agentleFS
MuvonMuvon/octomind-tap/skills/cover-letter/SKILL.md

cover-letter

Skill6 starsChanged 8 months agoApache-2.0View on GitHub

Write a truthful cover letter tailored to the posting and grounded in the candidate's real experience, without AI-template phrasing. Use when applying.

33 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use interview-prep, tailor-resume and 7 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • AnthropicSkill

    interview-prep

    Create structured interview plans with competency-based questions and scorecards. Trigger with "interview plan for", "interview questions for", "how should we interview", "scorecard for", or when the user is preparing to interview candidates.

    Also in 7 projects that use this

  • proficientlyjobsSkill

    tailor-resume

    Tailor your resume for a specific job posting

    Also in 4 projects that use this

  • proficientlyjobsSkill

    job-search

    Search for jobs matching my resume and preferences

    Also in 4 projects that use this

  • aslavchevSkill

    mock-interview

    Simulate a real job interview for any role. Use when user says "mock interview", "interview me", "interview prep", "practice interview", or wants to rehearse for a specific company or position. Adapts rounds and questions to the role — technical, managerial, creative, or any other.

    Also in 3 projects that use this

  • JDerekLomasSkill

    literature-review

    Conduct comprehensive, systematic literature reviews using multiple academic databases (PubMed, arXiv, bioRxiv, Semantic Scholar, etc.). This skill should be used when conducting systematic literature reviews, meta-analyses, research synthesis, or comprehensive literature searches across biomedical, scientific, and technical domains. Creates professionally formatted markdown documents and PDFs with verified citations in multiple citation styles (APA, Nature, Vancouver, etc.).

    Also in 3 projects that use this

  • VercelSkill

    setup

    Set up Vercel CLI and project configuration. Use when the user says "set up Vercel", "configure Vercel", "link to Vercel", or "vercel init".

    Also in 5 projects that use this

  • +1 more from proficientlyjobs

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 29 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Every claim traces to the candidate's actual background.

    line 21
  2. Distinctive:

    If the candidate is missing a stated requirement, do not paper over it with bravado.

    line 48

“Common” is measured: kept by at least 6 in 10 of the 29 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Overview

A cover letter's job is to connect the candidate's real, specific experience to this specific role and company in a way a busy hiring manager grasps in a skim. Most cover letters fail by being generic — interchangeable praise that could be sent to any company — or by restating the resume. This skill encodes how to write one that earns its read.

Every claim traces to the candidate's actual background. A cover letter that invents enthusiasm, achievements, or fit is worse than none.

Mental model

Generative AI made fluent, well-aligned letters free, so fluency no longer signals anything. On a large online labour platform, after an AI cover-letter tool launched, the link between letter-to-job alignment and callbacks fell by about half and employers shifted weight to work history; time spent editing the AI draft still predicted hiring (Cui, Dias & Ye, 2025). What still carries signal is what a generic draft can't produce: verifiable specifics about this candidate and this company.

Instructions

What a good cover letter does

  • Opens with a specific hook — a real reason this candidate fits this role, or a genuine connection to the company's work — not "I am writing to apply for the position of…".
  • Proves fit with 2–3 concrete, quantified achievements from the candidate's real experience that map to the posting's top requirements, framed as "here is the problem I solved" not "I have skill X".
  • Shows it is for THIS company: reference something specific and true — the product, a stated challenge, the team's domain — that could not be copy-pasted to a competitor.
  • Closes with a confident, low-pressure call to action.

Structure

  • Length: 3–4 short paragraphs, roughly 250–400 words, one page maximum. Hiring managers skim; density loses them.
  • Hook paragraph: the specific fit or connection.
  • Body (1–2 paragraphs): the mapped achievements, each tied to a posting requirement.
  • Close: enthusiasm that is specific, plus the call to action.
  • Salutation: a named person when discoverable; a role-specific greeting ("Dear Hiring Team for the X role") over "To Whom It May Concern".

Grounding and honesty

  • Pull every achievement, number, and skill from the candidate's resume or their confirmed input. No invented projects, metrics, or motivations.
  • The enthusiasm must be real and specific — a fabricated "I've always admired your mission" reads as filler. If there is no genuine specific hook, use a truthful competence-based one instead.
  • If the candidate is missing a stated requirement, do not paper over it with bravado. Lead with genuine strengths; a stretch application can acknowledge the gap briefly and pivot to adjacent, real experience.

Avoid the AI-template tells

Generic cover letters read as mass-produced. Apply content-voice's rules: no dead phrases ("I am excited to apply", "proven track record", "team player", "hit the ground running", "align with your values"), vary sentence rhythm, use contractions, sound like a specific person. Strip anything that could belong in any other candidate's letter to any other company. If a sentence survives find-and-replace of the company name into a competitor's, it is too generic — rewrite it.

Locale

Match the target market: the letter language follows the posting, formality follows the market (more formal in DE/FR/JP, warmer and more direct in the US), and the greeting/sign-off use local convention. Hand non-English letters to the localization path for native fluency.

When the letter is optional

If the posting marks it optional or the form has no field, a short letter (or a 3–4 sentence note in the application's message box) is still worth sending for a role the candidate really wants or a career change that the resume alone doesn't explain. Skip it for high-volume, knockout-driven applications rather than send a generic one.

Examples

Generic open (discard pile): "I am writing to express my strong interest in the Senior Engineer position at your company. I am a passionate team player with a proven track record."

Specific open (grounded, human): "I spent the last two years cutting a data pipeline's cost by 60% at 3B events/day — which is the exact scaling problem your engineering blog described last month. That's why the Senior Data Engineer role caught my eye."

Checklist

  • Every achievement, number, and skill traces to the resume or the candidate's confirmed input.
  • The hook names something specific and true about this company or role.
  • 2–3 achievements, each mapped to a top posting requirement.
  • Swap the company name for a competitor's: if a sentence still works, it's rewritten.
  • No template phrases; 250–400 words; local greeting and formality.

References

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.