kb
claudeKnowledge-worker companion over the Brain: cited answers and Markdown deliverables.
8 skills · 1 agent · hooks
Build, maintain, and deploy the Brain: a local, truthful knowledge engine (RAG + taxonomy graph + deterministic marts) over docs + spreadsheets, served via a governed MCP.
Plugin brain from marketplace applied-ai in onetest-ai/applied_skills. Commands read from the repo's manifest — 9 days ago.
brain-maintenanceUse when the user asks to refresh, synchronize, maintain, rebuild changed sources, update the knowledge base, publish a new Brain image, deploy a Brain MCP revision, or roll back an update — safely updates and optionally deploys an existing Brain knowledge product. Orchestrates source registry, visu
corpus-taxonomy-extractionUse when you need to induce a starting taxonomy (intent classes, entities/dimensions, and a metric inventory) from a heterogeneous document corpus (PDF/PPTX/DOCX/XLSX/MD) under a stated analytical goal — e.g. seeding a local knowledge graph, semantic layer, or classification scheme before building d
evals-remoteUse when you need to evaluate a REMOTE, key-authenticated Brain (MCP over HTTP) — reconcile its sources against a corpus inventory export to gate out out-of-scope data (including superseded documents), then score answers for accuracy, completeness and consistency, diffed run to run. Config-driven; w
evalsUse when the brain is built (knowledge.sqlite exists with chunk_topics populated) and you need to generate adversarial eval suites from a VTT/SRT corpus and run them against a FastMCP brain. Two modes — extraction (verbatim quotes via Bedrock Sonnet, recommended) and db-fallback (chunk_topics, smoke
hybrid-retrievalUse when you need to answer a question over one local SQLite knowledge store, at ANSWER time — routing numeric/aggregation claims to deterministic SQL (marts), narrative/qualitative claims to hybrid RAG (FTS5+vector RRF), and taxonomy/relations to graph JOINs, then composing one cited answer. Use wh
knowledge-indexUse when you need to build or query a LOCAL hybrid retrieval index over Markdown — SQLite FTS5 (BM25) + sqlite-vec (embeddings), fused by Reciprocal Rank Fusion. One portable .sqlite file, no server, torch-free (fastembed/onnx). Feed it Docling/plain Markdown; it chunks, embeds, and serves cited rec
knowledge-pipelineUse when the user wants to "build the knowledge base", "index this corpus", "set up retrieval", "create a brain", "get started / onboard", or "answer questions over these docs+spreadsheets+transcripts" — the orchestrator that turns a mixed corpus (documents, transcripts, spreadsheets) into ONE local
obsidian-vaultUse when you need to navigate and answer from an Obsidian vault — follow [[wikilinks]], filter by #tags, traverse MOCs/topic notes, read a note's Related sections and embedded images. For a brain built by this toolkit, the vault is a VIEW of the knowledge.sqlite store (note = section = retrieval chu
tabular-semantic-layerUse when you need TRUTHFUL numeric answers from large/heterogeneous Excel reporting workbooks (calls, KPIs, financials by branch/region/month) — via a config-driven ETL into a columnar store (Parquet/SQLite) and a governed metric layer, instead of RAG/LLM reading cells. Pairs with corpus-taxonomy-ex
visual-parseUse when a corpus has slide decks / diagram-heavy pages (flows, timelines, circle process charts, complex tables) that a text extractor mangles, or meeting recordings whose shared screens carry context a transcript alone would lose. Renders each page to an image, flags the visual ones, has a vision-
Knowledge-worker companion over the Brain: cited answers and Markdown deliverables.
8 skills · 1 agent · hooks
Living documents over the Brain: scheduled, versioned, cited docx/pdf with claim-level lineage.
4 skills
A manager's Epic > Story > Task tree kept current from meetings, calendar and files: cited evidence, dependencies, staleness and asks.
4 skills
Self-learning vector database — HNSW, FlashAttention-3, Graph RAG, hybrid search, DiskANN, and Brain AGI
4 skills · 1 command · 1 agent
Official Convex plugin for Claude Code with bundled Convex skills, the convex-expert subagent for code-writing, a runtime-error monitor, and MCP access for backend development, schema design, real-time features, auth, file storage, scheduled jobs, and AI agents.
16 skills · 1 command · 2 agents · 1 MCP server · hooks
LLM application development with LangGraph, RAG systems, vector search, and AI agent architectures for Claude 4.6 and GPT-5.4
8 skills · 3 commands · 3 agents
Build and deploy on Val Town. Bundles the Val Town MCP server and platform skills (HTTP vals, cron/intervals, SQLite, email, OAuth, React UI, third-party integrations, templates).
11 skills · 1 MCP server
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
Skills for Dataproc.
1 skill
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.