Software factory toolkit for Claude Code: Postgres/Supabase & React/Next best practices, SQL-migration & security reviewers, docs architect, RPC-API contract, functional front QA, and the wachi-fabrica orchestrator — plus db/frontend/security subagents. Project-agnostic.
Designs and evolves Postgres/Supabase data models with senior judgment — not just CRUD. Owns schema coherence, self-describing semantics (COMMENT/RAG-ready), audit strategy, agent-operable RPC contracts, RLS + security tests, and performance. Use to design a new model, harden an existing one, or add a non-trivial DB capability.
Reviews SQL migrations before they are applied. Validates naming conventions, soft-delete filtering, COMMENT ON coverage, SECURITY DEFINER hardening, RLS policies, and Postgres performance.
Builds production-grade React/Next UI that kills AI slop — real component library (shadcn/ui), accessibility, loading/empty/error states, composition, and a self-audit pass against a design-slop blacklist. Use to build or rewrite product UI to a senior bar, not a generic autogenerated front.
Reviews code for OWASP Top 10 vulnerabilities — SQL/command injection, XSS, broken auth/authorization, hardcoded secrets, and insecure data handling, with Supabase-specific checks.
Actualiza el plugin de la fábrica Wachines (marketplace `wachines` de Claude Code: Wachines-Plugin-Ironman) a la última versión — refetchea el marketplace y recarga los plugins. Reemplaza el flujo viejo de `npx skills` (el equipo instala por plugin de Claude Code, no por npx). Usar cuando el usuario diga "actualizar wachines", "actualizá el plugin de la fábrica", "traé las skills nuevas", "/actualizar-wachines", o después de un release del plugin.
Assess how ready a codebase is for autonomous AI coding agents — by delegating a deep investigation of each of Factory.ai's 9 readiness pillars (~80 criteria) to a dedicated subagent, then cross-referencing their reports into a pass-rate + maturity level with a prioritized, concrete fix list. Use when asked to "check agent readiness", "is this repo agent-ready", "readiness report/score", "/readiness", "how well does this repo support AI agents", or to audit a repo's dev environment for agent autonomy.
Genera y mantiene la documentación de referencia GENERADA de un repo (By the Numbers, mapa del repo, inventarios de funciones/migraciones/edge-functions/rutas) computándola del código con un generador determinístico, y la cablea a CI (check en PR). Sigue la taxonomía AutoWiki de Factory.ai (doc = build artifact). Usar cuando se pida instalar/regenerar docs generadas, "documentación que no envejece", un wiki del codebase, o cablear generación de docs en CI. Complementa a docs-architect (que audita la doc AUTHORED escrita a mano).
Review SQL migrations before applying them. Validates naming conventions, soft-delete filtering, COMMENT ON coverage, SECURITY DEFINER hardening, RLS policies, and Postgres performance. Use when reviewing a migration, a CREATE TABLE/FUNCTION/POLICY, or any schema change before it hits production.
Audit, create, update, reorganize, or improve documentation in a repository. Detects stale docs out of sync with code, finds undocumented features/APIs, restructures doc folders, fixes broken links, and runs comprehensive documentation reviews. Use when asked to review the docs, document a feature, check if docs are up to date, or reorganize documentation.
External network access
Connects to servers outside your machine
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
A curated, installable set of Agent Skills for Claude Code (and any agent that supports the open Skills standard). Hand-picked tools for shipping quality web apps and databases: Postgres/Supabase best practices, React/Next.js performance, a SQL-migration reviewer, and a documentation architect.
Formerly wachines-skills (renamed to match the Wachines-Plugin-Ironman repository).
Project-agnostic by design — no company-, domain-, or schema-specific content. Add the ones you want, contribute the ones you wish existed.
¿Sos del equipo? Empezá por SETUP.md — instala todo el toolchain dev (gstack + Wachines-Plugin-Ironman + gokapso), registra Engram para Claude Code/Codex y deja listo el camino de Engram cloud. Las skills se instalan desde repos centralizados, no se editan dentro de cada proyecto.
