Systematic QA of CLI tools and pipelines across multiple real workspaces using SFDPOT heuristics. Executes structured test flows, evaluates consistency oracles, collects evidence, and produces a structured bug report with P1/P2/P3 priorities and a release readiness verdict.
Turn rough ideas into clear, validated designs through focused questions, practical options, trade-off analysis, and approval checkpoints.
30/60/90-day plans, a 45-item first-week checklist, buddy/mentor ops, weekly 1:1 question lists, and 7 onboarding failure patterns with fixes. Table-based Markdown you paste straight into Notion or your team wiki.
I've managed thousands of pull requests across open-source and enterprise repos — branching strategies, CI debugging, merge conflicts, and review workflows. This skill encodes that entire pipeline so you can automate your PR lifecycle through natural language, just tell me what you need.
DriftGuard analyzes a repository for dependency and API upgrade impact, identifies affected code, applies targeted migration changes, and validates the result with tests. It returns a structured migration result with changed files, diff, migration report, test results, and PR-ready summary. Runs with Claude Agent in Capafy and supports terminal/CI workflows.
A scan tells you what is wrong. This tells you what to do. Same engine as the ADA Website Risk Scanner — 14 WCAG 2.2 AA check families. But instead of a defect list, you get a work plan: findings grouped into batches, ordered by exposure reduced per hour of developer time, each with before/after code, effort estimate, required skill, and a verification step. Three phases. Quick wins first. A project manager can assign it as-is.
Wraps each phase of a long AI task in a start-check / work / end-check bracket — and re-anchors the original instructions at every phase boundary so the agent cannot drift from its rules or skip verification as the session grows longer.
Turn design debt — five button colors, every page redrawn, components reinvented in every PR — into a design system engineers actually adopt. This is a six-step SOP: inventory audit, semantic tokens before components, a core component library, design-to-code parity, an adoption playbook, and a governance model. Built to stop a Figma library nobody uses and a shipped system that rots into an unmaintained museum.
Forces AI agents to prove a task is actually done before declaring it complete. 4-phase gate: instruction reconciliation, evidence anchoring (values only readable from the actual output), self-scoring (A/B/C/D), and reverse witness check. Eliminates "done" declarations that aren't.