alterlab-recommendation-letters

name	alterlab-recommendation-letters
description	Drafts evidence-anchored academic reference and recommendation letters across types — graduate admission, faculty hiring, tenure/promotion external review, fellowship, and award nomination — from a structured prompt of candidate accomplishments, role context, evaluator relationship, and audience, calibrating specificity and register to the letter type and running a no-fabrication guard that flags unsupported superlatives, unanchored rankings, and claims with no evidence in the supplied dossier. Ships scripts/letter_scaffold.py to emit a typed section skeleton and scripts/claim_guard.py to lint a draft for evidence-free assertions. Use when the request is to write a recommendation or reference letter for a student or colleague, a tenure or promotion external-review letter, a fellowship or award nomination, or to check a letter draft for unsupported claims. For a candidate writing their own CV, research statement, or career narrative prefer alterlab-academic-career. Part of the AlterLab Academic Skills suite.
license	MIT
allowed-tools	Read Write Edit Bash(python:*) Bash
compatibility	No API key, account, or network required — generates letters from the supplied dossier via the Read/Write/Edit tools plus two stdlib-only helpers (scripts/letter_scaffold.py, scripts/claim_guard.py) run through `uv run python`. The recommender always reviews, signs, and submits the final letter themselves.
metadata	{"skill-author":"AlterLab","version":"1.0.0","last_updated":"2026-06-06","depends_on":"alterlab-academic-career (owns the candidate's OWN CV/statements; this skill writes ABOUT a candidate for a third party)"}

Recommendation Letters — Evidence-Anchored References Written About a Candidate

The faculty task this skill owns is writing about someone else: the letter a professor sends to an admissions committee, a hiring chair, a tenure case, or a fellowship panel. It is the mirror image of alterlab-academic-career, which helps the candidate write their own CV and statements. Here the author is the recommender, the subject is a third party, and the failure mode is not modesty but fabrication — the warm letter full of superlatives that an evaluator cannot act on because nothing is anchored to evidence.

This skill turns a structured dossier (what the recommender actually knows) into a letter whose every strong claim is earned by a specific, checkable example, with specificity and register calibrated to the letter type.

When to Use This Skill

Use this skill when the request is to draft, revise, or evidence-check a letter written about a candidate by a recommender:

• "Write a recommendation letter for my PhD student applying to postdocs."
• "I'm a reference for a colleague's faculty application — draft the letter."
• "I've been asked for an external review letter for X's tenure case."
• "Draft a fellowship / award nomination for my mentee."
• "Here's my draft letter — flag anything I claim without backing it up."
• "Make this reference letter more specific; it reads like boilerplate."

The skill always treats the recommender as the author of record: it produces a draft for them to verify, edit, sign, and submit, never a letter it claims to send or to vouch for on its own authority.

Does NOT Trigger

The request is really…	Route to	Why
The candidate's own CV, research/teaching statement, cover letter, tenure dossier, promotion narrative	alterlab-academic-career	Self-authored career documents, not a third party writing about the candidate
A peer-review report judging a manuscript's quality with an accept/revise/reject verdict	alterlab-peer-review	Editorial quality judgment of a paper, not a personal reference for a person
A structured peer review of a full manuscript (core-pipeline reviewer)