All authors
CarlosCaPe avatar

Claude Skills by CarlosCaPe

github.com/CarlosCaPe
204 skillsA× 200B× 3C× 10 installs43 views
4d Paradigm ProtocolA

Protocolo completo del paradigma 4D (Describe, Delegate, Diligent, Disclose): el gate de 3 preguntas del 2D, el formato del Change Manifest, la matriz de validacion 3D y el Impact Radius. CLAUDE.md solo trae el resumen. Carga antes de escribir archivos o armar un manifiesto.

ai-agentspythongo
0
15
4d SpecA

Orchestrator that merges the 4D Paradigm with Spec-Driven Development (SDD). Classifies task complexity and activates SDD phases only when warranted. Use at the START of any implementation task to determine the right workflow depth.

ai-agentsgitapi
0
15
Ado Pr Merge Via ApiA

Completa merges de Pull Request en Azure DevOps por REST API cuando la UI no sirve o hay que scriptear en lote. Cubre los 403 por threads sin resolver, voto en 'waiting for author' y CI gate rancio.

ai-agentsnodeazure
0
15
Ado Refactor Performance GateA

Mandatory performance gate for Azure DevOps SQL refactor tickets. Use when a ticket includes stored procedure refactor/review and you must validate execution plans, index usage, parameter sniffing risk, and query structure optimization opportunities.

ai-agentssqlazure
0
15
Agent BrowserA

CLI de automatizacion de navegador para agentes, nativo en Rust, sin Playwright. Navega, llena formularios, da clic, toma screenshots y extrae datos. Dispara con 'abre el sitio', 'toma screenshot', 'prueba esta web', 'QA'.

ai-agentsjavascriptrust
0
15
Agent Proof Approval GateA

Build a fail-closed PreToolUse gate for merge/deploy/destructive actions that the AI agent provably cannot self-bypass. Use when you need human-only override for a consequential action the agent orchestrates.

ai-agentspythongo
0
15
Anthropic Enterprise AnalyticsA

Pull Anthropic's Admin API usage_report into ~/.claude/analytics/ so brain-digest can reconcile estimated cost (from session JSONL list-price math) against actual billed cost (from Anthropic). Closes the estimated-vs-billed gap that any operator running on Pro/Max/Enterprise has.

ai-agentspythongo
0
15
Arm OnboardingA

Protocolo paso a paso para crear un arm nuevo de cliente: archivos requeridos, sync-ai-docs, el grafo de linaje sellado del arm, alta en QueryMaster y la higiene de gitignore. Dispara con 'crear un arm' u 'onboard a un cliente'.

ai-agentsgobash
0
15
Arm SyntheticsA

Per-arm health check templates. Each arm defines a synthetics.yaml with endpoints to probe + expected responses + cron schedule. The skill ships the template + GH Action runner. Failures open issues IN THE ARM REPO (not the brain) to preserve octopus arm isolation. Use when onboarding a new arm or when an arm's health monitoring needs a scheduled probe.

ai-agentsgogit
0
15
Ask With RecommendationA

Toda pregunta de opcion multiple al operador lleva recomendacion explicita marcada mas su razon (impacto, alcance, tiempo, riesgo de esperar). Aplica a cada AskUserQuestion y a cada 'quieres X o Y?' en prosa.

ai-agentsgoapi
0
15
Atomic 3phase Ddl ScriptsA

Atomic 3-Phase DDL Scripts

ai-agentsgosql
0
15
Autovacuum Bloat ManagementA

Autovacuum & Table Bloat Management

ai-agentsrustgo
0
15
Backward Compatible Schema ChangesA

Backward-Compatible Schema Changes

ai-agentsgosql
0
15
Batch Import Relative PathsA

When you batch-add an `import` line to N source files via sed/awk, the relative path must be computed PER-FILE (depth varies). Vite/esbuild often silently normalize bad `../` and the bug hides across multiple deploys until a larger rebuild forces strict module resolution.

ai-agentstypescriptpython
0
15
Browser Bearer Graph AuthA

Conditional-Access-resilient OAuth alternative for Microsoft Graph: drive a Playwright + Edge persistent context to capture the bearer token during normal sign-in. Works when Device Code Flow / headless OAuth is blocked by AADSTS53003 (Device state: Unregistered). Outlook Web grants a broader scope set than Teams Web. Hard-won workaround that should NOT be the production answer.

ai-agentsgoshell
0
15
Bruno Postman AlternativeA

Cliente de API open-source donde las colecciones son archivos de texto en el repo, revisables por PR, sin nube ni licencias por equipo. MIT. Para equipos que viven en git o cuando Postman sale caro.

