Sidiora-Labs/centra-llm-agents - Page 2

content-hash-cache-pattern

Cache expensive file processing results using SHA-256 content hashes — path-independent, auto-invalidating, with service layer separation.

context-budget

Audits Claude Code context window consumption across agents, skills, MCP servers, and rules. Identifies bloat, redundant components, and produces prioritized token-savings recommendations.

continuous-agent-loop

Patterns for continuous autonomous agent loops with quality gates, evals, and recovery controls.

continuous-learning

Automatically extract reusable patterns from Claude Code sessions and save them as learned skills for future use.

continuous-learning-v2

Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills/commands/agents. v2.1 adds project-scoped instincts to prevent cross-project contamination.

cost-aware-llm-pipeline

Cost optimization patterns for LLM API usage — model routing by task complexity, budget tracking, retry logic, and prompt caching.

council

Convene a four-voice council for ambiguous decisions, tradeoffs, and go/no-go calls. Use when multiple valid paths exist and you need structured disagreement before choosing.

create-cli

Design command-line interface parameters and UX: arguments, flags, subcommands, help text, output formats, error messages, exit codes, prompts, config/env precedence, and safe/dry-run behavior. Use when you’re designing a CLI spec (before implementation) or…

crosspost

Multi-platform content distribution across X, LinkedIn, Threads, and Bluesky. Adapts content per platform using content-engine patterns. Never posts identical content cross-platform. Use when the user wants to distribute content across social platforms.

dashboard-builder

Build monitoring dashboards that answer real operator questions for Grafana, SigNoz, and similar platforms. Use when turning metrics into a working dashboard instead of a vanity board.

data-scraper-agent

Build a fully automated AI-powered data collection agent for any public source — job boards, prices, news, GitHub, sports, anything. Scrapes on a schedule, enriches data with a free LLM (Gemini Flash), stores results in Notion/Sheets/Supabase, and learns from…

database-schema-design

Relational schema design playbook — normalization, keys and identifiers, constraints, indexing, migrations, and modeling common relationships. Use when designing or evolving a database schema.

date-formatting

Date and time formatting for applications. Use when displaying dates, timestamps, or formatting time in UI components. Use centralized utilities instead of native JS date methods. Triggers on date, time, timestamp, formatDate, formatTime, toLocaleDateString,…

deep-research

Multi-source deep research through Centra AI web search, fetch, and the router-owned Exa MCP. Searches, extracts, synthesizes, and delivers cited reports with explicit grounding.

deep-researcher

Use when delegating research tasks requiring verified information from multiple authoritative sources - crawls and fact-checks beyond surface-level findings, providing evidence of verification process with confidence levels for each claim

defense-in-depth

Use when invalid data causes failures deep in execution, requiring validation at multiple system layers - validates at every layer data passes through to make bugs structurally impossible

deployment-patterns

Deployment workflows, CI/CD pipeline patterns, Docker containerization, health checks, rollback strategies, and production readiness checklists for web applications.

design

Comprehensive design skill: brand identity, design tokens, UI styling, logo generation (55 styles, Gemini AI), corporate identity program (50 deliverables, CIP mockups), HTML presentations (Chart.js), banner design (22 styles, social/ads/web/print), icon…

design-system

Token architecture, component specifications, and slide generation. Three-layer tokens (primitive→semantic→component), CSS variables, spacing/typography scales, component specs, strategic slide creation. Use for design tokens, systematic design,…

dev-commands

Development commands for monorepo projects. Use when running dev servers, building apps, linting, testing, or troubleshooting build issues. Triggers on yarn, dev, build, lint, test, desktop, mobile, web, extension, ios, android, compile, bundle.

dispatching-parallel-agents

Use when facing 3+ independent failures that can be investigated without shared state or dependencies - dispatches multiple Claude agents to investigate and fix independent problems concurrently

django-patterns

Django architecture patterns, REST API design with DRF, ORM best practices, caching, signals, middleware, and production-grade Django apps.

django-security

Django security best practices, authentication, authorization, CSRF protection, SQL injection prevention, XSS prevention, and secure deployment configurations.

django-tdd

Django testing strategies with pytest-django, TDD methodology, factory_boy, mocking, coverage, and testing Django REST Framework APIs.

django-verification

Verification loop for Django projects: migrations, linting, tests with coverage, security scans, and deployment readiness checks before release or PR.

dmux-workflows

Multi-agent orchestration using dmux (tmux pane manager for AI agents). Patterns for parallel agent workflows across Claude Code, Codex, OpenCode, and other harnesses. Use when running multiple agent sessions in parallel or coordinating multi-agent…

docker-patterns

Docker and Docker Compose patterns for local development, container security, networking, volume strategies, and multi-service orchestration.

documentation-lookup

Use up-to-date library and framework docs via Context7 MCP instead of training data. Activates for setup questions, API references, code examples, or when the user names a framework (e.g. React, Next.js, Prisma).

e2e-testing

Playwright E2E testing patterns, Page Object Model, configuration, CI/CD integration, artifact management, and flaky test strategies.

ecc-tools-cost-audit

Evidence-first ECC Tools burn and billing audit workflow. Use when investigating runaway PR creation, quota bypass, premium-model leakage, duplicate jobs, or GitHub App cost spikes in the ECC Tools repo.

error-handling

Error handling patterns and best practices. Use when implementing try/catch blocks, handling async errors, showing error messages, or managing error states in UI. Triggers on error, try, catch, exception, throw, fail, failure, error handling, error boundary,…

eval-harness

Formal evaluation framework for Claude Code sessions implementing eval-driven development (EDD) principles

evm-token-decimals

Prevent silent decimal mismatch bugs across EVM chains. Covers runtime decimal lookup, chain-aware caching, bridged-token precision drift, and safe normalization for bots, dashboards, and DeFi tools.

exa-search

Grounded semantic search and asynchronous research through Centra AI's router-owned Exa MCP. Use for controlled web evidence, company research, known-URL extraction, outbound briefs, or source-grounded drafts.

executing-plans

Use when partner provides a complete implementation plan to execute in controlled batches with review checkpoints - loads plan, reviews critically, executes tasks in batches, reports for review between batches

finishing-a-development-branch

Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup

frontend-design

Create distinctive, production-grade frontend interfaces with high design quality. Use when the user asks to build web components, pages, or applications and the visual direction matters as much as the code quality.

frontend-patterns

Frontend development patterns for React, Next.js, state management, performance optimization, and UI best practices.

game-developer

Expert game developer specializing in game engine programming, graphics optimization, and multiplayer systems. Masters game design patterns, performance optimization, and cross-platform development with focus on creating engaging, performant gaming…

gateguard

Fact-forcing gate that blocks Edit/Write/Bash (including MultiEdit) and demands concrete investigation (importers, data schemas, user instruction) before allowing the action. Measurably improves output quality by +2.25 points vs ungated agents.