Embeddings
Vector embeddings and similarity
qmd
by MichaelVessia
Local semantic search for docs, notes, knowledge bases. INVOKE THIS SKILL when user: - Asks to "search my notes/docs/vault/obsidian" - Wants to "find" something in their knowledge base - Says "what did I write about X" - Asks "do I have notes on X" - Needs context from their local markdown files - Mentions "qmd" directly - Asks about journal entries, meeting notes, or personal documentation Trigger phrases: "search notes", "find in docs", "search obsidian", "what do my notes say", "look in my vault"
plan-game-design
by jujumelona
Produce a Fabric mod design, request-resolved implementation methods and acceptance-test plan without writing
vault
by vadirn
Personal knowledge management in an Obsidian vault. Use this skill whenever the user wants to save, find, review, or organize knowledge — even if they don't say "vault" or "Obsidian". Triggers on: saving a link/article/video/book for later (creates a reference in 10 references/), distilling a concept or takeaway from something they read/watched (creates a card in 20 cards/), writing down an original idea, observation, or synthesis connecting multiple concepts (creates a note in 30 notes/), searching or browsing what they know about a topic, quizzing or testing recall on saved concepts, listing or filtering cards by tag, resuming or saving progress on a project, checking project status or open checkpoints. Also handles explicit /vault commands (search, card, note, reference, review, cards, projects, start, save). Do NOT use for: Obsidian app settings/UI questions, editing .base files, creating canvas files, general markdown editing, or web search.
tensor-grep
by oimiragieo
Use when searching text in files, codebases, logs, or documents at scale. Use when finding files by pattern, searching massive logs that are too big for CPU regex, extracting specific content from many files, when you need semantic/AST structural code queries, or when you need NLP classification of threats in server logs. Triggers on "search for", "find occurrences", "look for pattern", "search in files", "classify logs", or "structural code search".
research-cross-validator
by tomwangowa
Cross-validate technical claims using multiple independent verification strategies (official docs, counter-examples, source code inspection). Use when a tech-feasibility report, design document, or any technical analysis contains claims that were verified by only one method or one AI session. Triggered by "cross-validate", "verify these claims", "double-check this", or "independent verification".
gather-adaptive-minecraft-evidence
by jujumelona
Gather exact-version Minecraft, Fabric, Yarn, dependency, and project evidence with adaptive retrieval. Use before
paperless
by MichaelVessia
Search and manage documents in Paperless-ngx document management system. Use when the user asks about documents, invoices, receipts, tax forms, bills, or wants to search their document library.
revise-existing-mod
by jujumelona
Inspect an existing mod archive safely and produce a bounded, provenance-preserving revision plan.
find-skills
by costa-marcello
"Discovers and installs agent skills from the open ecosystem and CCPM registries. Use when users ask 'how do I do X', 'find a skill for X', 'is there a skill that can...', 'ccpm', 'claude code skill', 'installed skills', or want to extend capabilities."
esm
by YuukiAS
Comprehensive toolkit for protein language models including ESM3 (generative multimodal protein design across sequence, structure, and function) and ESM C (efficient protein embeddings and representations).
obsidian-semantic-linker
by psycho-baller
Semantically links notes in your Obsidian vault using a local vector database (.nexus/cache.db). It analyzes the content of notes, finds related ideas, and appends a "## Related Notes" section with wiki-links to similar notes. Use when asked to "link my notes", "find related notes", or "process semantic connections".
paper-dive
by G-Eskayo
Socratic reading partner for scientific papers. Ingests a paper and walks the user from plain-English understanding (L0) up to expert-level synthesis (L5) through conversation. Adaptive to the user's analogy domains. Builds a shared lexicon. Pulls related papers from Semantic Scholar / arXiv / scihub.org. Runs challenge and compare modes.
tech-feasibility
by tomwangowa
Use when evaluating whether a specific technology, tool, or approach can solve a given problem before committing to implementation. Triggered by questions like "can X do Y?", "will X work for Y?", "is X feasible for Y?", or "should I use X to achieve Y?"
critical-research
by tomwangowa
Falsification-first research skill that actively seeks counter-evidence before supporting evidence to eliminate cognitive biases and ensure rigorous, objective conclusions.
scikit-bio
by YuukiAS
Biological data toolkit. Sequence analysis, alignments, phylogenetic trees, diversity metrics (alpha/beta, UniFrac), ordination (PCoA), PERMANOVA, FASTA/Newick I/O, for microbiome analysis.
patch-existing-project
by jujumelona
Inspect, extract and modify an existing Fabric source project with hash-guarded transactional patches.
convex-queries
by Sstobo
This skill should be used when implementing Convex query functions. It provides comprehensive guidelines for defining, registering, calling, and optimizing queries, including pagination, full text search, and indexing patterns.
agent-registry
by MaTriXy
MANDATORY agent discovery system for token-efficient agent loading. Claude MUST use this skill instead of loading agents directly from ~/.claude/agents/ or .claude/agents/. Provides lazy loading via search and get tools. Use when: (1) user task may benefit from specialized agent expertise, (2) user asks about available agents, (3) starting complex workflows that historically used agents. This skill reduces context window usage by ~95% compared to loading all agents upfront.
Convex Agents Context
by Sstobo
"Customizes what information the LLM receives for each generation. Use this to control message history, implement RAG context injection, search across threads, and provide custom context."
Convex Agents RAG
by Sstobo
"Implements Retrieval-Augmented Generation (RAG) patterns to enhance agents with custom knowledge bases. Use this when agents need to search through documents, retrieve context from a knowledge base, or ground responses in specific data."
valyu-best-practices
by valyuAI
Complete Valyu API toolkit for AI agents. Use this skill when asked to perform real-time search across web, academic, medical, transportation, financial sources, content extraction from URLs, AI-powered answers with citations, or comprehensive deep research reports.
upstage-builder
by UpstageAI
"Build pipelines, agents, RAG flows, and full web services by combining Upstage Solar models, embeddings, and document APIs. Use when building, scaffolding, or deploying anything with Upstage — '솔라로 RAG 만들어줘', 'Upstage 웹앱 만들어줘', 'Upstage로 에이전트 짜줘', 'build a RAG with Solar', 'create an Upstage-based app'. Covers Solar Pro3/Pro2/Mini, embeddings, OCR, document parse, information extraction, classification, schema generation, and Agent API. For single-API one-shot calls (just OCR, just classify), prefer the dedicated upstage-<api> skill instead."
cocoindex
by 89jobrien
Comprehensive toolkit for developing with the CocoIndex library. Use
memory-metadata-search
by basicmachines-co
"Structured metadata search for Basic Memory: query notes by custom frontmatter fields using equality, range, array, and nested filters. Use when finding notes by status, priority, confidence, or any custom YAML field rather than free-text content."