ai-agentsgobash
0
15
Bug HunterA

Adversarial bug hunting with a sequential-first pipeline (Recon, Hunter, Skeptic, Referee) that can optionally use safe read-only parallel triage. Finds, verifies, and auto-fixes real bugs by default (with --scan-only opt-out) using checkpointed verification and resume state for large codebases. Use this skill whenever the user wants bug finding, security audits, regression checks, or code review focused on runtime behavior.

ai-agentsrustgo
0
15
Commit Security ScanA

Scan code changes for security vulnerabilities using Bug Hunter-native artifacts and STRIDE context. Use whenever the user asks for PR security review, commit-diff scanning, staged-change security checks, branch-comparison security review, or pre-merge security analysis of changed code.

ai-agentssqlgit
0
15
Doc LookupA

Unified documentation lookup for Bug Hunter agents. Uses Context Hub (chub) as primary source with Context7 API fallback. Provides verified library/framework documentation to prevent false positives and ensure correct fix patterns.

ai-agentsbashsql
0
15
FixerA

Surgical code fixer for Bug Hunter. Implements minimal, precise fixes for verified bugs. Uses doc-lookup (Context Hub + Context7) to verify correct API usage in patches. Respects fix strategy classifications (safe-autofix vs manual-review vs larger-refactor).

ai-agentsnodeexpress
0
15
HunterA

Deep behavioral code analysis agent for Bug Hunter. Performs multi-phase scanning to find logic errors, security vulnerabilities, race conditions, and runtime bugs. Uses doc-lookup (Context Hub + Context7) for framework verification. Reports structured JSON findings.

ai-agentstypescriptrust
0
15
ReconA

Codebase reconnaissance agent for Bug Hunter. Maps architecture, identifies trust boundaries, classifies files by risk priority, and detects service boundaries. Does NOT find bugs — finds where bugs hide.

ai-agentsrustgo
0
15
RefereeA

Final arbiter for Bug Hunter. Receives Hunter findings and Skeptic challenges, independently re-reads code, and delivers authoritative verdicts with CVSS scoring and proof-of-concept generation for security findings.

ai-agentsrustgo
0
15
Security ReviewA

Run a focused STRIDE-based security review using Bug Hunter-native artifacts. Use whenever the user asks for a full security audit, repository security review, weekly security scan, PR security review with deeper validation, or wants dependency CVEs and threat-model context combined into one workflow.

ai-agentsnodesecurity
0
15
SkepticA

Adversarial code reviewer for Bug Hunter. Rigorously challenges each reported bug to determine if it's real or a false positive. Uses doc-lookup (Context Hub + Context7) to verify framework claims before disproval. The immune system that kills false positives.

ai-agentstypescriptrust
0
15
Threat Model GenerationA

Generate or refresh a STRIDE-based threat model for the current repository using Bug Hunter-native artifacts. Use whenever the repository has no threat model yet, the architecture changed materially, a security review needs fresh trust-boundary context, or the user explicitly asks for a threat model.

ai-agentsrustsecurity
0
15
Vulnerability ValidationA

Validate security findings for exploitability, reachability, and real-world impact using Bug Hunter-native findings artifacts. Use after security scans, before patch generation, or whenever the user wants confirmation that a suspected vulnerability is actually exploitable.

ai-agentsrustsecurity
0
15
Cache Bust Deploy ValidationA

After a production deploy of a CDN-fronted site, force cache-bust on every validation request and inspect Age/cache-status headers — the CDN can serve a stale 200 with old content for hours, hiding a broken deploy. Use whenever validating a freshly-deployed web app, debugging "deploy completed but the live site shows the old version", or building a post-deploy smoke test.

ai-agentsgobash
0
15
Canary SymbiontA

Centinela cross-plane: un watcher en el plano B detecta la muerte SILENCIOSA del scheduler del plano A (bloqueo de billing, cron load-shedding) y avisa por correo. Fail-open. Incluye el test en vivo obligatorio.

ai-agentsrustgo
0
15
Capture Ends With TriageA

Un pipeline programado que solo vuelca datos crudos obliga al humano a sintetizar, y por eso se omite. Todo capture debe cerrar con un paso de TRIAGE que diagnostique causa y siguiente accion. Aplica al construir o revisar cualquier job periodico.

ai-agentsvueapi
0
15
Case Insensitive UniquenessA

Case-Insensitive Uniqueness (Functional Indexes)

ai-agentsgosql
0
15
Ccxt PythonA

Libreria CCXT para exchanges de cripto en Python, REST y WebSocket: conectar, bajar datos de mercado, colocar ordenes y transmitir tickers. Para bots de trading y analisis, sync o asyncio.

