agentleFS
Sign inStart free
vespa-enginevespa-engine/skills/AGENTS.md

skills

AGENTS.md16 starsChanged 6 months agoApache-2.0View on GitHub

Auto-generated by generate.py. Do not edit manually. This repository contains AI coding-assistant skills for Vespa.ai. Each skill is a self-contained folder with a SKILL.md file as the primary reference. 1. Read the relevant SKILL.md for the task at hand. 2. Load files from the docs/ folder when you need deeper reference detail. 3. Combine skills as needed — e.g., use schema-authoring to define the schema, app-package to set up services.xml, query-builder for rank profiles, and feed-operations to populate data.

  • Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.

    Of the AGENTS.md files we read, the 31,843 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.

  • In this repository7 other files it gives its agents.

The file

We split this AGENTS.md into the rules it gives an agent

1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read the relevant SKILL.md for the task at hand.

    line 54

≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
AGENTS.md

Vespa Skills — Agent Instructions

Auto-generated by generate.py. Do not edit manually.

This repository contains AI coding-assistant skills for Vespa.ai. Each skill is a self-contained folder with a SKILL.md file as the primary reference.

Available Skills

app-package

  • Path: app-package/SKILL.md
  • Scaffold and configure Vespa application packages, including services.xml, schemas, deployment.xml, query profiles, and embedder components.
  • Reference docs: docs/embedders.md, docs/services-xml.md

elasticsearch-migration

  • Path: elasticsearch-migration/SKILL.md
  • Migrate from Elasticsearch to Vespa — map ES indices and mappings to Vespa schemas, translate Query DSL to YQL, plan reindexing, and bridge ranking differences. Use when the user mentions migrating from Elasticsearch, ES→Vespa, porting an ES index, or replacing Elasticsearch with Vespa.
  • Reference docs: docs/concept-mapping.md, docs/fetching-docs.md, docs/parser-and-tooling.md, docs/query-translation.md

feed-operations

  • Path: feed-operations/SKILL.md
  • Vespa document CRUD operations and bulk feeding — covers document ID format, JSON wire format for put/update/remove, REST API endpoints, CLI commands, partial updates, conditional writes, bulk feeding, and document visiting/export.
  • Reference docs: docs/document-json.md, docs/feed-clients.md, docs/partial-updates.md, docs/rest-api.md, docs/visiting-export.md

pyvespa

  • Path: pyvespa/SKILL.md
  • Python API for Vespa.ai — define schemas, deploy applications, feed documents, query, and manage Vespa from Python using pyvespa.
  • Reference docs: docs/application-api.md, docs/deployment-auth.md, docs/package-api.md, docs/query-builder-dsl.md

query-builder

  • Path: query-builder/SKILL.md
  • Build Vespa YQL queries and design rank profiles. Covers YQL syntax, operators, grouping, rank-profile phases, ML model integration, and query tensor inputs.
  • Reference docs: docs/grouping.md, docs/ml-models.md, docs/query-tensors.md, docs/rank-features.md, docs/yql-operators.md

schema-authoring

  • Path: schema-authoring/SKILL.md
  • Writing, validating, and evolving Vespa .sd schema files — covers field types, indexing pipelines, match modes, tensors, rank profiles, structs, fieldsets, and common pitfalls.
  • Reference docs: docs/example-ecommerce-schema.md, docs/field-types.md, docs/gotchas-extended.md, docs/schema-patterns.md, docs/tensors-and-hnsw.md

vespa-cli

  • Path: vespa-cli/SKILL.md
  • Vespa CLI for deploying, managing, and debugging Vespa.ai applications -- covers target configuration, authentication, deployment lifecycle, production pipelines, document operations, log inspection, testing, and CI/CD integration.
  • Reference docs: docs/ci-cd.md, docs/cli-reference.md, docs/production-deploy.md, docs/tests-utilities.md

How to Use

  1. Read the relevant SKILL.md for the task at hand.
  2. Load files from the docs/ folder when you need deeper reference detail.
  3. Combine skills as needed — e.g., use schema-authoring to define the schema, app-package to set up services.xml, query-builder for rank profiles, and feed-operations to populate data.

Reference

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free