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
- mysocialio/mysocial-intelligencetheir own version, first seen Nov 14, 2026
- guaardvark/guaardvarktheir own version, first seen Nov 13, 2026
- cismontane-harris2642/signal-prospecting-kittheir own version, first seen Nov 1, 2026
- saksham10arora-dotcom/everything-claude-codextheir own version, first seen Nov 1, 2026
- ShawhinT/non-coding-skillstheir own version, first seen Oct 29, 2026
- jaredhhawk/claude-skillstheir own version, first seen Oct 25, 2026
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.
NVIDIASkillevaluate
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 CloudSkilltriage
Gather context on a change or bug and plan the implementation.
Also in 3 projects that use this
Other versions18 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 18
- QuixiAI/agi-memory★ 623same name
- QuixiAI/Hexis★ 623same name
- andrew-shwetzer/career-ops-plugin★ 501same name
- andrew-shwetzer/career-ops-plugin-do-not-fork-currently-updating-v2-★ 500same name
- guaardvark/guaardvark★ 320same name
- saksham10arora-dotcom/everything-claude-codex★ 96same name
- ShawhinT/non-coding-skills★ 40same name
- emelia-io/claude-outreach★ 21same name
- alejopijuan/Claude-Code-Agency-Co-Founder★ 19same name
- Abhipaddy8/outreach-agent★ 17same name
8 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
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
- Distinctive: line 8
Read CLAUDE.md first. Quality over volume: a few well-matched emails a week.
“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.
Files
Supervisor outreach
Read CLAUDE.md first. Quality over volume: a few well-matched emails a week.
- 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. - 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.
- 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. - 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 - 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. - 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.
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
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.

