Install
openclaw skills install @clawjames1/job-applicationCreate tailored application documents from structured profile data
openclaw skills install @clawjames1/job-applicationCreate truthful, role-specific application documents from the bundled structured profile or a profile supplied by the user.
$JOB_APPLICATION_PROFILE_DIR/*.json when configured, otherwise the fictional demonstration data in assets/profile/*.json$JOB_APPLICATION_OUTPUT_DIR when configured, otherwise applications/ in the user's working directoryjob.json shaped like examples/job.jsonassets/templates/Keep real profiles, photographs, generated documents, and application history outside the installed skill directory. ClawHub updates may replace that directory. Resolve bundled resources relative to this skill directory, but honor the two environment variables for private persistent data. Do not assume a username, home directory, workspace layout, messaging channel, or recipient ID.
Create the application folder with python3 scripts/prepare_application.py --slug <yyyy-mm-company-role>. Use the printed absolute path for all following files. Never overwrite an existing application directory unless the user explicitly requests reuse.
Save normalized job details as job.json.
Run scripts/generate_cv_selection.py --job <job.json> --output <cv_selection.json>. Review its deterministic suggestion and adjust only with facts supported by the profile.
Create cover_letter.json and indeed_text.json using the example schemas. Keep claims grounded in selected profile records.
Generate source documents:
python3 scripts/generate_cv.py --selection <cv_selection.json> --output <CV.tex>
python3 scripts/generate_cover_letter.py --content <cover_letter.json> --output <cover_letter.tex>
python3 scripts/generate_plain_text.py --content <indeed_text.json> --output <indeed_text.txt>
If pdflatex is available and PDFs are requested, run the cross-platform renderer:
python3 scripts/render_application.py <application-dir>
On Windows, py -3 can be used instead of python3. Linux and macOS users may alternatively use the scripts/render_application.sh wrapper.
Return the generated paths. Deliver files externally only after destination-specific approval.
Installation requirements and platform-specific commands are documented in README.md. Generated sample PDFs using only fictional data are in examples/generated/.
organization, context, and context_label) so generated CVs can distinguish employer projects from work performed through the candidate's own company.profile_picture; the bundled photo is fictional demonstration material.JSON contains content, Python performs deterministic transformation, and LaTeX handles layout. Do not hand-edit generated LaTeX when the source JSON can be corrected instead.