# Send Openclaw Skill Work Application to your agent
Use the source page and any available docs to guide the install because the item currently does not return a direct package file.
## Fast path
- Open the source page via Open source listing.
- If you can obtain the package, extract it into a folder your agent can access.
- Paste one of the prompts below and point your agent at the source page and extracted files.
## Suggested prompts
### New install

```text
I tried to install a skill package from Yavira, but the item currently does not return a direct package file. Inspect the source page and any extracted docs, then tell me what you can confirm and any manual steps still required. Then review README.md for any prerequisites, environment setup, or post-install checks.
```
### Upgrade existing

```text
I tried to upgrade a skill package from Yavira, but the item currently does not return a direct package file. Compare the source page and any extracted docs with my current installation, then summarize what changed and what manual follow-up I still need. Then review README.md for any prerequisites, environment setup, or post-install checks.
```
## Machine-readable fields
```json
{
  "schemaVersion": "1.0",
  "item": {
    "slug": "work-application",
    "name": "Openclaw Skill Work Application",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/Romain-Grosos/work-application",
    "canonicalUrl": "https://clawhub.ai/Romain-Grosos/work-application",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadUrl": "/downloads/work-application",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=work-application",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "packageFormat": "ZIP package",
    "primaryDoc": "SKILL.md",
    "includedAssets": [
      "README.md",
      "SKILL.md",
      "config.example.json",
      "references/api.md",
      "references/troubleshooting.md",
      "scripts/_analyzer.py"
    ],
    "downloadMode": "manual_only",
    "sourceHealth": {
      "source": "tencent",
      "slug": "work-application",
      "status": "source_issue",
      "reason": "not_found",
      "recommendedAction": "review_source",
      "checkedAt": "2026-05-06T16:33:45.513Z",
      "expiresAt": "2026-05-07T16:33:45.513Z",
      "httpStatus": 404,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=work-application",
      "contentType": "text/plain",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=work-application",
        "contentDisposition": null,
        "redirectLocation": null,
        "bodySnippet": null,
        "slug": "work-application"
      },
      "scope": "item",
      "summary": "Known item issue.",
      "detail": "This item's current download entry is known to bounce back to a listing or homepage instead of returning a package file.",
      "primaryActionLabel": "Open source listing",
      "primaryActionHref": "https://clawhub.ai/Romain-Grosos/work-application"
    },
    "validation": {
      "installChecklist": [
        "Open the source listing and confirm there is a real package or setup artifact available.",
        "Review SKILL.md before asking your agent to continue.",
        "Treat this source as manual setup until the upstream download flow is fixed."
      ],
      "postInstallChecks": [
        "Confirm the extracted package includes the expected docs or setup files.",
        "Validate the skill or prompts are available in your target agent workspace.",
        "Capture any manual follow-up steps the agent could not complete."
      ]
    }
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/work-application",
    "downloadUrl": "https://openagent3.xyz/downloads/work-application",
    "agentUrl": "https://openagent3.xyz/skills/work-application/agent",
    "manifestUrl": "https://openagent3.xyz/skills/work-application/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/work-application/agent.md"
  }
}
```
## Documentation

### Work Application Skill

Job search automation with CV generation, scraping, analysis, and tracking. 4 HTML CV templates (classic, modern-sidebar, two-column, creative), job scraping across 5 French platforms (Free-Work, WTTJ, Apec, HelloWork, LeHibou), keyword-based scoring, deep page analysis, full multi-dimension report (skills/company/location/salary with market data), and candidature tracking via markdown table. Stdlib only (except Playwright for scraping/analysis). Supports local and Nextcloud storage.

Profiles: ~/.openclaw/data/work-application/ · Config: ~/.openclaw/config/work-application/config.json

### Trigger phrases

Load this skill when the user says anything like:

"generate my CV", "create a resume", "render my CV"
"adapt my CV for this job offer", "tailor my resume"
"scrape job offers", "find jobs", "search for devops positions"
"analyze job offers", "rank these jobs", "score job matches"
"deep analyze these jobs", "scrape and analyze job pages"
"analyze this job offer", "generate a report for this URL", "report on this job"
"track this application", "log candidature", "update application status"
"list my applications", "show candidatures"
"validate my CV", "check CV formatting"
"show my profile", "what's in my master profile"

### Quick Start

python3 scripts/work_application.py profile show
python3 scripts/work_application.py render --template classic --output cv.html
python3 scripts/work_application.py report "https://example.com/job-offer"
python3 scripts/work_application.py track list

### Setup

python3 scripts/setup.py       # interactive: profile + permissions + scraper config
python3 scripts/init.py        # validate configuration

config.json - behavior restrictions (all destructive capabilities disabled by default):

KeyDefaultEffectallow_writefalseallow modifying master profileallow_exporttrueallow generating HTML/PDFallow_scrapefalseallow running job scraper + network requests (requires Playwright)allow_trackingtrueallow logging candidaturesdefault_template"classic"CV template when not specifieddefault_color"#2563eb"accent colordefault_lang"fr"language (fr/en)report_mode"analysis"report output: analysis or cv+analysisreadonly_modefalseoverride: block all writes regardless of above

