mturac - Overview

• 🔍 content-pulse — Semantic Decay & Freshness Engine for PayloadCMS v3. Detect stale dates and outdated version references before your readers do. 14/14 tests passing.
• 🔍 contentpulse-strapi — ContentPulse for Strapi v5. Lifecycle hooks + admin widget for content freshness analysis.
• 🔍 contentpulse-contentful — ContentPulse for Contentful. Sidebar app with Forma 36 design system integration.
• 👻 simulacra — Ghost personas review your code before it ships. Find edge cases, race conditions, and business logic bugs before production.
• 🧠 sparse-attention-viz — MiniMax-style Top-k sparse attention visualizer. CPU-only, no GPU required.
• 🪑 claude-roundtable — Multi-agent governance for Claude Code. Council deliberates, votes, dispatches, and enforces quality gates.
• ⏱️ leyla-scheduler — Durable, session-aware task scheduler in Rust. Jobs survive disconnects.
• 🔎 skill-hunter — Pre-execution layer that makes agents check for existing skills before building from scratch.
• 🛡️ promptguard — Audits prompts as behavioral contracts. Pre-write guard for agents that ship code.
• 🧠 recall-mcp — Shared brain for AI agents. SQLite-backed persistent memory over MCP.
• 👵 moooom-claude — 10 cultures of moms nagging your Claude Code to drink water and sit up straight.
• 🐍 hermes-supercode-skills — 13 production-grade Claude Code skill modules: database, auth, observability, infra, security, deployment, debugging, API design, and more. Also available for OpenAI Codex.
• 🧰 pluginpool — Ten focused Claude Code plugins for everyday developer productivity. Each one is its own MIT-licensed repo: commit-narrator, pr-storyteller, test-gap, deps-doctor, env-lint, secret-guard, standup-gen, todo-harvest, flaky-detector, changelog-forge. 89 hermetic tests · Python 3 stdlib only.
• ♿ a11y-ci — Automated accessibility audits for Claude Code. Static WCAG 2.1 checks on HTML, JSX/TSX, and Vue SFC — violations annotated in-source with line numbers and fix suggestions.
• 📐 adr-sync — Keeps Architecture Decision Records aligned with actual code changes. Detects drift between ADRs and implementation before it compounds.
• 💰 agent-budget — Track token spend and enforce cost budgets for LLM agent runs.
• 🔗 api-contract — Validates frontend API calls against backend schemas, detects breaking changes before deploy, generates typed TypeScript clients.
• ⚡ build-cache-analyzer — Analyzes build cache hit rates across CI runs, finds what's busting your cache, and optimizes build times.
• 🏺 code-archaeologist — Uncovers intent and evolution in legacy codebases through git history, comments, and structural patterns.
• 👁️ codewatch — Automated PR review and security auditing for Claude Code.
• ✅ config-schema-validator — Validates YAML, TOML, and JSON config files against schemas and suggests auto-fixes for common misconfigurations.
• 🗺️ contract-atlas — Maps the implicit contracts in your codebase. You find out about them when they break — this finds them first.
• 💸 cost-watch — Token spend tracking and budget alerts for Claude Code sessions.
• 🚫 dead-end-finder — Discovers unreachable code, unused exports, and orphaned API endpoints that accumulate silently.
• 📦 dep-drift — Detects when your lockfile diverges from package.json, flags silent transitive dependency updates, and catches license incompatibilities before they become compliance issues.
• 🕸️ dependency-graph-viz — Builds import dependency graphs, detects circular dependencies, and analyzes deep chains that create brittle architectures.
• 🚀 deploy — Deploy to Vercel, Railway, Fly.io, or Render directly from your editor.
• 🍴 devfork — Git branch for your entire running dev environment. Switch context without killing your server.
• 📄 docs-sync-checker — Detects documentation drift: when docs describe functions, CLI commands, file paths, or config keys that no longer exist or have changed.
• 🧪 eval-kit — Assertion-based prompt evaluation for LLMs. Test AI outputs like unit tests, run from the terminal.
• 🚩 flag-ops — Manage feature flags: scan for orphaned flags, track rollout status, and safely remove flags when done.
• 🎯 flaky-test-hunter — Detects, quarantines, and fixes flaky tests by analyzing CI run history and test timing patterns.
• 🌍 i18n-sync — Keeps translation keys in sync across locales. Detects missing, extra, duplicate, and untranslated keys. Generates type-safe stubs and prunes orphaned entries.
• 🚨 incident — Production incident response for Claude Code. Triage fast, diagnose deep, fix correctly, document thoroughly.
• ⚖️ license-guard — Enforces license compliance policy on dependencies, generates SBOM, and blocks incompatible licenses before they reach production.
• 🧹 llmfmt — Normalizes LLM output: extracts JSON, code blocks, strips markdown, removes thinking tags, and unwraps common prose prefixes.
• 🏗️ mcp-scaffold — Scaffold production-ready MCP servers in seconds — stdio, multi-tool, and HTTP templates included.
• 🧠 memex — Personal semantic memory for claude.ai. Save notes, links, code snippets, and ideas — search and recall them in any conversation via a knowledge graph.
• 🗄️ migrate-safe — Analyzes database migrations for destructive operations and safety issues before you run them.
• 🔍 perf-lens — Identifies N+1 query patterns, redundant React re-renders, and bundle bloat before they hit production.
• 🔬 promptlab — Zero-backend visual prompt engineering studio. Multi-model comparison, variable interpolation, eval assertions, and shareable URLs.
• 🔄 refactor-preview — Simulates refactoring impact with blast radius analysis before applying changes — see exactly what would break.
• ⏮️ replay — Records and replays Claude Code agent runs. Every bash command, file read/write, and tool call logged to SQLite. Inspect, diff, and audit any past session.
• ⚗️ schema-forge — Generates Zod schemas from JSON examples, OpenAPI specs, and JSON Schema definitions.
• 📝 semantic-release-notes — Auto-generates human-readable changelogs and release notes from conventional commits and PR titles.
• 🔭 test-scout — Finds untested code paths and generates targeted unit tests by analyzing coverage gaps and control flow.
• 🏷️ type-coverage — Tracks TypeScript type safety across your codebase. Surface where any is spreading.
• 🎨 open-design — Local-first open-source alternative to Anthropic's Claude Design. 19 skills · 71 brand-grade design systems · generates web, desktop, mobile prototypes, slides, images, and video. Runs on Claude Code, Codex, Cursor, Gemini, OpenCode, Qwen, Copilot, Hermes, and Kimi CLI.
• 🔬 proofbox — Verify AI-generated technical recipes before engineering teams trust them.
• 🌊 weave — Visual AI-agent flow builder with real LLM execution and Python export.
• 🔀 mcpx — MCP gateway that proxies and routes multiple MCP servers behind one endpoint.
• 🛂 mcp-guard — Policy firewall and security scanner for MCP servers and agent tools.
• 🧹 debtlint — Vibe debt scanner: AI attribution and code ownership tracker.
• 🎭 multichar-studio — Local-first multi-character AI scene studio with shared and subjective memory.
• 🧰 awesome-claude-code-toolkit — The most comprehensive Claude Code toolkit: 135 agents, 35 curated skills, 42 commands, 176+ plugins, 20 hooks, 15 rules, 7 templates, 14 MCP configs, 26 companion apps, and 52 ecosystem entries.

