agentleFS
ch4570ch4570/vulpora/skills/opensearch-code-authoring/SKILL.md

opensearch-code-authoring

Skill1 starsChanged 56 days agoApache-2.0View on GitHub

Write or modify OpenSearch mappings, Query DSL, vector or hybrid search settings, and reindex plans with relevance, latency, and operational safety. Use when a feature, bug fix, or refactor in a repository detected as OpenSearch touches search behavior, mapping, configuration, or queries, even when the user does not name OpenSearch; do not use for review-only requests.

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Treat mapping type, analyzer, or vector changes as migration work.

    line 15
  2. Distinctive:

    Read mapping construction for schema changes and query construction for Query DSL.

    line 18

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 skill 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
SKILL.md

OpenSearch code authoring

Inspect the target OpenSearch version, existing mappings/settings, client builder, document shape, workload, and evaluation signals before drafting. Preserve existing naming and index lifecycle conventions; do not invent field names, analyzer behavior, or model dimensions.

Construction contract

  • Make mappings explicit for fields that are searched, filtered, sorted, aggregated, or embedded. Match text/keyword, analyzer, doc-values, and vector dimension/space to demonstrated use.
  • Build Query DSL from validated field/operator inputs. Put non-scoring constraints in filter context, constrain expensive query forms, and use a stable pagination strategy for the requested depth.
  • For vector or hybrid search, keep embedding model, dimension, space type, k, candidate controls, and filtering strategy compatible. Tune recall and p99 together; do not claim either improves without measurement.
  • Treat mapping type, analyzer, or vector changes as migration work. Supply a versioned index, reindex, alias/blue-green cutover, and rollback approach when the existing lifecycle requires it.
  • Author artifacts and diagnostic/benchmark commands only. Do not mutate an index or cluster without separate authorization.

Read mapping construction for schema changes and query construction for Query DSL. The installed opensearch-query-review, opensearch-schema-review, and opensearch-optimization dependencies provide the shared review rationale; apply them as construction constraints.

Deliverable

Return the mapping/query/settings or migration artifact, assumptions, compatibility notes, and recall@k/p99 plus operational verification plan.

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.