Email apply
10  58     SmallCo          Full Stack Developer     Remote          🤖 Auto-apply

🤖 = Agent will fill and submit the application automatically
🔗 = LinkedIn — agent will open the page, you submit manually
📧 = Email — agent will draft the email, you review and send

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

Which jobs would you like to apply to?
Options: "all", "1,3,5", "1-5", "none", or "1-5 except 3"

Apply method classification:

• 🤖 Auto-apply

  — Standard form-based application. Agent fills and submits.

• 🔗 Manual (LinkedIn)

  — LinkedIn Easy Apply. Agent navigates to the page but user must submit. (LinkedIn automated submission is disabled by default due to ToS concerns.)

• 📧 Email apply

  — Agent drafts the application email for user review.

• 🔗 Manual (redirect)

  — Redirects to external ATS. Agent navigates, user may need to complete.

Wait for the user to respond with their selection before proceeding.

Step 7 — Auto-Apply to Approved Jobs

For each job the user approved, execute the following sub-steps:

7a. Generate Cover Letter (via OpenClaw's built-in AI)

No external AI API is used. Cover letters are generated by OpenClaw's own LLM.

The

draft_cover_letter.py

python3 scripts/draft_cover_letter.py \
  --resume /tmp/resume.json \
  --job_title "Software Engineer" \
  --company "Acme Corp" \
  --job_description "We are looking for..." \
  --output /tmp/cover_letter_acme.txt

The script outputs the generation prompt to stdout. The agent then:

1. Reads the prompt
2. Uses its built-in LLM to generate the cover letter text
3. Saves the result to the

   --output

   path if specified

Cover letter structure:

1. Hook (1 sentence): why this specific company/role excites the candidate
2. Match (2–3 sentences): specific skills/experiences that directly map to job requirements
3. Value add (1–2 sentences): a concrete result from their past work
4. Close (1 sentence): call to action

Keep it under 200 words. Professional but human tone.

7b. Navigate to Application Page

Use the browser tool to navigate to the job's application URL:

browser: navigate to "{job_url}"

Wait for the page to load. Take a screenshot to confirm you're on the right page.

7c. Identify Form Fields

Analyze the page to identify the application form. Look for:

• Input fields (

  <input>

  ,

  <textarea>

  ,

  <select>

  )
• Required indicators (

  *

  ,

  required

  attribute)
• Submit buttons
• Multi-step form indicators (next/continue buttons)

See

references/form_field_mappings.md

7d. Fill Form Fields

For each form field, use this priority order to find the value:

1. Resume data (from ResumeX API)           → profile.email, profile.phone, etc.
2. User preferences (from preferences.json) → salary_expectation, visa_status, etc.
3. Derived data (calculated by agent)       → years of experience, full name split, etc.
4. Ask the user (last resort)               → save answer to preferences for reuse

Common field mappings (see

references/form_field_mappings.md

profile.fullName

profile.fullName

profile.email

profile.phone

profile.linkedin

profile.github

profile.website

profile.location

experience[0].company

experience[0].role

startDate

salary_expectation

notice_period

Browser fill commands:

browser: click on the "First Name" input field
browser: type "{first_name}"
browser: click on the "Email" input field
browser: type "{email}"
...
browser: click on the "Cover Letter" textarea
browser: type "{cover_letter_text}"

7e. Handle File Upload Fields

If the form has a resume/CV upload field:

• Do NOT attempt to upload a file automatically.
• Note it in the summary: "⚠️ Resume upload required — please upload manually"
• Fill all other fields and leave the upload for the user.

7f. Handle Unknown Fields — Ask & Remember

If a form field requires information not in the resume or saved preferences:

1. Pause the application (do not skip the field)
2. Ask the user: "The application for [Company] - [Role] requires: [field name]. What should I enter?"
3. Save the answer for future use:

python3 scripts/manage_preferences.py set "[field_key]" "[user_answer]"

4. Fill the field with the user's answer and continue

When asking for sensitive fields (gender, ethnicity, DOB, veteran/disability status), always mention which company's form requires it and that the answer will be saved locally. The user may decline — if so, skip the field or leave it blank if optional.

Don't ask again for the same field type. Once "salary expectation" is saved, use it for all future applications unless the user explicitly changes it.

