This skill should be used to periodically defragment a multi-app/multi-service codebase — both CODE (duplicate deploy targets, colliding bindings, stale forks) and CONTEXT (parallel spec conventions, orphan docs, scattered context packages) — on any platform (Cloudflare, Railway, Vercel, Fly, Render, Docker Compose). Converts the vague "things are getting messy" feeling into specific, located, severity-ranked findings. Detect-only — does NOT auto-consolidate. Apply on a monthly cadence, before any risky deploy, after a migration, or whenever canonical-source ambiguity is suspected. Core principle — agentic coding fragments state faster than humans consolidate it, so drift accumulates silently until a deploy fires from the wrong place or an agent onboards from the wrong context.
This skill should be used when making SEO, AEO (Answer Engine Optimization), or search visibility decisions. Apply expert perspectives (Eli Schwartz, Mike King, Lily Ray, Rand Fishkin, Cyrus Shepard) to diagnose what actually matters for search performance — programmatic page generation, structured data, title tags, E-E-A-T signals, and AI Overview optimization. Use when building pages for search visibility, adding structured data, evaluating whether programmatic pages have search value, or optimizing for AI-generated answers.
This skill should be used when producing content (newsletter posts, blog posts, LinkedIn posts) from existing corpus material. Discovers relevant context from the knowledge graph, selects the right content framework, assembles a draft against a spec, then runs an eval loop of anti-slop checks until the output clears quality gates. Built from real content production pipelines with 142 automated anti-slop tests and the eval-loop methodology.
This skill should be used when making architectural decisions, writing specs, or reviewing decisions that contain "future work", "v2", "simpler for now", "out of scope", or complexity claims. Verifies assumptions are grounded and catches corner-cutting disguised as pragmatism. Applies to code, specs, data models, auth flows, and context structures.
This skill should be used when processing raw content (transcripts, documents, notes, current conversation) into structured knowledge nodes for a Context OS. Extracts atomic concepts, creates nodes with complete frontmatter and [[wiki-links]], and routes each node to the correct knowledge_base/ domain. Use when user says "ingest this", "process into knowledge base", "turn this into nodes", or provides raw content to structure. Uses tags consistent with existing graph nodes; new concepts start as status emergent.
This skill should be used when a user wants to build their first Context OS or kick off initial setup of a knowledge graph system. Guides through a 10-minute flow — assess content, create the two-layer directory structure, generate CLAUDE.md, ingest first content, and verify compounding works. Adapts to blank-slate vs existing-content starting points. Use when user says "set up a context OS", "get started with context OS", "build a knowledge graph from scratch", or "quickstart".
This skill should be used when decomposing a spec into a multi-agent implementation plan with dependency ordering, parallelism decisions, contract testing, and verification strategy. Applies evidence from 5 verified multi-agent builds (sequential handoff, parallel fanout, mixed waves, corpus-wide single-agent, phased query engine) to prevent the common failure modes — integration surprises, context loss, silent failures, and over-specification overhead. Use when the implementation involves 3+ agents, has parallelization opportunities, or requires handoffs across context windows.
This skill should be used when a specific quality problem (UX, data, architecture, feature) needs systematic diagnosis and iterative fixing toward a defined target. Traces symptoms to root causes, sets measurable targets with automated backpressure (unit tests, Playwright, LLM-as-judge, or rubric scoring), and iterates until targets pass. Use when user reports a quality gap ("this is a 3/10"), when shipping a feature that needs a quality bar ("what would 10/10 look like?"), or when a class of problems keeps recurring. Core pattern — symptom → generalize → root causes → targets → fix → verify → loop. Step 0 routes predictive/scoring problems OUT to eval-driven-scoring.