A personal collection of skills for AI coding assistants — covering code review, DX/UX analysis, TDD, holistic debugging, and developer productivity.
Agent
Independent fresh-context verifier for bug-fix PRs produced by /fix-bug. Receives only the Evidence Record, the reproduction path/command, the bug-notes ledger (read-only), and the PR diff — explicitly NOT the planner's reasoning, the plan.md, or the executor's reasoning. Runs FAILTOPASS (repro now passes), PASSTOPASS…
Agent
Independent fresh-context verifier for feature PRs produced by /autonomous-workflow. Receives only the plan.md (Acceptance Criteria, Requirements, File Changes), walkthrough.md, the PR diff, and the project test command — explicitly NOT the planner's reasoning, the executor's reasoning, or any chat history. Runs…
Agent
Extract evidence from a single Linear ticket — read the ticket, locate affected code, and return an Evidence Record matching the /fix-bug Phase 2 schema. Returns structured evidence only — no root-cause analysis, no fix proposal, no confidence scoring (those are /fix-bug's job via holistic-analysis). Used by…
Agent
Code reviewer for GitHub PRs — your own (self relation) and other people's (cross relation). Runs a pre-merge gate check (description vs. code, CI, unresolved review feedback, self-review signals, docs) then a multi-lens review — correctness, quality, description accuracy, external integrations, holistic…
Agent
Context-isolated root-cause analysis. Runs the holistic-analysis skill in fix mode plus confidence in analysis mode inside a fresh sub-agent context, then returns ONLY a compact Root-Cause Record (root cause, causal chain, evidence, ruled-out alternatives, confidence score, proposed fix direction). The verbose 8-phase…