All Skills

164 skills in the catalog

Docker Deployment Architect

Attested

Designs production-grade Docker Compose stacks with service isolation, secrets, health checks, and reverse proxy configurations.

risk: lowpublished

IAM Policy Enforcer

Attested

Generates exact, least-privilege AWS IAM policies. No wildcards. Covers Lambda, API Gateway, EventBridge, cross-account, and permission boundaries.

risk: lowpublished

IoT Event Mocker

Attested

Generates IoT/webhook mock payloads and deterministic unit tests for event evaluation engines. Supports Ring, generic webhooks, and cooldown/rate-limit testing.

risk: lowpublished

Loki Mode

Attested

Multi-agent autonomous development system. 41 agent types across 7 swarms, builds from PRD with zero human intervention. RARV+C cycle with 7 quality gates.

risk: mediumpublished

MCP Tool-Use Enforcer

Attested

Enforces surgical MCP server usage preventing context flooding, unconstrained queries, and silent mutations. Governs all MCP interactions regardless of server.

risk: lowpublished

Next.js Full-Stack

Attested

Full-stack Next.js with App Router, Tailwind, TypeScript, Drizzle ORM, Supabase/PostgreSQL. Server actions, RSC, and auth patterns.

risk: lowpublished

Policy DSL Designer

Attested

Designs policy DSLs, WASM sandbox plugins, and policy validation pipelines for governance rule engines.

risk: lowpublished

Adversarial Test Suite

Attested

Generates adversarial attack tests, property-based invariant tests (proptest), and security boundary tests for enforcement systems. Supports Rust, TypeScript, and Python.

risk: lowpublished

AWS Serverless Architect

Attested

Designs AWS serverless infrastructure (API Gateway, EventBridge, SQS, Lambda, DynamoDB, Timestream) with IaC templates and Rust Lambda handlers.

risk: lowpublished

CLI/TUI Architect

Attested

Designs production-grade Rust CLI binaries with clap subcommands and ratatui terminal UIs.

risk: lowpublished

PRD Generator

Attested

Converts raw feature ideas into sprint-ready PRDs. Also handles architecture docs, feature specs, technical briefs, and sprint planning.

risk: lowpublished

Lead Follow-Up

Pending Review

Captures leads and sends personalized follow-up across channels.

risk: T0_STANDARDcandidate

Web Search

Pending Review

Searches the internet for real-time information and returns structured results.

risk: T0_STANDARDcandidate

Governance Logging

Pending Review

Persists detailed audit logs for compliance reviews.

risk: T0_STANDARDcandidate

Summarization

Pending Review

Condenses long documents, threads, or pages into concise key points.

risk: T0_STANDARDcandidate

Data Extraction

Pending Review

Pulls structured data from unstructured sources like PDFs, web pages, or emails.

risk: T0_STANDARDcandidate

Classification

Pending Review

Categorizes inputs like emails, leads, or tickets into predefined labels.

risk: T0_STANDARDcandidate

Sentiment Analysis

Pending Review

Detects the emotional tone of text - positive, negative, or neutral.

risk: T0_STANDARDcandidate

Research & Enrichment

Pending Review

Gathers background info on people, companies, or topics from multiple sources.

risk: T0_STANDARDcandidate

Scheduling

Pending Review

Reads calendars, finds open slots, and books meetings automatically.

risk: T0_STANDARDcandidate

Code Generation

Pending Review

Writes, reviews, or debugs code snippets based on a prompt or spec.

risk: T0_STANDARDcandidate

Memory & Context

Pending Review

Stores and retrieves past interactions to maintain continuity across sessions.

risk: T0_STANDARDcandidate

RAG (Retrieval Augmented)

Pending Review

Answers questions by searching a private knowledge base before generating a response.

risk: T0_STANDARDcandidate

Decision Routing

Pending Review

Evaluates conditions and routes tasks to the right branch or agent.

risk: T0_STANDARDcandidate