architect
claudecodexSoftware architecture agent and skills: decisions and ADRs, C4 documentation, threat modeling, Clean Architecture, Domain-Driven Design and software design.
13 skills · 1 agent · hooks
Software developer agent and skills for any language: implementing and reviewing code, framework practices for ASP.NET Core and Spring Boot, implementing architecture designs, clean code, refactoring, testing, debugging, secure coding, APIs, production readiness, user interfaces, design patterns, algorithms, relational databases, pragmatic practices, commits and pull requests.
Plugin developer from marketplace developer-vault in facundomartinezvidal/developer-vault. Commands read from the repo's manifest — 5 days ago.
api-designDesigns and reviews APIs other code depends on: HTTP endpoints, RPC, GraphQL, webhooks, events and public library functions. Use for request and response shapes, status codes, errors, pagination, idempotency, versioning and breaking changes (\"qué status devuelvo\", \"esto rompe a los clientes\").
clean-codeMakes code readable at the level of names, functions, comments, error handling and async code, in any language. Use when code is hard to follow, a name misleads or errors are swallowed (\"esta función es muy larga\"). Step-by-step restructuring: refactoring; whole PRs: reviewing-code.
data-structures-and-algorithmsChooses data structures and algorithms and reasons about cost, in any language. Use when code is slow on large inputs, for Big-O, caching or profiling, or for sorting, search, graph and dynamic programming problems (\"esto tarda mucho\", \"qué estructura uso\"). Queries: relational-databases.
debuggingFinds the root cause of a failure with a reproduce, hypothesize and prove method, in any language. Use for stack traces, crashes, hangs, flaky or production-only failures and fixes that didn't hold (\"por qué falla\", \"falla a veces\"). Not needed when the error already shows the cause.
design-patternsChooses, applies and removes design patterns and GRASP responsibilities, in any language. Use when growing conditionals, object creation or notifications might need a pattern, to judge if one is overkill, or to explain one (\"qué patrón uso\", \"quién debería hacer esto\").
developerSoftware developer for any programming language that implements features, fixes bugs, refactors and writes tests, and also advises on code. Use for building or changing code, code review, diagnosing failures, testing strategy, secure coding, APIs, production behavior, choosing a pattern or data stru
clean-architectureReviews and designs code structure with Clean Architecture: layers, the Dependency Rule, ports and adapters, boundaries and packaging. Use when a framework, ORM or database leaks into business logic, or to decide where code lives (\"cómo estructuro el proyecto\", \"dónde va esta lógica\").
domain-driven-designModels complex business domains with ubiquitous language, bounded contexts and aggregates. Use when business terms conflict, a shared model is tangled, or a business invariant needs a consistency boundary (\"cómo modelo este dominio\", \"agregados\"). Layers and folders alone: clean-architecture.
software-designDesigns and reviews module interfaces: information hiding, what callers must know, call ordering, and failure or retry contracts. Use when one change spreads across modules, an API is easy to misuse or a layer adds nothing (\"cómo diseño esta interfaz\", \"lo separo o lo junto\").
threat-modelingThreat-models a design with STRIDE: assets, data flows, trust boundaries, ranked risks and mitigations. Use when designing or reviewing something with users, money, files, tenants, webhooks or AI agents (\"es seguro este diseño\", \"cómo lo podrían atacar\"). Vulnerable code: secure-coding.
framework-practicesApplies current practices of the framework in use, with deep guidance for ASP.NET Core and Spring Boot, checking official docs for the installed version. Use for controllers, DI, configuration, ORMs, framework security, tests, startup and upgrades (\"cómo se hace esto en Spring\").
implementing-designsTurns an architect's plan, ADR, C4 view, DDD model or threat model into working code without losing what was decided. Use to implement a design or check code against one (\"implementá lo que dijo el arquitecto\", \"cómo llevo esto a código\"). Open decisions: architect agent.
opening-pull-requestsOpens pull requests and writes their title and description following the project's conventions and PR template. Shows the exact text and publishes nothing until confirmed. Use to open or describe a PR or set up PR conventions (\"abrí el PR\", \"armá la PR\").
pragmatic-practicesAdvises on how to approach development work: unclear requirements, slicing, estimates, prototypes, unfamiliar code, dependency upgrades, merge conflicts, docs and automation (\"cómo encaro esto\", \"cuánto puede llevar\"). Not needed for a clearly specified small task.
production-readinessMakes code behave well in production with logging, metrics, tracing, timeouts, retries, graceful failure and safe releases. Use when code calls other services, runs as a job or consumer, or is about to ship (\"agregá logs\", \"está listo para producción\"). A known failure: debugging.
refactoringImproves existing code without changing behavior, using code smells and small, safe refactoring moves. Use when code resists a change, before adding a feature, or to judge if a cleanup is worth it (\"refactorizá esto\", \"qué code smells tiene\"). Layers or modules: architect agent.
relational-databasesDesigns relational schemas and migrations, writes and reviews SQL, and handles indexes, transactions and concurrency on any SQL engine or ORM. Use for tables, keys, slow queries, balances, stock or uniqueness (\"cómo modelo estas tablas\", \"falta un índice\"). Not for NoSQL.
reviewing-codeReviews diffs, pull requests and commits for correctness, safety and maintainability, with feedback people can act on. Use before merging or to check one's own change (\"revisá este PR\", \"le das una mirada\"). A whole package's structure: architect agent.
secure-codingWrites and reviews code to resist vulnerabilities, following OWASP Top 10 and CWE. Use when code handles input, SQL or shell commands, files, auth, sessions, permissions, tokens, secrets or personal data, or someone asks if code is safe (\"esto es seguro\"). Design threats: threat-modeling.
testingWrites and reviews automated tests and makes code testable, in any language. Use when behavior needs tests, mocks are brittle, a suite is slow or flaky, code has no tests, or for TDD and coverage (\"qué debería testear\", \"cómo testeo esto\"). An unknown failure: debugging.
user-interfacesBuilds and reviews screens and components on any front-end stack. Use for pages, forms, tables, modals, client state and UI bugs, including loading, empty and error states, accessibility and responsive layout (\"armame esta pantalla\", \"el formulario no anda\").
writing-commitsCreates Git commits and writes their messages following the project's conventions, looking first in conventions/commits.md. Use to commit, split a change into commits, write a message or set up commit conventions (\"hacé el commit\", \"qué título le pongo\"). Without conventions, offers a default.
developerSoftware developer for any programming language that implements features, fixes bugs, refactors and writes tests, and also advises on code. Use for building or changing code, code review, diagnosing failures, testing strategy, secure coding, APIs, production behavior, choosing a pattern or data stru
Software architecture agent and skills: decisions and ADRs, C4 documentation, threat modeling, Clean Architecture, Domain-Driven Design and software design.
13 skills · 1 agent · hooks
Collaborative pull request review assistant: understand intent and code, investigate evidence, consult developer or architect, and build useful peer feedback with the human reviewer.
2 skills · 2 agents
Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).
39 skills
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
15 skills · hooks
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications
5 skills · hooks
Cross-session memory and token savings for coding agents.
6 skills · 1 agent · 1 MCP server · hooks
Up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your coding agent's context.
1 MCP server
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.