agentleFS
AxectAxect/skills/cover-letter/SKILL.md

cover-letter

Skill4 starsChanged 20 days agoMITView on GitHub

Write, diagnose, and tailor academic cover letters for postdoc, fellowship, and early faculty applications, plus two related forms that follow the same rules, UK supporting statements written against a person specification and European motivation letters. Rules come from an evidence-based guideline compiled from university career offices (Berkeley, Yale, Northwestern, UConn, UC Davis, Cornell, Toronto), UK recruitment guidance (jobs.ac.uk, University of Reading), career columns (Inside Higher Ed, Chronicle), and physicists' own advice. Korean working draft, user revision, English final; `scripts/cl_check.py` checks length, dashes, clichés, hedges, placeholders, and wrong institution names. Use when the user mentions 커버레터, cover letter, covering letter, 지원서 편지, motivation letter, supporting statement, or person specification. Use `research-statement` for the research statement or proposal itself, and `academic-jobs` to find calls.

35 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

5 rules. 0 are common, 3 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 31 edited versions we read keep these.

  • 3

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Not for the research statement itself (research-statement), not for reference letters, and not for emails to prospective hosts, mentors, or …

    line 16
  2. Distinctive:

    Ask only for what files and the call cannot answer.

    line 20
  3. Distinctive:

    Honesty: No exaggeration and no false modesty.

    line 56
  4. Distinctive:

    UK supporting statements are scored criterion by criterion: Use the criteria as headings, essential first and in the given order, one …

    line 60
  5. Very specific:

    If the project keeps reviews of earlier letters (e.g.

    line 81

“Common” is measured: kept by at least 6 in 10 of the 31 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

Cover Letter

A cover letter is a short argument that this applicant fits this position, built from evidence the rest of the file supports. It frames the CV and research statement; it does not repeat them.

When to use

  • A cover letter for an advertised postdoc, research associate, fellowship, or early faculty post.
  • A UK supporting statement against a person specification (essential and desirable criteria).
  • A motivation letter for a European fellowship or institute.

Not for the research statement itself (research-statement), not for reference letters, and not for emails to prospective hosts, mentors, or referees (contact-email).

Inputs to confirm

Ask only for what files and the call cannot answer.

  • The call text: title, reference number, where it was posted, addressee, page or character limit, requested documents, and any person specification or explicit questions.
  • The research statement and CV that go with this letter; the letter must agree with them and must not copy their sentences.
  • Facts the call requires that files may lack: citizenship or work-permit status, start date, PhD date, current position.
  • The name form to use (the one on the CV and the one referees will enter in upload portals must match).

Workflow

  1. Read the call twice. List every explicit ask (documents, citizenship statement, referee contacts, start date, questions to answer) and every stated priority in the order the call gives them; that order sets the order of the letter. For a UK post, copy the person specification criteria verbatim into the notes.
  2. Choose the form and length.

    FormLengthShape
    PI-group postdoc or research associateabout one pageopening, one research paragraph, one contribution and fit paragraph, logistics, close
    Independent fellowship or instituteone to two pagesas above plus the research direction and why this institute
    Faculty or senior postone and a half to two pagesresearch, future agenda, teaching, service, fit
    UK supporting statementthe stated character or word limitcriteria as headings, essential criteria first and in order, one evidence example each
    Motivation letterthe stated limit, often two pagesmotivation, fit with the programme's aims, career goals, what the applicant brings
  3. Collect facts from files only. Contributions as recorded (never inferred from author order), unpublished work marked as such, every date and contact from a file; unknowns stay as [확인 필요: ...].
  4. Draft in Korean as <name>_ko_vN.md with _guide/<name>_notes_vN.md mapping each factual sentence to its source and listing open questions. Lead with the questions that block submission (citizenship, name form, referees, dates).
  5. Check with python3 scripts/cl_check.py DRAFT.md --expect "<institution>" --forbid "<other institutions>" and the checklist below. Record verdicts (○ met, △ partial, × missing) with line numbers.
  6. Revise with the user, then translate to English only after approval. Render the PDF and confirm it fits the limit; sign it and use letterhead if the applicant has one.
  7. Cross-check the set: the letter, research statement, and CV tell one story, the letter adds what the others cannot (why this post, what the applicant brings, logistics), and no paragraph is copied from the statement.

Core rules

Short form; quotes and sources in references/evidence.md.

