llm wiki maintainer 1.1
by Roy Yuen
Turn your AI agent into a digital librarian that builds and audits a persistent markdown knowledge base.
Ship agent workflows in 30 seconds. Browse 1,500+ expert-built and security scanned skills. Browse skills
THE AGENSI STORE
22 skills found
by Roy Yuen
Turn your AI agent into a digital librarian that builds and audits a persistent markdown knowledge base.
Teach your AI agent to read, search, and structure your Obsidian Vault using Wikilinks and Frontmatter standards.
by Al1as
Map the geometry of system failures to transform edge-case chaos into structured architectural governance.
by loreto
Builds the organizational memory schema your AI agent needs to answer why — capturing decision provenance, causal chains, and event context that embedding-based retrieval permanently discards.
by loreto
Architects the right retrieval strategy for every query — teaching your agent when to use RAG, a knowledge graph, or a temporal index instead of defaulting to vector search for everything.
by loreto
RAG fails quietly. It retrieves documents, returns confident-looking answers, and misses the question entirely — because the question required connecting facts across documents, reasoning about sequence, or tracing causation. This skill gives you a five-question diagnostic checklist that classifies any failing query as either RAG-safe or structurally RAG-incompatible, then maps it to the specific failure pattern and the architectural fix that resolves it.
by tudor
Build a full-stack AI chatbot trained on your own documents across any industry — legal, healthcare, e-commerce, HR, finance, real estate, insurance, education, cybersecurity, government, and more.
by Nex AI
Deploy a structured, long-term memory palace for AI agents on Raspberry Pi via MCP and ChromaDB.
by Nex AI
Deploy a self-hosted, private RAG system with pgvector, Ollama, and a Telegram interface for your personal notes.
Figure out why your Vercel build or deploy failed without scrolling the whole log. Reads the build log plus your package manifest and framework config to pinpoint missing modules, Node and package-manager mismatches, missing env vars, monorepo root mistakes, and serverless/edge runtime errors, with the likely cause and a fix for each.
An adversarial reviewer for AI-written code changes. It pressure-tests a pull request or diff for untested branches, silent behavior changes, missing edge cases, over-confident code that only looks right, and weak tests, then returns a PASS / REVISE / BLOCK verdict before the change merges.
Reviewer left comments and your PR is stuck? Find the #1 blocking comment and get a finished reply — acknowledge, the fix, what to test — written to move the reviewer to approve.
Build stateful AI agents with persistent memory, SQLite, and cron scheduling on Cloudflare's global edge network.
A retrieval architect that diagnoses why RAG returns confident-but-wrong answers, picks the right context architecture (RAG vs knowledge graph vs structured/temporal retrieval) instead of defaulting to vector search, and designs the institutional-memory schema embeddings throw away.
Automate the complete deployment of Astro projects on Cloudflare Pages: configuration, CI/CD with GitHub Actions, edge functions, SSL domains, and SSR error resolution.
by Shandra
Tests AI agents, prompts, and agent skills against edge cases, unsafe behavior, output failures, permission risks, escalation gaps, memory leaks, and marketplace-quality weaknesses.
by loreto
Give AI agents the ability to trace decision chains, reconstruct causal sequences, and reason over complex event timelines spanning months or years.
Turn complex system documentation into structured, agent-accessible knowledge bases optimized for MCP and AI tools.
by LocoLoboZ
Automate the ingestion, indexing, and maintenance of a dual-vault Obsidian knowledge base with strict traceability.
An adversarial gate that audits an AI eval or test suite — LLM-judge rubrics, datasets, regression tests, metrics — for gameable criteria, data leakage, missing edge cases, and non-determinism, then returns one PASS/REVISE/FAIL verdict.
Write a technical spec that lets reviewers find the flaw before the code does — with data models, edge cases, and failure modes explicit.
by John Barros
Evaluate and plan the migration of vision inference pipelines to native OpenCV 5 DNN CPU execution.