cover-letter

Solid

Write a tailored, concise cover letter (150-250 words) from a job description and the user's resume, humanized for natural tone.

AI & Automation 67 stars 17 forks Updated yesterday MIT

Install

View on GitHub

Quality Score: 84/100

Stars 20%
61
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
50
License 10%
100
Description 5%
100

Skill Content

# Cover Letter Generator Write a short, tailored cover letter connecting the candidate's resume to a specific role. ## Setup Follow `../_shared/setup.md` to load profile and resume. Then `Read` the resume file at `primaryResumeSourceAbsolutePath` for full context (identity, education, experience, skills, projects, research, awards). ## Step 1: Analyze the JD From the argument, identify: company + what they do, role title and level, key responsibilities, required/preferred qualifications, tech stack and domain, culture cues. ## Step 2: Read Your Last 5 Letters Do not skip. Letters that are individually fine and collectively identical are what reads as AI - not word choice. ```bash curl -fsS -H "authorization: Bearer $JOBPILOT_API_TOKEN" "$JOBPILOT_API/api/cover-letters?page=1&pageSize=5" | jq -r '.items[].id' ``` The list is metadata only, so `GET /api/cover-letters/<id>` each for the body. No history (first letter, or the call fails) → Step 3. Note three things: which experience each one **led** with, every metric phrasing, and each closing sentence. They become the constraints in Step 3. ## Step 3: Select Relevant Experience From the resume, pick the most relevant: 2–3 work experiences, 2–3 projects, research (if AI/ML/CV), education (if relevant to level). **Apply rules 14-16 here**, against Step 2's letters. Rotating the lead is a selection decision - make it before drafting, not by patching a draft that already opened with the usual paragraph. ## Step 4: Wri...

Details

Author
suxrobGM
Repository
suxrobGM/jobpilot
Created
5 months ago
Last Updated
yesterday
Language
TypeScript
License
MIT

Integrates with

Similar Skills

Semantically similar based on skill content — not just same category