LinkedIn

• 🗡️ Çift Yüzlü Katana: Yapay Zeka Dönüşümlerinin Gerçekçi Bir Analizi — AI transformations realistic analysis. The 5 illusions that compound into expensive, fragile systems.
• 📄 LinkedIn Articles — All published articles
• 📊 LinkedIn Documents — Research papers and technical documents

Dev.to — All 39 Articles

Scale Wars — The Architectural Secrets of Tech Giants

• Scale Wars — The Architectural Secrets of Tech Giants
• #1 Netflix: The Company That Killed the Monolith
• #2 Uber: How They Processed 100 Billion Events Per Day
• #3 Amazon: Two-Pizza Teams and the SOA Manifesto
• #4 Airbnb: Data Mesh and the Death of the Central Data Team
• #5 Twitter: The Fan-out Pattern and the Architecture Behind 140 Characters
• #6 Spotify: The Squad Model and the Power of Golden Paths
• #7 What We Learned from the Giants (Series Finale)

Back to Code — A 15-Episode Technical Novel About Waking Up From the AI Illusion

• I Wrote a 15-Episode Technical Novel About Waking Up From the AI Illusion
• Ep 01: The Invoice of Illusion and the Black Friday Crash
• Ep 02: Autopsy — The Lie That Looked Flawless
• Ep 03: The Lost Craft — TDD and False Confidence
• Ep 04: Forgetting the Machine — Big O and the Performance Tax
• Ep 05: The Revenge of Context — DDD and Bounded Contexts
• Ep 06: State Hell and Idempotency
• Ep 07: The Lies of Mocks — Reality with Testcontainers
• Ep 08: The Illusion of Type Safety
• Ep 09: CI/CD Pipeline and Flaky Tests
• Ep 10: The Security Vulnerability Factory
• Ep 11: The Legacy Code Mine — Strangler Fig Pattern
• Ep 12: Observability — From Log Spaghetti to Traces
• Ep 13: Event-Driven Architecture — Kafka and the Async World
• Ep 14: Technical Debt Credit Score — Measuring the Unmeasurable
• Ep 15: The New Manifesto — Master and Apprentice (Season Finale)