ai-agentspythongo
0
15
Chatgpt AppsA

Construye y depura apps del ChatGPT Apps SDK que combinan servidor MCP y UI de widget: definir tools, registrar recursos de UI, puente MCP Apps, metadata, CSP y dominios. Consulta la doc antes de generar codigo.

ai-agentspythongo
0
15
Claude Mem Persistent MemoryA

Memoria persistente entre sesiones para agentes de codigo: captura la sesion, la comprime y reinyecta lo relevante despues, con ~75% menos tokens. AGPL 3.0, ojo con el copyleft en entregables comerciales.

ai-agentsgobash
0
15
Claude Plugins OfficialA

Official, Anthropic-managed directory of high quality Claude Code Plugins.

ai-agentspythongit
0
15
Claude Usage ReportA

Aggregate Claude Code usage (tokens, sessions, API-equivalent cost) by day, week, month, model, and project from local JSONL session logs. Use when the user asks about their Claude Code usage, consumption, costs, "cuánto he usado", "uso diario/semanal/mensual", or wants to audit which projects/models are eating the most tokens.

ai-agentspythonrust
0
15
Client Doc LintA

Reflejo de QA antes de mandar un entregable generado a cliente: revisa acentos rotos, em-dash, fechas ya pasadas, falta de nota fiscal cuando hay montos, e inventaria cada monto. Correlo antes de decir 'listo para enviar'.

ai-agentspythongo
0
15
Cloudflare DeployA

Deploy applications and infrastructure to Cloudflare using Workers, Pages, and related platform services. Use when the user asks to deploy, host, publish, or set up a project on Cloudflare. Also use when the user needs to purge or clear Cloudflare cache after deploys, or automate cache invalidation.

ai-agentsgobash
0
15
Cloudflare Email ServiceA

Envia y recibe correo transaccional con Cloudflare Email Service (Sending mas Routing), por binding de Workers o REST. Cubre entregabilidad, SPF, DKIM, DMARC y setup con wrangler.

ai-agentstypescriptpython
0
15
Column Renames Metadata OnlyA

Column Renames (Metadata-Only)

ai-agentsgosql
0
15
Command Boundary Hook MatchingA

Pattern-match what a Bash command actually does in a PreToolUse hook without false-firing on mentions inside quoted args, commit messages, or echo strings. Use when building any hook that decides based on command semantics.

ai-agentspythonshell
0
15
Config Driven DiagramsA

Build config-driven architecture diagrams as dark-themed SVG/PNG with swimlanes, embedded logos, auto-layout, and overlap validation. Use when the user asks for architecture diagrams, data flow diagrams, system topology, or any visual diagram that should be rendered programmatically from a JSON config. Trigger on: diagram, architecture diagram, data flow, swimlane, render SVG, render PNG, system diagram, topology.

ai-agentspythongo
0
15
Connection Pooling Timeout SafetyA

Connection Pooling & Timeout Safety

ai-agentsgosql
0
15
Content Deduplication DisciplineA

Content Deduplication Discipline

ai-agentsjavascriptrust
0
15
Coolify Self Hosted PaasC

Alternativa autoalojada a Vercel, Heroku y Render: despliega apps, bases y servicios en tu propio servidor con git-push, SSL automatico y sin costo por asiento. Apache 2.0.

ai-agentsgobash
0
15
Cotizacion Legal BaselineA

Clausulado legal base Mexico B2B que TODA cotizacion o propuesta lleva desde el borrador 1: propiedad intelectual, LFPDPPP, confidencialidad, limite de responsabilidad, garantia, licenciamiento e IVA.

ai-agentsgo
0
15
Coworking Concept CollisionA

Protocol for when two live sessions are codifying the SAME concept concurrently (not just sharing a working tree). Detect semantic friction BEFORE committing, defer ownership to whoever is further ahead, and integrate from an isolated dimension. Trigger — a file you are about to reference or claim primacy over shows as modified (M) by another live session, or your new skill overlaps a concept another dimension is actively editing.

ai-agentsgogit
0
15
Cron Bridge Daily PublisherA

Patron para autopublicar a diario N elementos curados desde D1 a una plataforma social via el worker programador. Incluye rotacion justa, idempotencia por hash, dedup por sentinel y barrido de retraccion.

ai-agentsgosql
0
15
Cross Reference IntegrityA

Cross-Reference Integrity

ai-agentsjavascriptrust
0
15
Daily ReflectionA

Retro honesta de fin de sesion, errores primero, que destila la leccion a memoria del cerebro. Dispara con 'que aprendiste hoy?', 'reflexiona', '/reflect', 'what did you learn today', 'how would you be better tomorrow'.

ai-agentspythonrust
0
15