agentleFS
alibaba-damo-academyalibaba-damo-academy/ScholarSeed/skills/community/academic-research-guidance/SKILL.md

academic-research-guidance

Skill44 starsChanged 5 days agoApache-2.0View on GitHub

Guide academic and scientific research requests: scholarly concepts, paper understanding, research questions, research methods, experimental design, and academic evidence analysis across natural sciences, engineering, humanities, and social sciences. Clarify unresolved intent and route to specialized research skills. Not for ordinary coding, writing, file management, or product operations without a research objective.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    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:

    Before presenting key research conclusions, read Research conclusions and evidence.

    line 32
  2. Distinctive:

    Keep internal classification and routing reasoning private, while still explaining evidence limits and any user-facing execution modes, …

    line 47
  3. Distinctive:

    When the user switches to a nonresearch task, stop applying research-specific clarification and conclusion formatting.

    line 52

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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

Academic Research Guidance — 科研任务指导

Apply this skill to the research portion of the current request, not unrelated tasks merely sharing its vocabulary or tools. Inspect relevant user-provided materials and prior answers before deciding anything is missing.

Choose the appropriate depth

  • For every request handled by this skill, first read and follow the complete Research intent clarification and routing. Apply its five judgments before deciding whether clarification is needed or proceeding with the task. A fully specified request requires no extra questions. Preserve all stated constraints and previous answers; do not ask again merely because a skill changed.
  • Before presenting key research conclusions, read Research conclusions and evidence. Apply these rules to substantive research claims, not to greetings or questions.

Respect task ownership

This skill supplies shared research guidance, not a research deliverable or a mode option. Never select it again as a routing destination. Determine matching task skills from their available descriptions and actual scope; use general capabilities only when no available task skill covers the explicit deliverable.

The selected task skill owns its stages, modes, checkpoints, authorizations, and recovery. Intent clarification is not authorization to start, download, or publish. Do not reproduce or override those protocols here.

Keep internal classification and routing reasoning private, while still explaining evidence limits and any user-facing execution modes, costs, or confirmations the task skill requires. Follow the host's current search restrictions; loading this skill does not authorize external retrieval.

When the user switches to a nonresearch task, stop applying research-specific clarification and conclusion formatting. Previously read text may remain in the conversation history; its presence does not make unrelated tasks research.

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.