retrieval skills

37 tagged retrieval, measured the same way as everything else here.

Browse within: RAG 18knowledge-base 7

VectifyAI/OpenKB

Skill Claude CodeCodex

Use when the user asks the openkb chat to make a deck / slide presentation / PPT / slides / 演示稿 / 幻灯片 from their compiled KB content. Generates a polished single-file HTML deck in the Editorial Monocle visual direction (warm cream background, serif type, brick-red accent) — designed to be opened in a browser…

4.2k 1mo ago A 117 tokens original Apache-2.0

openkb-deck-neon

02

VectifyAI/OpenKB

Skill Claude CodeCodex

Use when the user asks the openkb chat to make a deck / slide presentation / PPT / slides / 演示稿 / 幻灯片 from their compiled KB content AND wants a dark, high-tech, neon / glow / glassmorphism look (赛博 / 科技风 / 暗色 / 霓虹 / 炫酷). Generates a polished single-file HTML deck in the Aurora Glass visual direction (near-black…

4.2k 1mo ago A 173 tokens original Apache-2.0

openkb-html-critic

03

VectifyAI/OpenKB

Skill Claude CodeCodex

Use to review a generated HTML deck or single-page artifact for visual quality and structural correctness. Especially good at catching CSS specificity bugs where slide-modifier classes (.divider, .center, .q, .flow etc.) accidentally override the base .slide{display:none} and cause one slide to stack on top of every…

4.2k 1mo ago A 132 tokens original Apache-2.0

NVIDIA-NeMo/Nemotron

Skill Claude CodeCodex

Use when planning, debugging, tuning, evaluating, exporting, or deploying public Nemotron embed/rerank retrieval recipes.

2.0k 11d ago A 36 tokens original Apache-2.0

moss-pikachu

05

usemoss/moss

Skill Claude CodeCodexCursor

Build and maintain Moss Pikachu, a macOS menu bar semantic file search app using Moss Python SDK (PyPI moss>=1.6.0), FSEvents, SwiftUI, and Pikachu pet animations. Use when working on MossPikachu, mossworker.py, FileMonitor, SearchService, menu bar overlay, or Moss integration in this repository.

667 8d ago A 80 tokens original BSD-2-Clause

moss-search

06

usemoss/moss

Skill Claude CodeCodex

Sub-10ms semantic search for Zo via Moss. Create indexes, add documents, and query them with semantic and keyword search. Use when users want to search through documents, knowledge bases, or any text content.

667 8d ago A 48 tokens original BSD-2-Clause

rag

07

mytk2012/python_agent

Skill Claude CodeCodex

A document question-answering setup that finds relevant passages in your files and uses a language model to generate answers. It accepts PDF, DOCX, TXT, and Markdown files, and can store searchable document collections.

22 4mo ago A 7 tokens original Apache-2.0

rag-evaluation

08

karthikrshet/aiskills

Skill Claude CodeCodex

Use this skill to evaluate the quality of a RAG pipeline on faithfulness, answer relevancy, context precision, context recall, and hallucination rate. Activates after a RAG system is implemented or when retrieval quality is in question. Produces a structured evaluation report with measurable results.

3 12d ago A 63 tokens

wpc0323/StructuredMemoryManager

Skill Claude CodeCodex

A structured long-term memory tool for storing and retrieving user preferences, past decisions, task summaries, and habits across conversations. It can search memories by meaning as well as keywords.

2 21d ago A 60 tokens original MIT

axrbarsic/verifiable-memory-bank

Skill Claude CodeCodex

Research and synthesize from a local Verifiable Memory Bank with source-backed evidence, reproducible selectors, chronology, attribution, and explicit uncertainty. Use when a request asks Codex to recall banked material, investigate a topic, verify a claim, build a dossier or timeline, distinguish quoted facts from…

0 1mo ago A 76 tokens original 0BSD

repository-memory

11

LeslieWylie/repository-memory

Skill Claude CodeCodex

Answer questions about this project, its history, past conversations, and prior team decisions from source-backed evidence with verified citations. Use whenever the user asks what something is, why it was decided, what happened before, or what the team already knows.

0 5d ago A 52 tokens original MIT