AI Agents & LLMs

• eoc: Building the Operating System for OpenAI Codex — 230+ Skills, 60 Agents
• Why AI Agents Fail?
• Your Agent Isn't Reflecting. It's Performing Reflection.
• How I Stopped My AI Agent From Reinventing the Wheel
• Stop Your AI Agent From Building Tools That Already Exist
• Hermes vs OpenClaw: Which AI assistant would you actually trust?

LLM & Memory Systems

• The Context Window Lie: Why Your LLM Remembers Nothing
• Why Versioned SQL Beats Vector RAG for Agent Memory Systems
• Strategic LLM Adoption: A Director's Guide to Fine-Tuning Models
• I Got Access to 136 AI Models for Free — NVIDIA NIM API Deep Dive

Software Engineering

• We Ship to Production Without Tests. Here's How It Destroyed Us.
• I built a product in one AI session. Here's the system that made it ship right.
• Remote Work Didn't Break Productivity — It Broke Human Connection

Major OSS projects

• 🎭 microsoft/playwright — dot reporter fix for parseable GitHub annotations.
• 🌐 google-gemini/gemini-cli — Google's official Gemini terminal agent. CLI ergonomics fix (session-ID rendering in resume messages).
• 🦙 ollama/ollama — local LLM runtime. Docs fixes (GPU FAQ link, Linux context-length config) and a ggml LoongArch quantization source PR.
• 🔎 elastic/elasticsearch — ESQL InvalidMappedField equality metadata fix.
• 📊 elastic/kibana — Fleet UI: use "Failed" label for failed integration status.
• 📦 elastic/elastic-package — system-test query for ignored fields.
• 🛰️ elastic/elastic-agent — os.Remove error guards in symlink/marker/enrollment cleanup paths.
• ☁️ cloudflare/wrangler-action — docs: add missing install and build steps to the canonical example.
• 🧱 strapi/strapi — four reliability fixes: review-workflows stages for unsaved locales, media-url refresh on replacement, null adminUserOwner in api-token service, and content-manager locale resolution for non-i18n delete paths.
• 📈 grafana/grafana — frontend reliability fixes across dashboard variables, logs, legends, query editors, and image-render export flows.
• 🛒 medusajs/medusa — types fix: compound-word pluralization handling for uncountable suffixes.
• 🛡️ open-webui/open-webui — null-check in upload_image to prevent crashes when SSRF protection blocks a fetch.
• ☸️ kubestellar/console — store fix: use make([]T, 0) instead of var x []T for nil-safe JSON.
• 🛂 envoyproxy/ai-gateway — per-backend HTTPRoute cluster-name handling.
• 🤖 langgenius/dify — error class cleanup (removed unnecessary | None from typed error returns).
• 🤓 Aider-AI/aider — accept model-settings-file in benchmark mode.
• 🚦 maximhq/bifrost — return proper 400 for schema parse errors.
• 🔐 project-zot/zot — skip DynamoDB table creation when tables already exist.
• 🐙 oraios/serena — empty projects config-key handling.
• 🎨 shadcn-ui/ui — shrink-0 fix on base-luma SelectContent so the component sizes correctly inside flex layouts.
• 🚀 raycast/extensions — productivity-extension fixes for Jira, VS Code recent projects, Google Workspace, 1Password, Sentry, Spotify, Browser Bookmarks, Git Repos, ccusage, and more.
• ⚙️ actions/github-script — feature: working-directory input to change script execution directory.
• 🧱 twbs/bootstrap — docs and Sass fixes for carousel API wording and list-group action colors.
• 🌐 vercel/edge-runtime — cookie parsing fix for percent-encoded Set-Cookie values.
• 📦 pnpm/pnpm — package-manager reliability fixes: trusted-publisher provenance checks, non-root resolutions warnings, fish shell setup location, and complete global-update summaries.
• 📚 pnpm/pnpm.io — docs fixes for version-pinned v11 examples and zsh completion setup.
• 🕷️ firecrawl/firecrawl — scraper fix: pass fullPage option to fire-engine request.
• ✨ refined-github/refined-github — fix on the most-downloaded GitHub UX-improvement extension.
• 🧩 gfazioli/mantine-split-pane — resizer fix: fire onResizing and onResizeEnd on double-click reset.
• 📝 refactoringhq/tolaria — desktop markdown knowledge-base app fixes: responsive status-bar stacking, Kiro agent-target selection, and local-only git remote handling.

