agentleFS
rafaym1rafaym1/scholarship-desk/.claude/skills/outreach/SKILL.md

outreach

Skill18 starsChanged 4 days agoMITView on GitHub

Find supervisors whose current research matches the applicant (PhD and research master's — mainly Canada, Australia, UK, and anywhere a supervisor must agree first) and draft short, specific emails for the applicant to send. Use "/outreach" or "/outreach <opportunity id>".

18 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use evaluate and triage.

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.
  • NVIDIASkill

    evaluate

    Scores existing Sports Intelligence AVLM inference outputs with avlm/evals: MCQ accuracy (run_mcq_eval.sh, INFERENCE_DIR), open-ended LLM-as-judge scores (needs CLIENT_API_KEY for the configured judge endpoint), tennis category breakdowns, run comparisons, chance-level sanity checks and triage of mcq_results.json or llm_judge_results.json. Use when the user asks to score, evaluate, benchmark or compare predictions.jsonl from inference runs, or to explain a suspicious accuracy. Not for running inference, training, quantization, data preparation, or third-party API model inference: never open, list or run anything under avlm/evals/inference_3rdparty, including when the user asks for it; it is excluded from the release.

    Also in 3 projects that use this

  • Google CloudSkill

    triage

    Gather context on a change or bug and plan the implementation.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 18 edited versions we read keep these.

  • 1

    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:

    Read CLAUDE.md first. Quality over volume: a few well-matched emails a week.

    line 8

“Common” is measured: kept by at least 6 in 10 of the 18 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

Supervisor outreach

Read CLAUDE.md first. Quality over volume: a few well-matched emails a week.

  1. Gather: python -m scholar profile show --section target, python -m scholar library facts --tag research, and the opportunity (opp show <id>) if one is given.
  2. Find candidates on official university pages (faculty/lab pages). For each, check: recent work (last ~3 years) that genuinely connects to the applicant's interests and experience, whether they say they're taking students, and any funding route mentioned.
  3. Record them — data/tmp/supervisors.json: [{"name": "...", "institution": "...", "country": "...", "email": "<from the official page only>", "profile_url": "https://<official page>", "match": "2–3 sentences: which papers/projects and how they connect to the applicant's specific experience", "opp_id": null}] → python -m scholar outreach add data/tmp/supervisors.json.
  4. Draft each email in data/outreach/<contact id>.md: a specific subject line and at most ~200 words — who the applicant is (one line), the concrete connection to one or two of the supervisor's recent works, two facts from the bank showing fit, the ask (are they taking students for <term>, and the usual funding route), and that a CV is attached. No flattery templates. python -m scholar outreach update <contact id> drafted --draft data/outreach/<contact id>.md
  5. Show the drafts. The applicant sends them from their own email. Only if they ask you to send through a connected email tool: show the exact recipient and text and get a yes for each email. After sending: python -m scholar outreach update <contact id> sent.
  6. The CLI warns after 5 sends in a week. Suggest one polite follow-up after about two weeks, no more. Record replies with outreach update <id> replied_positive|replied_negative|no_reply.

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.