ab-equivalence
Compare two versions of an LLM-directed document - an original (teacher) and a candidate…
Six Thinking Hats Analysis
$ npx -y skills add bjcoombs/ai-native-toolkit --skill 6hats --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/6hatsContext preview
The summary Claude sees to decide when to auto-load this skill.
Six Thinking Hats Analysis
name: 6hats disable-model-invocation: true description: "Six Thinking Hats Analysis" argument-hint: "<topic or problem to analyze>"
A solo huddle (team size 1). Spawn hat agents in parallel, synthesize as Blue Hat.
**This is an alias for `/huddle` with team size 1.** Follow the huddle protocol's Solo Mode:
1. Assess the topic and choose a hat sequence 2. Spawn hat agents in parallel based on the sequence 3. Collect results 4. Synthesize as Blue Hat and deliver the verdict
See `/huddle` for full protocol, sequences, and facilitation principles.
A Claude Code plugin - and a set of standalone skills for any AI assistant: skills and agents for AI-native development. In Claude Code it runs locally against your own codebase using whichever model you already pay for.
Repo: bjcoombs/ai-native-toolkit
Compare two versions of an LLM-directed document - an original (teacher) and a candidate…
Renders the /assess report from the deterministic run-context.json and the layer scorecard -…
The /assess end-of-run offers - open a PR with the report, track the Top 3 Actions in the…
Assess a codebase's readiness for AI agent contributors using the layered contract model, and…