Loading...
Loading...
Found 12 Skills
Create, ingest into, and query a Pinecone full-text-search (FTS) document index using the graduated document-schema API (Python SDK 10.0.0, API version 2026-07). Use when the user or agent asks to build a text search index on Pinecone, add dense or sparse vector fields, ingest documents, construct score_by clauses (text / query_string / dense_vector / sparse_vector), or compose with text-match filters ($match_phrase / $match_all / $match_any). Ships `scripts/ingest.py` for safe bulk ingestion (batch_upsert + error inspection + readiness polling); query construction is documented inline in this skill — write `documents.search(...)` calls directly, validated against `pc.indexes.describe(...)` output.
PokéAPI as a fully offline Pokédex with SQL, full-text search, type math, and a damage calculator no other Pokémon tool ships as a CLI. Trigger phrases: `look up a pokemon`, `what beats charizard`, `build a pokemon team`, `type matchup`, `evolution chain`, `use pokeapi`, `run pokeapi-pp-cli`.
Expert-level PostgreSQL database administration, advanced queries, performance tuning, and production operations
Guide for using the AI's persistent journal database
Search data using vector similarity, full-text keywords, or hybrid methods with Reciprocal Rank Fusion (RRF). Use when setting up embeddings for search, configuring full-text indexing, writing vector_search/text_search/rrf SQL queries, using the /v1/search HTTP API, or configuring vector engines like S3 Vectors.
Provides comprehensive guidance for PostgreSQL database including SQL syntax, advanced features, JSON support, full-text search, and performance tuning. Use when the user asks about PostgreSQL, needs to work with PostgreSQL features, write complex queries, or optimize PostgreSQL databases.
Expert-level Elasticsearch, search, ELK stack, and full-text search
Store and retrieve memories (notes, facts, decisions, snippets, images) using a local SQLite database with full-text search. Use when you need to remember information across sessions, recall previous decisions, store code snippets, or search your knowledge base.
Use when finding files by name/path or searching inside file contents on the local Windows machine. Faster than `search_files` / `ls -R` / `find` / ripgrep when the search would touch many directories, because it uses live indexes (Voidtools Everything for filenames, AnyTxt for full-text incl. PDF/docx/pptx). One CLI (`local-search`) with self-explanatory subcommands - `files` (filename/path/ext, sub-second across millions of files), `text` (full-text incl. PDF/docx/pptx/code, keyword highlighting), `recent` (recently modified files, human-friendly time windows like `1h`/`today`/`30min`), `extract` (turn PDF/docx/pptx into plain text using AnyTxt's index — instant, no marker-pdf/OCR needed), `sync` (force AnyTxt to reindex a folder after writing new files so agent can search them immediately), `doctor` (health-check both backends with actionable fix hints). Default output is a markdown table; `--format json`/`csv` for machine consumption. Windows only.
Index and search documents. Similar to ZeroClaw's SQLite hybrid search and OpenClaw's memory system. Supports full-text search, keyword extraction, and document categorization.
Query pro-workflow wikis via SQLite FTS5 BM25 retrieval. Returns top-K passages with citations. Use when answering a question that any of the user's wikis already covers, when the user says "what does the wiki say about X", "ask wiki", "search wikis", or before drafting a new wiki page (to avoid duplication).
Render a self-contained HTML viewer for a pro-workflow wiki. Pages, sources, claims, seed queue, page-link graph and full-text search all in one file. No external dependencies, no JS framework, S3-uploadable. Use when the user wants to browse a wiki visually, share its current state with someone, audit research progress, or hand off a knowledge base. Inspired by Thariq Shihipar's "Unreasonable Effectiveness of HTML" — favors information density and shareability over markdown-only outputs.