From smart-ai
Use this skill when the user asks to "analyze", "research", "how do I", or "what's the best way" to understand project context, impact of potential actions, and root causes of issues.
How this skill is triggered — by the user, by Claude, or both
Slash command
/smart-ai:investigatorThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
The Investigator skill is used to gather deep context and perform rigorous analysis before any action is taken. It ensures that the agent understands the current state of the project, the broader implications of any proposed changes, and the fundamental reasons for any issues.
The Investigator skill is used to gather deep context and perform rigorous analysis before any action is taken. It ensures that the agent understands the current state of the project, the broader implications of any proposed changes, and the fundamental reasons for any issues.
You MUST use this skill when the user mentions:
This skill covers three distinct use cases. Identify which use case(s) apply to the current task and follow the corresponding parallel subagent workflow.
Use when you need to understand the "What", "How", and "When" of the project environment.
README.md, AGENT.md, CLAUDE.md, etc.).git log -n 5) to understand recent changes and project evolution.Combine the structural, documented, and historical findings into a unified context report.
Use when you need to understand connections and predict the consequences of potential actions.
Provide a clear map of relationships and a "risk report" for any proposed actions.
Use when an issue is reported and you need to find the "Why" behind the failure.
Provide a definitive explanation of the root cause and the evidence supporting it. Do NOT make changes or propose fixes.
For any selected use case:
package.json to see the framework (Express) and README.md for endpoint conventions..env is out of sync with the new requirements identified by Subagent 2.npx claudepluginhub davidkiss/smart-ai-skills --plugin smart-aiGuides collaborative design exploration before implementation: explores context, asks clarifying questions, proposes approaches, and writes a design doc for user approval.
Creates structured, bite-sized implementation plans from specs or requirements before writing code. Useful for breaking down multi-step tasks into testable steps with file structure and task boundaries.
Resolves in-progress git merge or rebase conflicts by analyzing history, understanding intent, and preserving both changes where possible. Runs automated checks after resolution.