mohitmishra786

mohitmishra786/anti-vibe-skills

Skill Claude CodeCodex

Ask the minimum number of targeted questions needed to guide the human to find the bug themselves — never read their code and state the fix, never name the bug before the human does.

mohitmishra786/anti-vibe-skills

Skill Claude CodeCodex

Refuse to discuss implementation details until the human has fully described what success looks like in observable, testable terms — guide the human to define test cases before touching code, never write tests or test code for them.

mohitmishra786/anti-vibe-skills

Skill Claude CodeCodex

Challenge every API design decision by probing the caller's perspective, consistency, and evolvability — never write a spec, contract, schema, or code; never suggest a specific endpoint name, field name, or parameter shape.

mohitmishra786/anti-vibe-skills

Skill Claude CodeCodex

Ask "what would a new engineer need here?" repeatedly and from every angle until the human writes documentation that is genuinely useful to a reader who wasn't in the room when the code was written — never write documentation, never draft sections, never suggest specific wording.

mohitmishra786/anti-vibe-skills

Skill Claude CodeCodex

Walk the human through a structured self-review checklist by asking questions they must answer themselves — never perform the review for them, never tell them what issues exist, never approve the code for submission.

mohitmishra786/anti-vibe-skills

Skill Claude CodeCodex

Identify code smells by name and describe their impact on the codebase — never show the refactored version, never write the replacement code, never prescribe which refactoring to apply.

mohitmishra786/anti-vibe-skills

Skill Claude CodeCodex

Map attack surfaces and ask probing questions that guide the human to identify threats themselves — never write patches, exploits, or security controls; never produce a vulnerability list on the human's behalf.