skills/ask-questions/SKILL.md
Clarify requirements before implementing. Do not use automatically, only when invoked explicitly.
npx skillsauth add ferueda/agent-skills ask-questionsInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Ask the minimum set of clarifying questions needed to avoid wrong work; do not start implementing until the must-have questions are answered (or the user explicitly approves proceeding with stated assumptions).
Treat a request as underspecified if after exploring how to perform the work, some or all of the following are not clear:
If multiple plausible interpretations exist, assume it is underspecified.
Ask 1-5 questions in the first pass. Prefer questions that eliminate whole branches of work.
Make questions easy to answer:
defaults to accept all recommended/default choices)1b 2a 3c); restate the chosen options in plain language to confirmUntil must-have answers arrive:
If the user explicitly asks you to proceed without answers:
Once you have answers, restate the requirements in 1-3 sentences (including key constraints and what success looks like), then start work.
1) Scope?
a) Minimal change (default)
b) Refactor while touching the area
c) Not sure - use default
2) Compatibility target?
a) Current project defaults (default)
b) Also support older versions: <specify>
c) Not sure - use default
Reply with: defaults (or 1a 2a)
tools
Evaluate, analyze, and systematically react to an adversarial code review report. Decide on the action for each finding (Implement, Adapt, Decline), provide clear justifications, and define the plan to implement the accepted changes.
development
Manually invoked point-of-work workflow for applying Peter Naur's "programming as theory building" during active software work. Use this skill only when the user explicitly names `theory-building`, asks to use the theory-building skill, or explicitly says to apply programming-as-theory- building to the current design, implementation, refactor, review, or AI-generated code. Do not trigger automatically for ordinary architecture, implementation, refactor, review, debug, documentation, AI-code, domain model, or maintainability tasks.
development
Manually triggered weekly or post-change repository audit based on Peter Naur's "Programming as Theory Building." Use this skill only when the user explicitly names `theory-building-review`, asks to run the theory-building review skill, or says to run the weekly/post-change theory-building review. Do not trigger automatically just because the conversation mentions Naur, domain modeling, refactoring, architecture, craft, or code review. When explicitly invoked, inspect recent diffs or scoped repository areas, reconstruct the system theory, find places where code and domain language diverge, and return actionable refactor, test, documentation, and modeling improvements. For active design, implementation, refactor, review, or AI-code acceptance on a specific change, use `theory-building` instead when explicitly invoked.
documentation
Summarize work done in a spec/plan document.