Agentic developer tools

• 🌐 browser-use/browser-use — browser-agent reliability patches around remote session lifetime, video artifacts, and structured tool-call parsing.
• 🧰 modelcontextprotocol/servers — runtime dependency and filesystem-tool behavior fixes for official MCP servers.
• 🧪 OpenHands/OpenHands — enterprise and repository-search reliability fixes.
• 🧠 cline/cline — VS Code and CLI agent fixes: completed-task resume state after hooks, command approval handling, context overflow detection, TLS opt-out handling, skill-picker render keys, settings/account setup flow, and config-view hook dependencies.
• 🟣 Kilo-Org/kilocode — CLI and VS Code agent fixes across permission docks, diff previews, export dialogs, startup migrations, paste summaries, offline model fetches, reasoning effort options, subagent prompts, autocomplete, and dependency-context filtering.
• 🍒 CherryHQ/cherry-studio — desktop AI client fixes for MCP structured content, cron/local-time tool responses, miniapp URL refresh, CherryIN provider aliasing, and thinking-segment stream handling.
• 🧩 opencode ecosystem — opencode.nvim (edit-diff buffer cleanup, immediate interrupt commands), opencode-manager (repo-action tooltips, config-refresh model-form preservation), and anomalyco/opencode (run-root cwd, hyphenated MCP tool-id normalization).
• 🧰 openclaw ecosystem — openclaw/openclaw (pnpm baileys/libsignal git-deps, agent-runtime inheritance) and openclaw/wacli (NativeFlowMessage button extraction).
• 🛠️ MCP ecosystem — tosin2013/mcp-adr-analysis-server (issue templates), IN3PIRE/github-health-monitor-mcp (clearer rate-limit errors).
• 🪟 Claude Code tooling — YishenTu/claudian (recover from invalid settings JSON), mksglu/context-mode (atomic native-binary swap), slopus/happy (missing-agent-key recovery), steipete/CodexBar (Kimi K2 provider note).
• 🌀 Agent infra — manaflow-ai/cmux (install Gemini feed hook with BeforeTool), getpaseo/paseo, floatpane/matcha, recurram/recurram-zig (workflow-token permissions).

Heaviest external engagements

• 🔧 nexu-io/open-design — design-tooling daemon, largest external contribution surface (12+ merged + open PRs): zip import-failure surfacing, manual edit tabs, Claude smoke-test stream-json wiring, draw-overlay scroll, comment-marker alignment, picker hints, design-files panel grouping, memory-editor reveal, plugin-publish footer, and more.
• 🎬 nexu-io/looper — sequencer for long-running agent loops. PR-merge-blocker UI, pause/unpause commands, timing-sensitive test relaxations.

Skills distribution

Authored recsys-pipeline-architect and shepherded it into ~25 public skill / agent registries spanning the Anglophone, Chinese, and Turkish Claude communities: vercel-labs/skills, wshobson/agents, github/awesome-copilot, davila7/claude-code-templates, karanb192/awesome-claude-skills, VoltAgent/awesome-agent-skills, ComposioHQ/awesome-codex-skills, RoggeOhta/awesome-codex-cli, ikaijua/Awesome-AITools, Prat011/awesome-llm-skills, skillmatic-ai/awesome-agent-skills, heilcheng/awesome-agent-skills, kodustech/awesome-agent-skills, libukai/awesome-agent-skills (CN), laolaoshiren/claude-code-skills-zh (CN), travisvn/awesome-claude-skills, BehiSecc/awesome-claude-skills, ComposioHQ/awesome-claude-skills, rohitg00/awesome-claude-code-toolkit, jqueryscript/awesome-claude-code, GetBindu/awesome-claude-code-and-skills, spencerpauly/awesome-cursor-skills, shanraisshan/claude-code-best-practice, jeremylongshore/claude-code-plugins-plus-skills, Chat2AnyLLM/awesome-repo-configs, sickn33/antigravity-awesome-skills, affaan-m/everything-claude-code, gmh5225/awesome-skills.