7g. Handle Screening Questions

Many application forms include screening questions. For each question:

1. Check

   user_preferences.screening_answers

   for a saved answer (fuzzy match on question text)
2. If found → use saved answer
3. If not → present the question to the user with the options available
4. Save the answer to preferences:

python3 scripts/manage_preferences.py set-screening "authorized_to_work" "Yes"

Common screening questions and strategies:

• "Are you authorized to work in [country]?" → check

  visa_status

  /

  work_authorization

• "Do you require sponsorship?" → derive from

  visa_status

• "What is your expected salary?" → use

  salary_expectation

• "What is your notice period?" → use

  notice_period

• "Are you willing to relocate?" → use

  willing_to_relocate

• "Why are you interested in this role?" → generate using OpenClaw's built-in LLM from resume + job description
• "Describe your experience with [X]" → generate using OpenClaw's built-in LLM from resume data

See

references/screening_questions.md

7h. Submit the Application

After all fields are filled:

1. Take a screenshot of the completed form for the user's records
2. Click the submit button
3. Wait for confirmation (success page, confirmation message, or redirect)
4. Take a screenshot of the confirmation
5. If submission fails, note the error and move to the next job

7i. Log to resumex.dev Job Tracker

After submission (or attempted submission), log the application:

python3 scripts/log_application.py \
  --company "Acme Corp" \
  --role "Software Engineer" \
  --url "https://careers.acme.com/apply/12345" \
  --status "applied" \
  --method "auto-applied" \
  --score 92 \
  --notes "Auto-applied via job applier skill."

Use

--dry-run

python3 scripts/log_application.py \
  --company "Test" --role "Test" --url "https://example.com" --dry-run

The script automatically tries multiple endpoints (

/api/v1/agent/jobs

/api/v1/agent/logs

Or via curl:

curl -s -X POST "https://resumex.dev/api/v1/agent/jobs" \
  -H "Authorization: Bearer $RESUMEX_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "company": "Acme Corp",
    "position": "Software Engineer",
    "url": "https://careers.acme.com/apply/12345",
    "status": "applied",
    "appliedDate": "2026-04-14",
    "notes": "Auto-applied via Auto Job Applier skill. Match score: 92/100. Method: auto-applied."
  }'

Step 8 — Present Final Summary

After all approved applications are processed, show a clean summary:

✅ Application Summary for [Name]
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

#  Company          Role                    Score   Status
1  Acme Corp        Software Engineer       92/100  ✅ Applied (auto)
3  MegaCorp India   Full Stack Engineer     81/100  ✅ Applied (auto)
5  CloudCo          API Engineer            73/100  ✅ Applied (auto)

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

📊 Results: 3 applied ✅ | 0 failed ❌ | 0 manual 🔗

📝 Notes:
  • All applications logged to your resumex.dev tracker
  • Cover letters generated using OpenClaw's built-in AI
  • Saved preferences: salary_expectation, notice_period (for future use)

💡 Tip: Re-run this skill weekly for fresh job listings!

If any applications had issues:

⚠️ Issues:
  • CloudCo (API Engineer) — Resume upload required. Open the application and upload manually:
    https://careers.cloudco.com/apply/67890

Error Handling

All HTTP scripts use the shared

http_client.py

Retry-After

401 Unauthorized

RESUMEX_API_KEY

403 Forbidden

404 Not Found

429 Rate Limited

Retry-After

5xx Server Error

Important Rules

1. NEVER auto-apply without user approval. Always present the approval list (Step 6) first.
2. Always fetch fresh resume data at the start of each session. Don't cache across sessions.
3. Cache within a session — fetch the resume once when the skill starts, reuse for all applications.
4. Save every unknown field to preferences — the user should never be asked the same question twice.
5. LinkedIn jobs are manual-only by default. Don't attempt LinkedIn Easy Apply unless the user explicitly requests it (ToS risk).
6. Skip file upload fields — note them for the user to complete manually.
7. Take screenshots before and after form submission for the user's records.
8. Handle CAPTCHAs gracefully — if detected, mark the job as "manual apply" and move on.
9. Rate limits — resumex.dev API has rate limits. Don't call the resume endpoint more than once per session.
10. No external AI APIs — cover letters and text generation use OpenClaw's built-in LLM only.
11. Privacy — resume data is fetched live from resumex.dev. Saved preferences are stored locally only in

    data/user_preferences.json

    and never transmitted to any server.
12. Sensitive fields — always inform the user before saving sensitive data (gender, DOB, ethnicity, etc.) and allow them to decline.

Files in This Skill

SKILL.md

scripts/http_client.py

scripts/fetch_resume.py

--field

scripts/search_jobs.py

scripts/fill_application.py

scripts/manage_preferences.py

user_preferences.json

scripts/draft_cover_letter.py

scripts/log_application.py

--dry-run

requirements.txt

requests>=2.28.0

references/job_boards.md

references/form_field_mappings.md

references/screening_questions.md

data/user_preferences.json