Claude Code reads settings from five levels — managed settings, CLI flags, project local, shared project, and user — where plain values are overridden by higher levels while list keys like permissions.allow merge across scopes. This guide covers each file's role, the allow/deny/ask rule syntax, and how to verify your settings with /status and claude doctor.
A single @Claude in Slack turns a bug report into a cloud-run Claude Code session. But there are now two paths: Pro/Max stays on the original Claude Code in Slack (each session runs under an individual account), while new or migrating Team/Enterprise setups should look at Claude Tag (shared org identity, admin-configured access and spend). Check your plan before setting anything up.
Sub-agents are specialized assistants that work in their own context window: a single Markdown file defines their system prompt, tools, and model. Claude delegates automatically based on the description field, or you can @-mention to force one. This post breaks down the frontmatter schema, background execution and nested spawning, permission inheritance rules, and when not to use them.
In a climbing RAG system, 'recommend the next route' (progression) and 'recommend a similar route' (similarity) were conflated by a single hasSimilarRouteIntent() function, causing recommendation quality to collapse. The fix is a two-stage intent classification with a Regex Fast Path + LLM Fallback.
The RAG system's extractRouteReference() used a for...return pattern that grabbed only the first match — so when a user provided five completed routes, only one was used. The fix evolves through three layers: rule-based multi-entity extraction, user profile aggregation, and embedding centroid.
Query: 'I just sent Beauty in the Mirror 5.11b — recommend routes of similar difficulty.' The results came back full of routes with similar-sounding names, not similar grades. Root cause: dense embeddings compress multiple attributes into a single vector, and the rarity of the route name drowns out the grade signal. The fix: three layers of defense — metadata pre-filtering, query rewriting, and score fusion.
Biome does the work of ESLint + Prettier in a single tool, running 10–20x faster with far less configuration. DaoDao uses it across an entire monorepo — lint and format in one pass.
AEO (Answer Engine Optimization) is a content strategy aimed at AI search engines like Perplexity, ChatGPT Search, and Google AI Overview. The core idea is to make your content the easiest source for AI to cite — not just another link in the results page.
SEO is more than keywords. Structured data (JSON-LD), Open Graph, hreflang, and robots.txt are the technical optimizations that actually help search engines understand your content. This guide walks through a complete implementation using an Astro blog as the example.
BullMQ is the most mature job queue in the Node.js ecosystem, backed by Redis, with support for priorities, retries, scheduling, and delayed jobs. DaoDao uses it to handle notification delivery and practice auto-completion scheduling.
Celery is Python's go-to distributed task queue, using Redis or RabbitMQ as a broker to offload long-running work to the background. DaoDao's AI service uses it to handle async tasks like LLM feedback generation.
Global skills live in ~/.claude/skills/, but they go missing in new sessions or the Desktop App? The problem usually isn't a missing file — it's that the skill descriptions aren't being loaded into context. This post clarifies the CLI vs Desktop App differences, the role of settings.json, and the most reliable fix.
ClickHouse is a column-oriented OLAP database that scans hundreds of millions of rows in seconds. DaoDao uses it to record user behavior events for the AI recommendation engine's feature engineering, letting PostgreSQL focus on transactional data.
D1 is Cloudflare's serverless SQLite database that binds directly to Workers, supports full SQL (JOINs, transactions), and handles automatic backups. It's well-suited for small-to-medium relational data needs — NobodyClimb uses it as its primary database.
KV is Cloudflare's globally distributed key-value store. Reads are served from the nearest edge node with extremely low latency. It's ideal for caching, feature flags, and ephemeral data — but writes are eventually consistent.
R2 is Cloudflare's object storage service — S3-compatible API, zero egress fees, and native Workers binding. Stop worrying about bandwidth bills for media-heavy applications.
Cloudflare Workers uses V8 Isolates instead of containers — no cold starts, global edge deployment, and direct access to D1, R2, KV, and AI via Bindings. Great for APIs, SSR, and lightweight backends; not suited for CPU-heavy work.
Docker lets you bundle your application together with its environment, eliminating the 'works on my machine' problem. Combined with multi-stage builds and Compose, it's an essential tool for modern backend deployment.
Expo turns React Native development from 'environment setup hell' into a state where you can just start writing logic. Expo Router brings file-based routing that dramatically lowers the barrier for web developers making the switch. Both DaoDao and NobodyClimb use it to ship across iOS and Android.
Express is the most mature Web framework for Node.js, with a rich middleware ecosystem and abundant learning resources. Paired with TypeScript and a clear layered architecture, it remains a justifiable choice in 2026.