Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add AlterLab-IEU/AlterLab-Academic-Skills --skill alterlab-recommendation-lettersgit clone --depth 1 https://github.com/AlterLab-IEU/AlterLab-Academic-SkillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/alterlab-ieu/alterlab-academic-skills/alterlab-recommendation-letters)<a href="https://agentmods.dev/skills/alterlab-ieu/alterlab-academic-skills/alterlab-recommendation-letters"><img src="https://agentmods.dev/badge/skills/alterlab-ieu/alterlab-academic-skills/alterlab-recommendation-letters/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/alterlab-ieu/alterlab-academic-skills/alterlab-recommendation-letters"><img src="https://agentmods.dev/badge/skills/alterlab-ieu/alterlab-academic-skills/alterlab-recommendation-letters.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00197 | $0.02727 |
| Opus 5 | $0.00098 | $0.01363 |
| Sonnet 5 | $0.00039 | $0.00545 |
| Haiku 4.5 | $0.00020 | $0.00273 |
Grade A, and why
alterlab-recommendation-letters scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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) | alterlab-paper-reviewer |
Section-by-section manuscript critique, not a recommendation about a candidate |
| Türkiye doçentlik eligibility / point computation for an associate-professor case | alterlab-docentlik-eligibility |
ÜAK criteria scoring, not a prose reference letter |
| Academic-incentive (akademik teşvik) point computation | alterlab-akademik-tesvik |
YÖK incentive points, not a letter |
| Checking that the citations in a letter or dossier actually exist | alterlab-citation-verifier |
Bibliographic existence verification, not letter-claim evidence-anchoring |
| Designing a course, rubric, or syllabus for the student | alterlab-teaching-design |
Course/instructional design, not a reference about the student |
| Writing a grant proposal or post-award report | alterlab-research-grants / alterlab-grant-reporting |
Funding documents, not personal references |
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 6d ago First seen · 206 lines · 197 tokens per session scan A 66e0b8a29ee4
alterlab-recommendation-letters is a skill published in the GitHub repository AlterLab-IEU/AlterLab-Academic-Skills (66 stars, last pushed 7d ago), licensed MIT. It adds 197 tokens to every session and 2,727 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-05.
Other skills, from other repositories
academic-slides
Create Beamer-inspired academic HTML presentations from scratch or by converting PowerPoint files. Use when the user wants to build slides for a conference talk, lecture, seminar, or thesis defense. Supports theorem environments, KaTeX equations, algorithm pseudocode, and citations. Helps academics discover their…
phd-milestone-tracker
A tracker for planning and monitoring the academic milestones of working business doctoral students.
academic-deck-animator
A tool for creating animated academic presentations from one JSON content file. It can produce a browser-based HTML presentation or an editable PowerPoint file; academic presentations are talks used to explain research to reviewers, classmates, or other researchers.
qual-exam-coach
A Traditional Chinese study coach for business PhD qualifying exams in organization, human resources, management psychology, strategy, innovation, and research methods.
defense-qa-coach
A preparation coach for thesis defenses, doctoral exams, and conference question-and-answer sessions. It helps researchers practise answering questions from the viewpoint of a committee member.
academic-pptx
Use this skill whenever the user wants to create or improve a presentation for an academic context — conference papers, seminar talks, thesis defenses, grant briefings, lab meetings, invited lectures, or any presentation where the audience will evaluate reasoning and evidence. Triggers include: 'conference talk'…