Stats
Actions
Tags
Use this skill whenever the user asks you to investigate, scope, scout, survey, or "look into" something before implementing. Trigger on phrases like "how hard would it be to...", "where would I even start with...", "I want to add X but I'm not sure what it touches", "do a spike", "do some recon", "don't write code yet", or any request where the scope is unclear. The job is to map the territory and surface unknowns — NOT to start implementing.
How this skill is triggered — by the user, by Claude, or both
Slash command
/vinhnguyen1211-skills:exploratory-workThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
When scope is unclear, the worst move is to start implementing. Map the territory first.
When scope is unclear, the worst move is to start implementing. Map the territory first.
No edits to source files. No new modules. No "while I'm in here" refactors. Reading code is fine. Pseudocode or small inline snippets to illustrate an approach is fine.
If you feel the urge to start building, that's the signal to write down what you'd build instead. It goes in the report.
A short written report covering:
Ask the questions one at a time.
If a question can be answered by exploring the codebase, explore the codebase instead.
If a question would meaningfully change the recommendation, ask the user. Examples: "should this live in service A or B?", "follow the older pattern (8 places) or the newer one (2)?". Don't ask about minor preferences.
Default to a markdown report — inline for small investigations, a file (exploration-<topic>.md) for larger ones so the user can reference it later.
Guides creation, editing, and verification of skills for AI coding agents using test-driven development with subagent scenarios. Use when authoring or debugging skills.
npx claudepluginhub vinhnguyen1211/skills --plugin vinhnguyen1211-skills