Pick by your agent: Claude Code → the plugin (recommended). Codex and any other agent →
npx skills (Claude Code plugins only work in Claude Code).
This repo is also a Claude Code plugin marketplace. One install wires up every skill and
the db-architect / frontend-specialist / db-reviewer / security-reviewer subagents — no
npx, no per-agent copying:
# add the marketplace (defined in .claude-plugin/marketplace.json)
claude plugin marketplace add Perennia-Regeneracion/Wachines-Plugin-Ironman
# install the plugin (skills + subagents auto-discovered)
claude plugin install Wachines-Plugin-Ironman@wachines
Or interactively inside Claude Code: /plugin marketplace add Perennia-Regeneracion/Wachines-Plugin-Ironman
then /plugin install.
Auto-update. Plugins do not update when you run a skill — they update at session
startup, and only if the marketplace has autoUpdate on (third-party marketplaces default to
off). To get hands-off updates, declare the marketplace with autoUpdate in your
~/.claude/settings.json (the team bin/setup-dev.sh does this for you):
{
"extraKnownMarketplaces": {
"wachines": {
"source": { "source": "github", "repo": "Perennia-Regeneracion/Wachines-Plugin-Ironman" },
"autoUpdate": true
}
}
}
Updates follow the plugin's version (in .claude-plugin/plugin.json). You don't bump it by
hand — a GitHub Action (.github/workflows/release.yml) computes
the bump on every push to main, derived from your Conventional Commits (feat → minor, fix →
patch, !/BREAKING → major), updates the CHANGELOG.md, and tags the release. Merge a PR as usual
and the team picks up the new version at their next startup.
How the bot pushes to a protected
main.mainis protected by an org ruleset that requires PRs, and the defaultGITHUB_TOKENcan't bypass it. The Action mints a token for theperennia-automergeGitHub App (already in the ruleset's bypass list) from the org secretsAUTOMERGE_APP_ID+AUTOMERGE_APP_PRIVATE_KEY, and pushes the bump with that. No per-user PAT, nothing to configure — it reuses the org's existing automerge app.
Manual update any time:
claude plugin marketplace update wachines && claude plugin update Wachines-Plugin-Ironman (restart to apply).
npx skills)Requires Node.js. Install all skills, or pick individual ones:
# everything
npx skills add Perennia-Regeneracion/Wachines-Plugin-Ironman
# Codex explicit
npx skills add Perennia-Regeneracion/Wachines-Plugin-Ironman -g -a codex
# or a single skill
npx skills add Perennia-Regeneracion/Wachines-Plugin-Ironman/db-reviewer
The skills CLI drops each skill into your agent's
config dir (.claude/skills/ for Claude Code, .agents/skills/ for others). List what you
have with npx skills list; search with npx skills find <query>.
npx claudepluginhub perennia-regeneracion/wachines-plugin-ironman --plugin Wachines-Plugin-IronmanComprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Harness-native ECC operator layer - 60 agents, 232 skills, 75 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Complete creative writing suite with 10 specialized agents covering the full writing process: research gathering, character development, story architecture, world-building, dialogue coaching, editing/review, outlining, content strategy, believability auditing, and prose style/voice analysis. Includes genre-specific guides, templates, and quality checklists.
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
A growing collection of Claude-compatible academic workflow bundles. Covers scientific figures, manuscript writing and polishing, reviewer assessment, citation retrieval, data availability, paper reading, literature search, response letters, paper-to-PPTX conversion, and evidence-grounded Chinese invention patent drafting. Rules are organized as reusable skill folders with explicit workflows and quality checks.
v9.52.0 - Reliability wave: tangle contextual review correction loop with hard round ceiling, progress-supervised review rounds (per-agent stall watch, descendant-tree kills), council diversity and agy pin fixes, marketplace generator source-of-truth fix, provider troubleshooting runbook and cost-expectations docs. Run /octo:setup.