isolated
Apply Chain-of-Verification (CoVe) with true factored verification using isolated sub-agents.
Apply Chain-of-Verification (CoVe) prompting to improve response accuracy through self-verification.
> /plugin marketplace add serpro69/claude-toolbox > /plugin install kk@claude-toolbox
How it fires
How this command gets triggered: by you, by Claude, or both.
/defaultContext preview
What this command does when you run it.
Apply Chain-of-Verification (CoVe) prompting to improve response accuracy through self-verification.
Apply Chain-of-Verification (CoVe) prompting to improve response accuracy through self-verification.
Arguments: $ARGUMENTS
**If $ARGUMENTS is provided:** Apply the CoVe verification process to answer the given question with systematic fact-checking.
**If $ARGUMENTS is empty:** Apply CoVe to verify the previous response in the conversation, generating verification questions and reconciling any errors found.
Invoke the `kk:chain-of-verification` skill and follow the 4-step workflow in `chain-of-verification-process.md`:
1. Generate Initial Answer (or use previous response if verifying) 2. Create 3-5 Verification Questions targeting potential errors 3. Answer questions independently without referencing the initial answer 4. Reconcile findings and produce the final verified answer
/kk:chain-of-verification What is the time complexity of Python's sorted()?
/kk:chain-of-verification
(Use after receiving a response to verify it)
<div align="center" claude-toolbox is a collection of "tools" for all your agentic workflows — pre-configured MCP servers, skills, sub-agents, commands, hooks, statuslines with themes, and more - everything you need for AI-powered development workflows, used
Repo: serpro69/claude-toolbox
Apply Chain-of-Verification (CoVe) with true factored verification using isolated sub-agents.
Migrate this project from Task Master MCP to native markdown-based task tracking.