zaxbysauce

Guidelines for safe subprocess calls in opencode-swarm. Load before adding, modifying, or reviewing any file that calls spawn, spawnSync, bunSpawn, or child_process. Covers the six required properties, Windows portability, _internals DI seam pattern, and verification grep.

Guidelines for writing, organizing, and maintaining tests in the opencode-swarm repository. Covers framework rules (bun:test), mock isolation, CI pipeline structure, file placement, and anti-patterns that break cross-platform CI. Load this skill before writing or modifying any test file.

Apply when converting test files from mock.module('node:child_process') to _internals DI seam pattern. Guides the complete migration: adding spawnSync/_internals to source files, converting test files, adding proper beforeEach/afterEach save/restore lifecycle, mockReset() cleanup, and temp directory cleanup. Prevents mock.module leaks across Bun's shared test-runner process.

Full execution protocol for MODE: PLAN -- plan creation, external plan ingestion, QA gate persistence, task granularity, and traceability checks.

Full execution protocol for MODE: BRAINSTORM -- structured discovery dialogue, approach selection, spec drafting, QA gate selection, and transition handling.

Full execution protocol for MODE: CLARIFY -- structured clarification funnel with critic review before surfacing user decisions.

Full execution protocol for MODE: CLARIFY-SPEC -- resolving spec clarification markers and maintaining spec/planning alignment.

Full execution protocol for MODE: ISSUE_INGEST -- GitHub issue intake, localization, spec generation, and transition to planning or tracing.

RAGAPPv3 engineering conventions — backend (FastAPI + SQLite + LanceDB), frontend (React + TypeScript + Vite + Vitest), database/migration/RBAC patterns, and the multi-agent skill layout. Load before implementing or refactoring backend routes/services/migrations or frontend pages/components, or when you need to know "how does this repo do X".

Apply when writing tests, modifying test files, fixing test failures, debugging CI failures, adding test coverage, creating adversarial tests, or reviewing any file under tests/. Also apply when implementing features or fixes that require corresponding test changes. Enforces framework-specific rules (bun:test for TypeScript, unittest/pytest for Python), mock isolation, cross-platform compatibility, and CI pipeline awareness. Load this skill before touching any test file.

Lightweight PR-time audit for whether changes are compatible with the actual RAGAPPv3 GitHub Actions workflow, dependency lockfiles, scripts, and cross-platform local validation.

RAGAPPv3 testing policy and conventions. Load before writing or modifying any test, fixing a test/CI failure, or adding coverage. Covers backend pytest + unittest (SimpleConnectionPool dependency-override harness, FK cascades, the Python 3.11-vs-local event-loop trap) and frontend Vitest + React Testing Library + jsdom (MemoryRouter, Radix Select, react-virtual mock patterns). This repo's frontend uses Vitest, NOT bun:test.

Run a graph-guided, tool-augmented Swarm PR review using context packing, parallel exploration, triggered plugin micro-lanes, independent reviewer validation, critic challenge, and metrics writeback. Use for deep pull request review with low false-positive tolerance and high recall.

Audit environment and configuration contracts across backend settings, frontend env usage, Docker, Compose, CI, docs, and examples. Use when changing config, deployment, root paths, CORS, settings schemas, env examples, or Docker files.

RAGAPPv3 subpath/reverse-proxy deployment system. Load before touching anything related to APP_ROOT_PATH, VITE_APP_BASENAME, VITE_API_URL, cookie paths, SPA catch-all routing, proxy configuration, or Docker build args for the frontend. Contains locked architectural decisions that must not be re-litigated.

Enable a high-quality swarm-like Codex workflow for the current session, and optionally execute a task immediately using that mode. Uses parallel subagents for breadth, independent reviewer validation for precision, and critic challenge for final confidence. Use when the user wants swarm-like behavior, higher review rigor, or maximum quality without sacrificing Codex speed.

Enable a high-quality swarm-like Claude Code workflow for the current session, and optionally execute a task immediately using that mode. Uses parallel subagents for breadth, independent reviewer validation for precision, and critic challenge for final confidence. Use when the user wants swarm-like behavior, higher review rigor, or maximum quality without sacrificing Claude Code speed.

