agentleFS
ThisisYoYoDevThisisYoYoDev/claude-rag/skills/context-recall/SKILL.md

context-recall

Skill9 starsChanged 8 months agoMITView on GitHub

Search past conversations and tool results for relevant historical context. Use when the user references past work ("how did we do X", "remember when", "last time"), asks about project history, or when historical context from previous sessions would help with the current task.

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. sepehrbayat/SEPCC★ 38same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository8 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    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:

    Search the RAG database for context relevant to the current conversation.

    line 14
  2. Distinctive:

    If code was found, include key snippets

    line 32
  3. Distinctive:

    Keep it brief — this is supplementary context, not the main answer

    line 33
  4. Distinctive:

    If no relevant results found, don't force it.

    line 36

≈ “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

Context Recall (Auto-invoked by Claude)

Search the RAG database for context relevant to the current conversation.

Instructions

  1. Determine the best search query from the current conversation context. Focus on:
    • Specific technical terms, function names, file paths
    • The core topic or problem being discussed
    • Any explicit references to past work
  2. Use mcp__plugin_claude-rag_rag__search with:
    • query: derived from the conversation context
    • limit: 5
    • threshold: 0.55
  3. Return findings concisely:
    • Lead with the most relevant finding
    • Include specific details: file paths, function names, dates
    • If code was found, include key snippets
    • Keep it brief — this is supplementary context, not the main answer
    • Prefix findings with "From past conversations:" to make the source clear
  4. If no relevant results found, don't force it. Simply state that no relevant historical context was found.

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.