jggomez/expert-ai-developer-skills

jggomez/expert-ai-developer-skills

Skill Claude CodeCodex

Use when the user wants to install, set up, check or remove agent-meter (token, API-equivalent cost and latency metrics for Claude Code and Antigravity per project, client, task and subagent), asks "how much did this task / project / client cost", "why is my agent slow or expensive", wants a local report or a BigQuery…

jggomez/expert-ai-developer-skills

Skill Claude CodeCodex

Author and validate Zero-Fluff technical documentation, root AGENTS.md, Google DESIGN.md alignment, Diátaxis guides, and Mermaid diagrams with strict conciseness caps and relative link verification.

jggomez/expert-ai-developer-skills

Skill Claude CodeCodex

Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.

jggomez/expert-ai-developer-skills

Skill Claude CodeCodex

Design and validate automated tests, concise IEEE/ISTQB TC-XX test cases, hermetic Arrange-Act-Assert (AAA) suites, Gherkin BDD scenarios, and Fail-Honest execution reporting across languages.

jggomez/expert-ai-developer-skills

Skill Claude CodeCodex

Guidelines, best practices, and script validators to verify commit message formats and configure local git commit hooks.

jggomez/expert-ai-developer-skills

Skill Claude CodeCodex

Prepare, audit, and author concise ( /test-matrix.md links, and transparent BLOCKED/SKIPPED gate disclosure.

jggomez/expert-ai-developer-skills

Skill Claude CodeCodex

Implements 3-Tier Adaptive SDLC state machines, capability-gated discovery, target-project AGENTS.md bootstrapping, isolated parallel worker execution (Disjoint Mode A / Git Worktree Mode B), and 3-loop self-correcting review gates.

jggomez/expert-ai-developer-skills

Skill Claude CodeCodex

Analyze a repository's structure, stack, commands, and invariants to create a high-signal Codebase Map (.agents/rules/project-context.md <= 80 lines) and bootstrap/sync root AGENTS.md and context/memory/MEMORY.md.

jggomez/expert-ai-developer-skills

Skill Claude CodeCodex

Adversarial stress testing, fuzzing, worst-case inputs, failure-path probes, timeout/reconnection simulations, and concurrency/memory stress.

jggomez/expert-ai-developer-skills

Skill Claude CodeCodex

Black-box browser verification validating real user flows, GUI forms, console/network errors, visual layouts, and 4-viewport screenshot evidence using deterministic Playwright execution.

jggomez/expert-ai-developer-skills

Skill Claude CodeCodex

Implements linters, code formatters, and automated build pipelines (CI/CD) to prevent syntax errors, enforce style consistency, and prevent failing builds from being merged. Use this skill when asked to add linters, configure docker builds, or set up GitHub Actions workflows.

jggomez/expert-ai-developer-skills

Skill Claude CodeCodex

Independent code review inspecting cyclomatic complexity, DRY, SOLID, anti-patterns, maintainability, and interface robustness.

jggomez/expert-ai-developer-skills

Skill Claude CodeCodex

Guides the implementation of code using Test-Driven Development (TDD) and clean code principles. Trigger when implementing new features, fixing bugs, or refactoring existing code.

jggomez/expert-ai-developer-skills

Skill Claude CodeCodex

Analyzes source code to identify, classify, and diagnose architectural design flaws known as "Code Smells" and technical debt. Use this skill when requested to perform a technical audit, evaluate code quality, look for SOLID violations (especially SRP and OCP), or identify reasons why code is difficult to maintain or…

jggomez/expert-ai-developer-skills

Skill Claude CodeCodex

Guides the final quality assurance and compliance verification of a project. Trigger when checking non-functional requirements, static code analysis, test coverage, and security compliance before release.

jggomez/expert-ai-developer-skills

Skill Claude CodeCodex needs its repo

Use when finishing a task at State 5 (Ship & Finish) or when the user explicitly asks to "save context", "guarda contexto", "record decisions", or "hand off" — writes ultra-compact persistent memory to context/memory/ and ensures target-project root AGENTS.md (<= 90 lines) stays wired to DESIGN.md and MEMORY.md across…

jggomez/expert-ai-developer-skills

Skill Claude CodeCodex

Use at session start (State 0) or when asked to "load context", "catch up", or "what was done before" — prioritizes LLM Wiki Progressive Disclosure (context/memory/MEMORY.md) across Claude Code and Google Antigravity while supporting user-confirmed restore for scripted sessions (context/sessions/).

jggomez/expert-ai-developer-skills

Skill Claude CodeCodex

Manages database schema migrations, seed data scripts, and table versioning in Python backends (Alembic, SQL). Use this skill when asked to change DB schemas, write migrations, or write seeding scripts.

jggomez/expert-ai-developer-skills

Skill Claude CodeCodex

Drafts concise Backend / API Design Specifications and Software Design Documents (docs/ /api-spec.md or SDD <= 70 lines) before coding when introducing new endpoints, schemas, or services.

jggomez/expert-ai-developer-skills

Skill Claude CodeCodex

Identifies, diagnoses, and remediates performance bottlenecks, memory leaks, and architectural scaling limitations. Use this skill when asked to optimize slow queries, configure caching mechanisms, design asynchronous worker systems, or perform load profiling.

jggomez/expert-ai-developer-skills

Skill Claude CodeCodex

Analyzes ambiguous feature requests, clarifies business rules, and authors the ultra-concise ## Product section of the single discovery file docs/ /spec.md (<= 50 lines) with standard User Stories (US-XX) and testable Acceptance Criteria (AC-XX).

jggomez/expert-ai-developer-skills

Skill Claude CodeCodex

Guides PEP 8 compliance, modern static type hinting (Python 3.10+ PEP 604, Protocols), generator pipelines, memory optimization (slots, dataclasses), structured concurrency (asyncio TaskGroup), and production error handling in Python applications. Use when writing pure Python modules, utility functions, algorithms, or…

jggomez/expert-ai-developer-skills

Skill Claude CodeCodex

Designs and executes Unit, Integration, and E2E test suites and authors concise, actionable IEEE/ISTQB QA Test Matrix artifacts (docs/ /test-matrix.md <= 80 lines) backed by empirical exit code 0 terminal proof.

jggomez/expert-ai-developer-skills

Skill Claude CodeCodex

Executes structural improvements on existing code to increase maintainability, readability, and extensibility without altering external behavior. Use this skill to address technical debt, fix "Code Smells", apply design patterns, or improve adherence to SOLID principles.