  1. Interpret, do not list. Select one or two results and say why they matter for this post. A paragraph that reads like the CV has no purpose of its own.
  2. Open with the position and a thesis. First sentence or two: the post (title, sub-field, reference number), the applicant's current role, and the strongest reason for fit.
  3. Explain the research for outsiders. The question, the applicant's contribution, and why it matters in the wider field, in plain terms. Detail belongs in the research statement; the letter gives direction.
  4. Say what the applicant will contribute, not only what they want. Concrete skills, results, or a project they would push forward in this group.
  5. Specific fit. Address the ad's stated needs in its own terms; name a real connection to the group's work, people, or resources; if the profile differs from the ad, explain what transfers and why that is an advantage. A sentence that could go unchanged to five other groups is cut or made specific.
  6. Evidence over adjectives. Show with facts (results, outputs, numbers, recognition); drop "passionate", "excellent", "uniquely qualified", "perfect fit", "prestigious institution".
  7. Tone of a colleague. Confident and measured; no hedges ("I will try", "I hope to"), no effusive praise of the institution or of advisers, not every sentence starting with "I".
  8. Honesty. No exaggeration and no false modesty; state one's own role in collaborative work plainly; state missing qualifications honestly with the closest transferable evidence.
  9. Logistics are part of the letter. Names, titles, department, and institution correct; addressed to the named person or the search committee; enclosed and separately sent materials listed; availability and any required status stated; signed PDF.
  10. Follow the call. Its length, questions, and documents override general advice; send nothing that was not requested; check that each tailored letter goes to the right institution.
  11. The applicant's own voice. Several sources warn that letters written by AI read as generic. Drafts produced with assistance must be revised by the applicant, contain only verified facts, and sound like the applicant.
  12. UK supporting statements are scored criterion by criterion. Use the criteria as headings, essential first and in the given order, one specific example each (situation, own action, result), then the desirable criteria the applicant meets.

How much the letter weighs

Readers differ. Some physics search committees barely read cover letters but punish errors in names; career offices for humanities faculty posts call it the most important document. Default for physics and astronomy postdocs: short, specific, and error-free, with the scientific case carried by the research statement and letters of reference.

Checklist

  • The first two sentences name the post and give the main reason for fit.
  • Every explicit ask in the call is answered (documents, citizenship or status, referee contacts, start date, questions).
  • One or two results, each with the applicant's role and why it matters here; no CV recitation.
  • A paragraph says what the applicant would contribute to this group, with one concrete example.
  • Fit is specific: the ad's own terms, a real connection, and an honest bridge for any mismatch.
  • No clichés, hype, or hedges; claims carry evidence.
  • Reads as a future colleague: no effusive praise, varied sentence openings.
  • Unpublished work marked; nothing beyond proven scope; consistent with CV and research statement, no copied paragraphs.
  • Names, titles, department, institution, reference number, and date correct; the right institution throughout.
  • Within the length limit after rendering; signed; enclosures listed.
  • UK form: every essential criterion has a heading and one example; desirable criteria covered where met.
  • cl_check.py reports zero dashes, clichés, hedges, placeholders, and forbidden names in the version meant for submission.

If the project keeps reviews of earlier letters (e.g. a _guide/ folder), read them first and add their recurring failures to this checklist for the session.

scripts/cl_check.py

Standard-library Python 3. For each Markdown or text file: word and character counts (body only, before a ## References or similar heading), em/en dashes, non-Hangul CJK, clichés and hype words, hedges, share of sentences that start with "I", placeholder slots, and institution-name checks (--expect NAME must appear, --forbid NAME must not). --strict exits 1 on dashes, CJK, clichés, hedges, placeholders, missing expected names, or forbidden names.

python3 scripts/cl_check.py cover_ko_v2.md
python3 scripts/cl_check.py --strict cover_en.md --expect "Example Institute" --forbid "Other University" --forbid "Third Lab" --max-words 600

Output layout

<application dir>/
  <name>_ko_vN.md              Korean working drafts
  <name>.typ | .tex, cover.pdf English submission
  _guide/<name>_notes_vN.md    claim-to-source map, open questions
  _guide/<name>_diagnosis_vN.md  checklist verdicts and fix list

References

  • references/evidence.md: each rule with verbatim, string-checked quotes from its sources, and gaps in the evidence.
  • references/sources.md: the 17 sources with type and URL.

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.