### Storage & data

PathWritten byPurpose~/.openclaw/config/work-application/config.jsonsetup.pyPermissions and defaults. No secrets.~/.openclaw/data/work-application/profile-master.jsonsetup.pyComplete master profile (all experiences, skills, etc.)~/.openclaw/data/work-application/profile.jsonAgentAdapted profile for current job offer~/.openclaw/data/work-application/candidatures.mdAgentApplication tracking table~/.openclaw/data/work-application/jobs/jobs-found.mdScraperRaw scraped job offers~/.openclaw/data/work-application/jobs/jobs-ranked.mdAnalyzerScored and ranked offers~/.openclaw/data/work-application/jobs/jobs-selected.mdAnalyzerTop selection (CDI + Freelance)~/.openclaw/data/work-application/market-data.jsonReportMarket salary references (auto-generated, editable)~/.openclaw/data/work-application/reports/report-*.mdReportFull analysis reports (markdown)~/.openclaw/data/work-application/reports/report-*.jsonReportFull analysis reports (JSON)

Nextcloud storage (optional): when storage.backend = "nextcloud" is set in config, files are stored on the user's Nextcloud instance instead of locally. Authentication is delegated entirely to the openclaw-skill-nextcloud skill - this skill never handles Nextcloud credentials. The nextcloud skill must be installed separately.

Cleanup: python3 scripts/setup.py --cleanup

Uninstall: rm -rf ~/.openclaw/data/work-application/ ~/.openclaw/config/work-application/

### Capability isolation

All capabilities are disabled or restricted by default. The agent cannot perform actions until explicitly enabled in config.json:

CapabilityDefaultWhat it gatesallow_writefalseModify master profileallow_exporttrueGenerate HTML/PDF outputallow_scrapefalseRun Playwright browser, make network requestsallow_trackingtrueAppend to candidature logreadonly_modefalseMaster kill-switch - blocks all writes

### Credential isolation

This skill stores no secrets and requires no environment variables. config.json contains only behavioral flags and defaults - never credentials.

Local storage (default): reads/writes files under ~/.openclaw/data/work-application/. No authentication needed.
Nextcloud storage (optional): delegates all authentication to the openclaw-skill-nextcloud skill, which manages its own credentials (NC_URL, NC_USER, NC_APP_KEY in ~/.openclaw/secrets/nc_creds). This skill never reads, stores, or handles Nextcloud credentials directly - it imports NextcloudClient from the nextcloud skill at runtime. The nextcloud skill must be installed and configured separately (clawhub install nextcloud-files).
Scraping (optional, allow_scrape=true): Playwright runs without authentication. Job pages are fetched as anonymous HTTP requests. Company review scraping (Glassdoor/Indeed) also runs unauthenticated - no login or API key is used.

### Path traversal protection

All storage operations (local and Nextcloud) validate filenames through _validate_name():

Rejects absolute paths (/etc/passwd, C:\\...)
Rejects traversal sequences (../, ..\\\\, bare ..)
Rejects null bytes (\\x00)
Normalizes slashes and collapses redundant separators
LocalStorage additionally resolves the final path and verifies it remains inside the storage root directory

### HTML output safety

All profile fields are passed through html.escape() before HTML rendering. No raw user content is inserted into templates. This prevents XSS if the generated CV is served or shared.

### Network boundaries

No network calls by default - CV generation, analysis, tracking are fully offline
Network calls only happen when allow_scrape=true, exclusively via Playwright (headless Chromium)
Domains contacted when scraping: free-work.com, welcometothejungle.com, apec.fr, hellowork.com, lehibou.com (job platforms), plus the specific job offer URL provided by the user
Domains contacted by report (optional, allow_scrape=true): glassdoor.fr, fr.indeed.com (company reviews - unauthenticated, anonymous)
Nextcloud storage (optional): contacts the user's own Nextcloud instance via the nextcloud skill - no third-party server
URLs built from user data (company names for review lookup) are properly URL-encoded
No background network activity, no telemetry, no phone-home

### File output safety

Reports and CVs are written only to the configured storage directory (~/.openclaw/data/work-application/ or Nextcloud remote path)
Filenames derived from user data (company names) are strictly sanitized to ASCII alphanumeric + hyphens
Subdirectories (reports/, jobs/) are created inside the storage root only

### Module usage

from scripts._profile import load_master_profile, load_adapted_profile, save_adapted_profile
from scripts._cv_renderer import render_cv
from scripts._validators import validate_profile
from scripts._tracker import log_application, list_applications, update_status
from scripts._report import generate_report, format_report_markdown, save_report

### CLI reference

# Profile
python3 scripts/work_application.py profile show
python3 scripts/work_application.py profile validate

# CV Rendering
python3 scripts/work_application.py render --template classic --output cv.html
python3 scripts/work_application.py render --template modern-sidebar --color "#e63946" --lang en

