Agent skill · software engineering · jeremylongshore
cohere-core-workflow-a
Build a Cohere v2 RAG pipeline with asymmetric embeddings, retrieval, Rerank v4, grounded Chat, and citation validation. Use when implementing grounded question answering. Trigger with "Cohere RAG", "Cohere retrieval", or "Cohere citations".
Why this skill is useful
Adds executable scripts for embedding, searching, and reranking documents using Cohere's APIs, which are not publicly documented.
What it needs
Requires cohere-ai installed locally. Requires cohere account access. About 2k tokens when loaded. Last updated 2026-08-07. 2,604 stars on the source repository.
What this skill does
Cohere Retrieval-Augmented Generation Overview Create a measurable retrieval pipeline that separates indexing, query embedding, candidate retrieval, reranking, generation, and citation checks. Prerequisites The target repository, runtime, environment, and accountable owner An approved Cohere team and key for any live verification Current quality, security, privacy, capacity, and change-control requirements Tool Discipline Use Read, Glob, and Grep to inspect code, configuration, and evidence. Use WebFetch only for current Cohere primary documentation. Use Write or Edit only when the user requested implementation and the exact target files are known; never write credentials or customer content. Current Contract Embed indexed passages with inputtype=searchdocument and user queries with inputtype=searchquery. Keep the embedding model, output type, dimensions, normalization, and document schema in index metadata. Use Rerank v4 on a bounded candidate set before generation and retain document IDs. Pass selected documents to Chat v2 and validate returned citations against those IDs. Authentication Use an environment-specific key injected from an approved secret manager. Never print, persist, commit, or place COAPIKEY in an example. Confirm access with the least costly bounded operation appropriate to the task, and treat key creation, rotation, revocation, role changes, and production-capacity requests as owner-approved actions. Instructions 1. Define document IDs, chunking rules, metadata filters, and an evaluation query set. 2. Resolve and pin a live Embed model, then index documents with the document input type. 3. Embed each query with the query input type and retrieve a bounded candidate set. 4. Rerank candidates with a live v4 model and record scores and selected IDs. 5. Generate from only the selected evidence with citation options appropriate to the use case. 6. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills jeremylongshore/cohere-core-workflow-a