yamanidev

Workflow for designing, querying, and reasoning about databases — schema modeling, normalization, keys/constraints, indexing strategy, query patterns, EXPLAIN plans, transactions and isolation. Covers general database concepts, relational/SQL behavior, engine-specific quirks, non-relational systems, and workload shapes. Defaults to relational; covers non-relational when the user is working there.

Mentorship workflow for conceptual DevOps and infrastructure questions, design discussions, tool selection, deployment strategy, observability planning, and troubleshooting production systems. Covers cloud, CI/CD, Kubernetes, Terraform, monitoring, incidents, and SRE topics, calibrated to teach the why alongside the what. NOT for application code changes (use ship) or code review (use review-code)

Workflow for drafting a logo mark for a side project or utility, producing a self-contained HTML gallery of 4–6 concept directions per round — each rendered in SVG at large, medium, and favicon sizes on both light and dark backgrounds. The user opens the gallery in a browser, picks favorites by short letter code, and converges through subsequent rounds of variations. Forces a written brief before

Workflow for compacting the current conversation into a handoff document that another Claude Code session can pick up from later. Produces a single Markdown file capturing the goal, current state, in-flight work, decisions made, open questions, paths touched, and a recommended next-session skill — referencing existing artifacts (commits, PRs, diffs, plan docs, tickets, ADRs) by path or URL rather

Workflow for understanding and operating Linux — kernel, processes, memory, filesystems, networking, init, permissions, and the distinctions between general OS concepts, POSIX, Linux-specific behavior, and distro-specific quirks. Calibrates between teaching the why (mental models, system internals) and helping operate real machines (configuring servers, debugging a workstation). Does not handle cl

Read-only workflow for code review, PR review, or feedback on a diff, branch, or specific files. Produces structured, prioritized feedback with blockers, should-fix items, nits, questions, and notable strengths — does not modify code. NOT for making changes (use ship for that). MANUAL INVOCATION ONLY: invoke this skill ONLY when the user explicitly types /review-code. Do not auto-invoke based on p

Workflow for extending, fixing, or evolving existing production code — bugs, features, investigations, refactors, or shipping changes that touch APIs, data models, integrations, business logic, or user-facing behavior. NOT for greenfield prototypes, throwaway scripts, pure exploration, or code review (use review-code for that). MANUAL INVOCATION ONLY: invoke this skill ONLY when the user explicitl

Workflow for turning a feature, change, or bug into a well-scoped ticket for a development team. May read code to understand the system well enough to write a good ticket — but the output is product-level, not an implementation plan. Produces concise tickets focused on the problem, behavior, and acceptance criteria. Does not implement the change (use ship). MANUAL INVOCATION ONLY: invoke this skil

Workflow for discussing product and UX decisions — user flows, interaction design, information architecture, mental models, feature framing, and the product trade-offs that sit between what users want and what the team can build. Engages with technical context when relevant, but the focus stays on the product and the user, not the implementation. Does not write tickets (use write-task) and does no

Workflow for writing tests against requirements — verifying that a feature, endpoint, or function behaves correctly according to its specification, not according to its current implementation. Reads the spec/requirement and the surface being tested (signatures, contracts, observable behavior); deliberately avoids mirroring implementation logic into the tests. Suitable for adding coverage after the

Workflow for authoring or revising any Claude Code configuration — skills (SKILL.md), CLAUDE.md guardrails, settings.json (permissions, hooks, env, model), sub-agents, slash commands, MCP server entries, plugins, and the install or sync scripts around them. Operates from working knowledge of LLMs, agent harnesses, and context engineering so the configuration it produces leverages how Claude Code a