# Job Scraping
python3 scripts/work_application.py scrape
python3 scripts/work_application.py scrape --platforms free-work,wttj

# Job Analysis
python3 scripts/work_application.py analyze

# Deep Analysis (scrape job pages for detailed matching)
python3 scripts/work_application.py deep-analyze
python3 scripts/work_application.py deep-analyze --max 10

# Report (full multi-dimension analysis of a single offer)
python3 scripts/work_application.py report "https://example.com/job-offer"

# Application Tracking
python3 scripts/work_application.py track list
python3 scripts/work_application.py track list --status en_attente
python3 scripts/work_application.py track add "Thales" "DevOps Engineer" --location Paris --salary "55-65k"
python3 scripts/work_application.py track update "Thales" entretien

# Config
python3 scripts/work_application.py config

### Adapt CV for a job offer

from scripts._profile import load_master_profile, save_adapted_profile
from scripts._cv_renderer import render_cv
from scripts._validators import validate_profile

# 1. Load master profile
master = load_master_profile()
# 2. Agent adapts profile for the job (select relevant skills, rewrite summary, etc.)
adapted = adapt_for_job(master, job_description)  # agent logic
# 3. Validate
report = validate_profile(adapted)
if not report["valid"]:
    print("Errors:", report["errors"])
# 4. Save and render
save_adapted_profile(adapted)
html = render_cv(adapted, template="classic", color="#2563eb")

### Scrape → Analyze → Track

# 1. Scrape jobs
from scripts._scraper import JobScraper, filter_jobs, deduplicate
scraper = JobScraper(config)
jobs = asyncio.run(scraper.scrape_all())
jobs = deduplicate(filter_jobs(jobs, config["scraper"]["filters"]))

# 2. Analyze
from scripts._analyzer import rank_jobs, select_top
ranked = rank_jobs(jobs, master_profile)
selected = select_top(ranked)

# 3. Track top matches
from scripts._tracker import log_application
for job in selected["cdi"][:5]:
    log_application(job["company"], job["title"], location=job.get("location",""))

### Quick candidature update

from scripts._tracker import update_status, list_applications
update_status("Thales", "entretien")
active = list_applications(status="en_attente")

### CV Templates

TemplateDescriptionBest forclassicSingle-column, ATS-optimizedMost applications, ATS systemsmodern-sidebarSidebar (35%) + main (65%)Tech companies, startupstwo-columnTwo-column grid (38/62)Creative roles, design-awarecreativeTimeline, gradient headerPersonal branding, portfolios

### Status icons

StatusIconMeaningen_attente⏳Waiting for responseentretien📞Interview schedulednegociation🤝In negotiationoffre✅Offer receivedrefus❌Rejecteddesistement🚫Withdrawn

### Scraper platforms

PlatformURLTypesNotesFree-Workfree-work.comFreelanceTJM parsing, remote detectionWTTJwelcometothejungle.comCDISalary ranges, company pagesApecapec.frCDI/CadreExecutive positionsHelloWorkhellowork.comCDIBroad coverageLeHiboulehibou.comFreelanceIT freelance missions

### Ideas

Set allow_scrape: false + allow_export: true for a CV-only mode
Use scraper with allow_tracking: true to auto-log the best matches
Adapt CV per job offer, validate, render, then log the application
Use readonly_mode: true for a safe demo mode

### Notes

Playwright dependency: Only needed for scraping. CV generation is stdlib only.
Profile structure: Master profile contains ALL data. Adapted profile is a filtered subset for a specific job.
Validators: Port of the JavaScript validators - same limits and thresholds.
i18n: CV rendering supports French and English section headings.
Print-ready: Generated HTML includes @media print rules and A4 page breaks.

### Combine with

SkillWorkflowghostGenerate CV → publish as Ghost pagenextcloudSave rendered CV to NextcloudgmailSend CV as email attachmentveilleMonitor job market trends → adapt search queries

### API reference

See references/api.md for CLI command details and profile schema.

### Troubleshooting

See references/troubleshooting.md for common errors and fixes.
## Trust
- Source: tencent
- Verification: Indexed source record
- Publisher: Romain-Grosos
- Version: 1.0.10
## Source health
- Status: source_issue
- Known item issue.
- This item's current download entry is known to bounce back to a listing or homepage instead of returning a package file.
- Health scope: item
- Reason: not_found
- Checked at: 2026-05-06T16:33:45.513Z
- Expires at: 2026-05-07T16:33:45.513Z
- Recommended action: Open source listing
## Links
- [Detail page](https://openagent3.xyz/skills/work-application)
- [Send to Agent page](https://openagent3.xyz/skills/work-application/agent)
- [JSON manifest](https://openagent3.xyz/skills/work-application/agent.json)
- [Markdown brief](https://openagent3.xyz/skills/work-application/agent.md)
- [Download page](https://openagent3.xyz/downloads/work-application)