End-to-end PR workflow for opencode-swarm. Covers branch setup, conventional commits, mandatory release notes, 5-tier CI checks, and PR submission format. Load this skill before creating branches, commits, or pull requests.

Deep technical debt and CI stability audit for identifying test theater, missing or mis-scoped tests, actual and potential test failures, flaky-test risk, dependency/toolchain brittleness, and structural debt that prevents PRs from going green safely.

Apply when writing tests, modifying test files, fixing test failures, debugging CI failures, adding test coverage, creating adversarial tests, or reviewing any file under tests/. Also apply when implementing features or fixes that require corresponding test changes. Enforces bun:test framework rules, mock isolation, cross-platform compatibility (Linux, macOS, Windows), and CI pipeline awareness. Load this skill before touching any test file.

Apply when committing, pushing, opening a PR, writing a pull request, creating release notes, or updating a changelog. Enforces conventional commit format, mandatory release notes, 5-tier test suite, SHA-pinning for workflow changes, and correct PR body format.

Apply when implementing features, fixing bugs, debugging errors, investigating failures, tracing root causes, reviewing tech debt, tracing issues, planning fixes, or completing any task. Enforces parallel sub-agent implementation, independent adversarial review, and a 95% confidence gate before stopping.

Apply when planning fixes, investigating tech debt, architecting solutions, or diagnosing unknown issues. Search online for current documentation and state-of-the-art approaches before tracing through code.

Evidence-first code review for correctness bugs, AI-generated code smells, unsupported claims, unwired functionality, dependency hallucinations, and release-to-code mismatches.

Validate new and changed dependencies, imports, install commands, lockfile entries, and runtime tool assumptions for package hallucinations, slopsquatting, cross-ecosystem confusion, and version validity.

Verify that README changes, release notes, changelog bullets, migration notes, PR descriptions, examples, and docstrings match what the code actually ships.

Inspect trust boundaries, validation, authn/authz, deserialization, command execution, path handling, secrets, and failure handling with an evidence-first security review.

Apply when writing tests, modifying test files, fixing test failures, debugging CI failures, adding test coverage, creating adversarial tests, or reviewing any file under tests/. Also apply when implementing features or fixes that require corresponding test changes. Enforces pytest framework rules, mock isolation, cross-platform compatibility (Linux, macOS, Windows), and CI pipeline awareness. Load this skill before touching any test file. For CI failure debugging specifically, also load the ci-failure-resolver skill.

Enable a high-quality swarm-like Claude Code workflow for the current session, and optionally execute a task immediately using that mode. Uses parallel subagents for breadth, independent reviewer validation for precision, and critic challenge for final confidence. Use when the user wants swarm-like behavior, higher review rigor, or maximum quality without sacrificing Claude Code speed.

Run a swarm-like PR review using parallel exploration, independent reviewer validation, and critic challenge. Use for deep pull request review with low false-positive tolerance.

Enable a high-quality swarm-like Claude Code workflow for the current session, and optionally execute a task immediately using that mode. Uses parallel subagents for breadth, independent reviewer validation for precision, and critic challenge for final confidence. Use when the user wants swarm-like behavior, higher review rigor, or maximum quality without sacrificing Claude Code speed.

Read and extract text from document files (.docx, .pdf, .xlsx, .pptx, .csv, .rtf, .odt, .epub, .html) into plain text or markdown for editing

Apply when modifying any async method in the Adapters/ layer (FtpFileClient, SftpFileClient), the IFileClient interface, or AppBridge file-operation calls. Also apply when adding new async methods that interact with FTP/SFTP libraries or when reviewing cancellation correctness. Covers FluentFTP, SSH.NET, and SemaphoreSlim patterns specific to this codebase.

Enable a high-quality swarm-like Claude Code workflow for the current session, and optionally execute a task immediately using that mode. Uses parallel subagents for breadth, independent reviewer validation for precision, and critic challenge for final confidence. Use when the user wants swarm-like behavior, higher review rigor, or maximum quality without sacrificing Claude Code speed.