agentleFS
EngDawoodEngDawood/arabic-scholar-mcp-server/skills/previous-studies/SKILL.md

previous-studies

Skill1 starsChanged 3 days agoMITView on GitHub

Draft the previous-studies section (الدراسات السابقة) or a literature review for a thesis or research proposal from real papers found with the Arabic Scholar tools. Use when the user asks for الدراسات السابقة, الإطار النظري, مراجعة الأدبيات, a literature review, or related work for a stated research topic.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    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. Very specific:

    Search: Use search_all with scope: "arabic" for the Arabic studies and scope: "international" for the foreign ones, one call per main …

    line 22
  2. Distinctive:

    Choose: Keep the studies closest to the user's variables, population and country.

    line 23
  3. Distinctive:

    Use only studies a tool returned in this conversation.

    line 31
  4. Distinctive:

    If you found fewer studies than asked for, deliver what you found and say how many are missing and which searches you ran.

    line 32
  5. Distinctive:

    Write only what the record or the text supports.

    line 33
  6. Distinctive:

    Write the section for the user to revise.

    line 35

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “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

Previous studies (الدراسات السابقة)

Build the section from papers the tools returned, each one read at least at the abstract level, each one cited.

Before you search

Get these from the user's message, and ask once for whatever is missing:

  • The research title or topic, and its main variables.
  • How many studies, and the split between Arabic and foreign ones (a common request is half and half).
  • The period (often the last five or ten years).
  • The citation style (APA 7 is the usual one in Arab universities).
  • The order: newest to oldest, oldest to newest, or by theme.

Steps

  1. Search. Use search_all with scope: "arabic" for the Arabic studies and scope: "international" for the foreign ones, one call per main variable, in Arabic and in English. Follow the find-papers skill.
  2. Choose. Keep the studies closest to the user's variables, population and country. Prefer peer-reviewed articles and theses with a record link. Drop duplicates.
  3. Read. For each kept study get the abstract from its record (get_paper_details, mandumah_get_record). Read the full text (read-paper skill) when the abstract lacks the method or the sample.
  4. Write each study as one paragraph in the user's language with the same parts in the same order: author and year, the aim, the method, the sample and where it was drawn, the instrument, the main findings.
  5. Add the commentary (التعقيب على الدراسات السابقة): where the studies agree and differ in aim, method, sample and findings, and what the user's study adds.
  6. Add the reference list with the cite-sources skill.

Rules

  • Use only studies a tool returned in this conversation. Never fill a gap with a study from memory.
  • If you found fewer studies than asked for, deliver what you found and say how many are missing and which searches you ran.
  • Write only what the record or the text supports. If the sample size or the instrument is not stated, write that it is not stated.
  • Mark a study you read only at the abstract level.
  • Write the section for the user to revise. Say so in one line at the end: the wording is a draft, and each study should be checked against its source before submission.

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.