dokkabei-harness

Development lifecycle workflows: project rules (AGENTS.md stack facts + specialist core for Claude Code, Codex and Antigravity; Claude path-scoped rules), spec/planning/shipping guides, MR review, handoff, release notes, retrospectives, and CLAUDE.md sync

11 skills · 3 commands · hooks

Shared backend specialist layer: PostgreSQL, Kafka, Valkey and distributed-call pitfalls, migration safety, DTO/serialization rules, plus user-invoked API design, docs, test, and perf commands

4 skills · 8 commands · 2 agents

Elasticsearch specialist layer: ES/Lucene performance, relevance (Korean nori), and vector/hybrid search pitfall hubs, review commands, and a user-invoked agent-team orchestrator

4 skills · 5 commands · 4 agents

Comprehensive static analysis of code quality, performance, architecture, and SQL

4 skills · 4 commands · 3 agents

Operates a cited llm-wiki knowledge vault through gated feed, audit, curation-loop, and Q&A

7 skills · 3 agents

Meta-plugin for harness design (v2 execution modes), evolution, generation, validation, and lightweight loops

4 skills · 4 commands · hooks

Foundational guard-hook & LSP layer for the loop harness

hooks · LSP

Python + FastAPI specialist layer: async, pool, serialization, GC and deployment pitfall triage, plus convention-first code generation and API design

1 skill · 2 commands · 2 agents

Go runtime and performance specialist layer (maps, GC, concurrency, net/http, database/sql) plus stdlib net/http mux code generation and API design

1 skill · 2 commands · 1 agent

JVM, Kotlin and Spring specialist layer: symptom-to-pitfall triage (GC, collections, coroutines, transactions, JPA, pools), a read-only diagnostic agent, and convention-first CRUD scaffolding

1 skill · 1 command · 2 agents

Next.js App Router specialist layer: version-aware caching, RSC boundary, data-waterfall and self-hosting pitfall triage, plus page design and code generation

1 skill · 2 commands · 1 agent

Test-first guide with a specialist testing-pitfall index, a browser E2E verification checklist (Chrome / Playwright MCP), and user-invoked Playwright spec generation

2 skills · 1 command · 1 agent

Measures real harness usage (Claude Code + Codex hooks, Antigravity backfill, opt-in git hooks) into a per-repo .tracer/ store and turns it into improvement proposals with an explicit feedback loop

2 commands · hooks

General-purpose utility skills for external AI CLI integration

2 skills