valpere

debug

Systematic bug diagnosis — reproduce, isolate, hypothesize, verify, fix. Usage: /debug [what's broken]

Subjects every non-trivial decision to a fresh-context adversarial review before it stands. Use when correctness matters more than speed, when working in unfamiliar code, when stakes are high (production, security-sensitive logic, irreversible operations), or any time a confident output would be cheaper to verify now than to debug later.

find-bugs

Read-only bug audit of the current branch vs a base ref. Dispatches subagents per stack (Go, JS/TS, etc.), consolidates findings, produces a prioritized report. Does not fix. Usage: /find-bugs [base-ref]

generate-find-bugs

Generates a project-specific /find-bugs skill with stack-specific security and correctness checklists. Run once per project. Usage: /generate-find-bugs

housekeeping

session-indexer repo health check. Universal hygiene + Go vet/fmt + project-specific checks. Usage: /housekeeping

improve

Critique any plan, architecture decision, or implementation approach. Research-first — gives SHIP IT / IMPROVE IT / RETHINK IT / KILL IT verdict. Usage: /improve <topic>

generate-improve

Generates a project-specific /improve skill with actual architecture layers, reference files, and known constraints from CLAUDE.md. Run once per project. Usage: /generate-improve

revival

Project self-diagnosis: session-indexer. Usage: /revival [lightweight|full]

self-learn

Self-learning system — log mistakes/wins, run retrospectives, promote patterns to hard rules, and coach on workflow quality. Usage: /self-learn [log|retro|status|init|tips]

ship

session-indexer ship pipeline: issue → implement → review → merge → close. Usage: /ship [--yes|-y] [issue-number | title]

AI & Automation Listed

grill-me

Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".