agentleFS
Sign inStart free
dmzoneilldmzoneill/skills/research-topic/SKILL.md

research-topic

Skill2 starsChanged 19 days agoApache-2.0View on GitHub

Research a topic thoroughly using code search, memory, knowledge, and optional web search. Use when you need to understand something before taking action.

7 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

1 rule. 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 6 edited versions we read keep these.

  • 0

    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. Very specific:

    If project empty: infer from cwd via config repositories.

    line 22

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

Research Topic

Deep dive on a topic using internal and external sources. Searches codebase, memory, project knowledge, and optionally the web.

Inputs

InputTypeDefaultPurpose
topicstringrequiredTopic to research (e.g., "pytest fixtures", "Redis caching")
projectstringautoProject to search (from config)
depthstring"normal""quick" (code only), "normal" (code + memory), "deep" (all sources)
focusstring-Specific aspect (e.g., "performance", "security")

Workflow

1. Detect Project

  • If project empty: infer from cwd via config repositories; default automation-analytics-backend

2. Search Codebase

  • code_search(query=topic + focus, project=project, limit=10)
  • Parse results into file paths, scores, previews

3. Check Memory (depth != "quick")

  • memory_read("learned/patterns")
  • Filter patterns relevant to topic/focus

4. Query Project Knowledge (depth != "quick")

  • knowledge_query(project=project, section="architecture")
  • knowledge_query(project=project, section="patterns")
  • knowledge_query(project=project, section="gotchas")

5. Optional External Search

  • For "deep" or when internal sources insufficient: WebSearch for external docs

6. Build Summary

Output markdown with:

  • Code Found: file list with previews
  • Past Learnings: relevant patterns from memory
  • Architecture Context: from knowledge
  • Coding Patterns and Gotchas
  • Next Steps: explain_code, plan_implementation, persona_load("developer")

7. Log

  • memory_session_log("Researched: {topic}", "Project: {project}, Depth: {depth}")

Key MCP Tools

  • code_search — semantic code search
  • memory_read — learned patterns
  • knowledge_query — architecture, patterns, gotchas
  • memory_session_log — session logging
  • WebSearch — external documentation (optional)

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.

Check your setup, free