Imbad0202/academic-research-skills

This page introduces an external open-source repository. It is not an HDATF product.

What it does

A suite of Claude Code skills for the academic pipeline of research, writing, review, revision and finalizing. It handles finding references, formatting citations, verifying data and checking logical consistency, leaving key decisions to the researcher.

How it helps ATF

Close to LabChin, which links a research question, sources, notes and a final report. Its staged flow from research to final version and its human-in-the-loop checks are worth comparing.

License

Custom license Custom or non-standard license. Read the license file before any reuse.

More in this category

• anthropics/claude-for-legal
  Reference agents, skills and data connectors for legal workflows such as privacy, litigation and IP, packaged as Claude plugins or for the Claude Managed Agents API. Every output is a draft for attorney review.
• Yuan1z0825/nature-skills
  A collection of reusable agent skills for research, focused on academic writing in the style of Nature papers and on scientific figures. The skills can be used with Claude Code, Codex, Chatbox and other agents.
• anthropics/claude-plugins-official
  An Anthropic-managed directory of Claude Code plugins, split into internal plugins and third-party plugins. Each plugin follows a standard structure with metadata and optional MCP server config, commands, agents and skills.
• composio-community/awesome-codex-skills
  A curated list of Codex skills for automating workflows in the Codex CLI and API, grouped into areas such as development tools, productivity, communication and data analysis, with a script that installs a chosen skill.
• hardikpandya/stop-slop
  Stop Slop is a skill file that teaches Claude or another LLM to find and remove patterns typical of AI writing, such as banned phrases and structural clichés. It scores prose on directness, rhythm, trust, authenticity and density.

Only repositories in the ranked Trendshift lists are included, and the lists are used only to find candidates. We do not copy their ranks. Descriptions, licenses and star counts come from each GitHub repository. The notes are our own reading. We have not tested these projects, and a place on a trending list does not prove quality.