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

profile

Skill18 starsChanged 4 days agoMITView on GitHub

Interview the applicant and save their profile — targets, citizenships and residence history, identity/contact for forms, education, tests, experience, referees, narrative in their own words, and documents (all CV variants). Use for first-time setup or whenever details change.

30 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use coverage, benchmark and 4 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.
  • PydanticSkill

    coverage

    Fetch coverage diff from Codecov for the current branch or a specific PR. Shows uncovered lines, patch coverage, and overall coverage change.

    Also in 3 projects that use this

  • dragonflydbSkill

    benchmark

    Benchmark Dragonfly (and compare against Valkey/Redis) on local or remote cloud instances, then produce a performance + memory report with charts and a raw-data appendix. Use this whenever the user runs /benchmark, or asks to benchmark / load-test / measure throughput, QPS, latency, or memory efficiency of Dragonfly or another Redis-compatible server, to compare Dragonfly vs Valkey or Redis, or to generate a benchmark report. Trigger it even when the user just describes the goal ("see how fast Dragonfly is on this box", "compare memory per key vs Valkey") without saying the word "benchmark".

    Also in 3 projects that use this

  • AnthropicSkill

    status

    Case status summary by audience — client-facing (plain language), internal (for the professor), or court-ready (formal caption format per local rules). Same facts, different framing and depth. Use when a student needs to update the client, brief the professor, or prepare a court status report.

    Also in 3 projects that use this

  • Microsoft AzureSkill

    docs

    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 3 projects that use this

  • GoogleSkill

    tdd

    Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

6 rules. 0 are common, 5 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 24 edited versions we read keep these.

  • 5

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read CLAUDE.md (non-negotiables) first.

    line 9
  2. Distinctive:

    If the profile already exists, ask only about missing fields and anything that changed.

    line 14
  3. Distinctive:

    Use country names, not nationalities ("Pakistan", not "Pakistani").

    line 80
  4. Very specific:

    If a result says NOT SAVED, explain the reason and ask again.

    line 81
  5. Distinctive:

    Never store passwords, SIN/SSN, passport or national-ID numbers, bank or card details.

    line 82
  6. Distinctive:

    After each batch, confirm briefly what was saved (not every value).

    line 87

“Common” is measured: kept by at least 6 in 10 of the 24 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

Profile interview

Goal: an accurate, complete profile so eligibility checks and applications never rely on guesses. Read CLAUDE.md (non-negotiables) first.

Start

  1. python -m scholar profile status — show the completeness percentage and what is missing. If the profile already exists, ask only about missing fields and anything that changed. Mention once that every answer can also be typed into the dashboard's Profile tab (and files dropped into the Documents tab) if they prefer the web to chat.
  2. Tell the applicant once: answers are stored only on this PC in data/profile.json; what they type here also goes to Claude as part of the conversation.

Ask in batches (one message per batch, wait for the reply)

A. What you're applying for — levels (masters, phd), fields of study, research/topic keywords, regions (europe, north_america, australia, scandinavia; default all four), intended start (YYYY-MM), universities in mind, countries to avoid, fully funded only?

B. Citizenship and residence (drives country eligibility) — every citizenship held; country of residence now and status there (citizen, permanent_resident, study_permit, work_permit, …); where they've lived over the last 5+ years (country, from, to); country of birth. Explain that some awards exclude people who already live in the host country, and some treat dual citizens specially.

C. Identity and contact for forms — legal given/middle/family names exactly as in the passport, preferred name, date of birth, email for applications, phone with country code, mailing address.

D. Education — each degree: institution, country, degree name, field, start/end, status, GPA and scale, grade as written on the transcript, honours, thesis title, supervisor, language of instruction.

E. Tests — IELTS/TOEFL/PTE/Duolingo/GRE/GMAT: exact exam name, overall score, date, expiry.

F. Experience, publications, awards, activities, languages.

G. Referees — name, title, institution, email, relationship, what they can speak to, and whether they've agreed to write. Entering a referee in a portal often emails them immediately.

H. Narrative bank (their words) — motivation, career goals, research experience/ideas, leadership, a challenge overcome, impact on community/home country. Ask them to write or paste; do not write it for them. They can skip this if their past essays will be ingested.

I. Consent — ask exactly: "May I include your nationality in web searches to find country-specific scholarships? The search engine will see those queries." Save as consent.identity_search yes/no.

J. Documents — ask them to put files in documents/ (CVs, transcripts, degree certificates, language certificates, past essays/statements, research proposal, writing samples). Register each:

python -m scholar profile doc-add cv "documents/CV - research.pdf" --label "CV - research focus"
python -m scholar profile doc-add cv "documents/CV - industry.pdf" --label "CV - industry focus"
python -m scholar profile doc-add transcript "documents/BSc transcript.pdf"
python -m scholar profile doc-add writing_sample "documents/Chevening essays 2025.docx" --label "Past essays"

Register every CV variant as type cv with a distinct label. A passport scan is type passport_scan; the applicant uploads it to portals themselves.

Saving

python -m scholar profile keys [identity|target|narrative|consent|lists]   # valid keys and choices
python -m scholar profile set identity.citizenships "Pakistan; Canada"
python -m scholar profile set target.levels "masters, phd"
python -m scholar profile list-add residence country=Canada from=2024-08 status=study_permit
python -m scholar profile list-add education institution="..." degree="BSc Computer Science" status=completed end=2024-05 gpa=3.6 gpa_scale=4
python -m scholar profile list-add tests exam="IELTS Academic" score=7.5 date=2025-03-02 expires=2027-03-02
python -m scholar profile list-update education 1 honours="Dean's list"
python -m scholar profile skip identity.gender
  • Copy values exactly as given. Ask when unclear (weighted or unweighted GPA? IELTS Academic or General?).
  • Use country names, not nationalities ("Pakistan", not "Pakistani"); the CLI suggests fixes.
  • If a result says NOT SAVED, explain the reason and ask again.
  • Never store passwords, SIN/SSN, passport or national-ID numbers, bank or card details. If offered, say they'll type those into forms themselves.
  • Long text (narrative) with quotes or newlines: write it to data/tmp/<key>.txt and pass it with python -m scholar profile set narrative.motivation "$(cat data/tmp/motivation.txt)", or keep it short and set directly.
  • After each batch, confirm briefly what was saved (not every value).

Finish

python -m scholar profile status, then tell them the next steps: /ingest (reads their documents), then /discover, and open the dashboard (python -m scholar serve --open, python3 on Mac/Linux, or the Scholarship Desk desktop shortcut on Windows).

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.