Use for Nim symbol navigation, diagnostics, and type resolution. MANDATORY: Use specialized MCP tools (nimFindSymbols, nimFindReferences, nimListSymbols, nimCheckFile, nimCheckProject, nimFindTypeDefinition) first; fall back to grep only on error or user confirmation.
Use when choosing or running JETLS tests after code changes. Prefer component-specific tests, avoid the full suite unless needed, and use TestRunner for focused iteration.
Use when adding or modifying JETLS tests. Covers test file and module structure, @testset organization, let blocks, withserver usage, and when subroutine tests are sufficient for language-server features.
Prepare and commit code changes with full verification, pre-commit checks, and tests. Runs verification skill, fixes issues using TDD, executes all test suites, and creates atomic commits. Use when ready to commit changes, before committing, or when asked to prepare a commit.
Start an implementation task with proper planning, TDD workflow, and session hand-off. Use when beginning work on a Jira issue, starting a new feature, or resuming implementation work. Triggers on phrases like "start task", "begin implementation", "work on issue", or "implement feature".
Deep verification of code changes before committing. Traces code paths, detects semantic changes, identifies code smells and security issues. Reads GitHub PR reviews to propose implementation decisions. Use before commits, after implementation, or when asked to verify/review changes.
Best practices for reading and reacting to VS Code settings in a Language Server Protocol (LSP) server. Use when handling vscode configuration or LSP configuration from clients.
Validate and understand schema-backed YAML (Kubernetes, Flux, and JSON-Schema configs) with the yayamlls language server. Use when editing or reviewing .yaml/.yml files, diagnosing schema validation errors, configuring .yayamlls.yaml, suppressing a diagnostic, or working with Flux HelmRelease / Kustomization rendering.
Semantic workflow for implementing, reviewing, or fixing onec-hbk-bsl diagnostic rules. Use for BSL/1C rule semantics, CST or tree-sitter behavior, BSLLS parity, performance, synthetic fixtures, related-rule overlap, and questions about whether a rule matches its documented language behavior.
Use when Codex should work on a repository with OACS-backed development memory: build repo context, record command results as evidence, checkpoint iterations, capture D1 repo episodes, coordinate explicitly requested subagents through one shared OACS database, and close subagents when their goals are done.
Add a new MCP tool to plumb — file layout, Tool interface, WriteDeps, registration, lean-profile decision, tests, and every doc/table that must be updated. Use when creating, renaming, or removing a plumb MCP tool.
Talk to another agent working the same plumb workspace — address a peer session by name, hand your turn over while waiting for its reply, and read silence correctly. Use when work has to be coordinated with a concurrent session.
Work out why a plumb call was refused, or why a change looks broken — read the rejection, get compile truth from diagnostics, and check the daemon and index before blaming the code. Use when a tool call fails or a result looks wrong.
This skill should be used when the user asks about "LSP configuration", "language server setup", "adding LSP to Claude Code", "mason config import", "lspconfig migration", "lspctl plugin", or discusses Claude Code LSP integration and troubleshooting.