systeminterview

A Socratic tutor that teaches you how AI agents work by making you build one — from a raw prompt to a full agent loop with tool calling, all in TypeScript. You type the load-bearing code; the tutor guides, quizzes, and reviews.

3 skills · 6 commands · hooks

Tutored, constrained build of Ruby web servers from raw sockets to C10K. Claude Code acts as a Socratic tutor: it quizzes you, reasons about your answers, and makes you type the load-bearing code yourself while it handles glue and review. Graded against a cgroup-constrained benchmark.

1 skill · 7 commands · hooks

Tutored, constrained build of Ruby web servers through the PROCESS family only — from a raw TCP socket up to a Unicorn-like preforking server with heartbeats, graceful shutdown, and zero-downtime USR2 restart. Claude Code acts as a Socratic tutor: it teaches the mechanisms, makes you type the load-bearing code yourself, then quizzes you to consolidate once it's built and running — handling glue and review along the way. Verification is local and lightweight (nc, ps, lsof, kill -SIGNAL) — the emphasis is building and the signal protocol, not load testing. A focused pilot of c10k-dojo.

1 skill · 7 commands · hooks

Lead-mode replicant: you lead an agent through database replication on top of SQLite in Ruby. The agent writes the ADR and the code — you make every decision, commit to numbers before the trial, review what it built, and answer for it. Hooks enforce decide-then-build and predict-then-measure.

1 skill · 7 commands · hooks

Tutored, constrained build of a single-threaded reactor (event-loop) server in Ruby, from a blocking accept loop to a nonblocking IO.select reactor that juggles thousands of connections. Claude Code acts as a Socratic tutor: it quizzes you, reasons about your answers, and makes you type the load-bearing code yourself while it handles glue and review. Offline by design.

1 skill · 6 commands · hooks

A tutored coding dojo: build database replication from scratch on top of SQLite in Ruby — leader/follower, a hand-written WAL, quorum and leader election — with a Socratic tutor that makes you type the load-bearing spine and an offline jail that keeps you honest.

1 skill · 6 commands · hooks

45 advanced engineering skills: agent designer, agent workflow designer, RAG architect, database designer + schema designer + SQL assistant, migration architect, observability designer, dependency auditor, changelog generator, API design reviewer, API test suite builder, CI/CD pipeline builder, MCP server builder, skill security auditor, skill tester, performance profiler, focused-fix, browser-automation, full-page-screenshot, git-worktree-manager, monorepo-navigator, codebase-onboarding, interview-system-designer, runbook-generator, spec-driven-workflow, secrets-vault-manager, env-secrets-manager, pr-review-expert, self-eval, tc-tracker, feature-flags-architect, kubernetes-operator, chaos-engineering, ship-gate, slo-architect (error-budget + multi-window burn-rate alerts per Google SRE Workbook), tech-debt-tracker, agent-regression-evals, coding-agent-rollout, commit-craft, agent-run-forensics and i18n-localization. Agent skill and plugin for Claude Code, Codex, Gemini CLI, Cursor, OpenClaw.

48 skills · hooks

Product discovery skills for PMs: ideation, experiments, assumption testing, feature prioritization, and customer interview synthesis.

13 skills · 5 commands

Build an immersive scroll-scrubbed landing page where a pre-rendered camera flies from outside each scene into its interior, then flows on to the next with no cuts. Interviews the user for topic, story beats, and brand kit; generates cohesive scenes + seamless camera clips with Higgsfield; wires a portable, framework-agnostic scrub engine.

1 skill

Run a user story mapping workshop with adaptive questions and structured output.

1 skill

Sits in front of Claude Code and fixes the brief before the code. An interview scores how vague your request is, and a score above the bar blocks spec generation until you pass force explicitly. When an acceptance criterion defines a verify command or an expected-output assertion, those values are omitted from the worker's contract block, with no flag to put them back, so the worker is asked for the outcome rather than handed the assertion. Redaction of those values elsewhere is literal over five encodings, so a reshaped copy can still get through; that gap is tracked in a public issue.

26 skills · 1 MCP server · hooks

Bundle of 12 LinkedIn marketing skills for Claude Code and Codex with verified 2026 hook formulas, comment + reply templates that earn author replies, a unified humanizer (rewrite + `--mode audit` pre-publish check, plus bundled emoji-detector, detector-spread tester, rule-explainer sub-tools), profile rewriter, content planner, employee advocacy playbook, thread monitor (warm-reply window author-reply tracking), and engager analytics (likers + commenters ICP segmentation), interviewer (Story Bank of receipts, turning points and positions).

13 skills