agentleFS
Sign inStart free
TheophilusChinomonaTheophilusChinomona/idev/skills/context-switching/SKILL.md

context-switching

Skill0 starsChanged 5 months agoMITView on GitHub

Switches between development modes (dev, review, research) by loading the appropriate context. Use when the user changes task type or asks to switch modes.

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 3 are distinctive, and 1 is 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.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read the appropriate context file from ${CLAUDE_PLUGIN_ROOT}/contexts/

    line 40
  2. Distinctive:

    Do NOT stay in research mode when the user wants to build

    line 45
  3. Distinctive:

    Do NOT switch modes without telling the user

    line 46
  4. Distinctive:

    Do NOT load multiple modes simultaneously

    line 47

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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 Switching Skill

Purpose

Dynamically adjust Claude's behavior based on the current task mode.

Modes

ModeContext FileBehavior
devcontexts/dev.mdWrite code, run tests, commit often
reviewcontexts/review.mdRead thoroughly, find issues, suggest fixes
researchcontexts/research.mdExplore, understand, document findings

Activation

  • User says "switch to review mode" or "let's review this"
  • User says "research how X works" or "investigate Y"
  • User says "switch to dev mode" or "let's build this"
  • Task type changes mid-session

Example

User: "let's review this PR"
→ Claude loads contexts/review.md
→ Behavior shifts to thorough reading, issue prioritization
→ Output grouped by file, severity first

User: "switch to dev mode, let's build the feature"
→ Claude loads contexts/dev.md
→ Behavior shifts to writing code, running tests
→ Output focuses on implementation

How It Works

  1. Read the appropriate context file from ${CLAUDE_PLUGIN_ROOT}/contexts/
  2. Load its behavior rules into working memory
  3. Apply those rules until the mode changes

Anti-Patterns

  1. Do NOT stay in research mode when the user wants to build
  2. Do NOT switch modes without telling the user
  3. Do NOT load multiple modes simultaneously

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