Agent skill

cv-tailor

ATS-focused CV tailoring workflow from job URL/text/image to bullet-point output and optional Google Drive upload.

Stars 163
Forks 31

Install this agent skill to your Project

npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/other/other/cv-tailor

Metadata

Additional technical details for this skill

openclaw
{
    "os": [
        "darwin",
        "linux"
    ],
    "emoji": "\ud83e\udde0",
    "requires": {
        "bins": [
            "node",
            "gog"
        ]
    }
}

SKILL.md

CV Tailor

Use this skill when the user asks to tailor a CV for a specific role, using:

  • Job posting URL
  • Copied JD text
  • Screenshot/photo of JD text (OCR/vision-capable flow)

Inputs accepted from Telegram

  1. Job URL
  2. JD pasted text
  3. JD image/capture

If image text cannot be read reliably, ask user for pasted text fallback.

Built-in resources

  • file_skill.ts: safe read/write/list helper rooted at ~/openclaw_pro
  • prompts/ATS_ALIGNMENT_ENGINE.md
  • prompts/IMPACT_REFRAMING_ENGINE.md
  • scripts/export_bullets_to_drive.sh
  • scripts/cv_model_mode.sh

Standard runbook

  1. Enter CV high-quality model mode (required):
    • bash scripts/cv_model_mode.sh start
  2. Parse JD from URL/text/image.
  3. Run ATS alignment analysis (keyword gaps, bullet rewrites, skills list).
  4. Run impact reframing (summary + before/after impact bullets).
  5. Read master_cv.md and tailor truthfully.
  6. Save full version to cv/CV_[Company]_[Role].md.
  7. Produce bullet-only version for copy/paste.
  8. Upload bullet file to Google Drive (optional):
    • bash scripts/export_bullets_to_drive.sh "$HOME/openclaw_pro/cv/CV_[Company]_[Role].md"
  9. Report saved local path + Drive file link/id.
  10. Exit CV high-quality model mode (required, always run even on failure):
    • bash scripts/cv_model_mode.sh end

Safety constraints

  • Never fabricate experience, projects, skills, or credentials.
  • Keep claims grounded in user-provided CV/history only.
  • For unknown metrics, request estimate or use qualitative impact.

Quality mode (CV-only)

  • CV tasks must use google/gemini-2.5-pro while the task is running.
  • Normal tasks should remain on stable default (google/gemini-2.5-flash).
  • If provider outage/rate-limit forces fallback, explicitly report fallback in response.

Expand your agent's capabilities with these related and highly-rated skills.

Didn't find tool you were looking for?

Be as detailed as possible for better results