Liste des compétences Claude

Estimate AI-assisted and hybrid human+agent development work with explicit PERT assumptions and calibration feedback loops

Build Progressive Web Apps (PWAs) with offline support, installability, and caching strategies. Trigger whenever the user mentions PWA, service workers, web app manifests,...

Project performance review: role, project and manager, delivery, quality and collaboration scores, overall score and feedback. Use for project appraisals.

This skill covers the principles for identifying tasks suited to LLM processing, designing effective project architectures, and iterating rapidly using agent-assisted development.

Govern evidence-backed canonical project state across sessions, branches, reviews, and research cycles without inventing product intent.

Build read models and projections from event streams. Use when implementing CQRS read sides, building materialized views, or optimizing query performance in event-sourced systems.

Project register: owner, team, priority, progress percentage, milestones, deliverables and budget against actual cost. Use for project tracking.

Complete guide to Prometheus setup, metric collection, scrape configuration, and recording rules.

Set up metrics collection and visualization with Prometheus and Grafana.

Promotion register: current and requested role and grade, justification, OKR and behaviour scores, time in role, salary proposal and decision. Use for upgrade requests.

Caching strategies for LLM prompts including Anthropic prompt caching, response caching, and CAG (Cache Augmented Generation)

Transforms user prompts into optimized prompts using frameworks (RTF, RISEN, Chain of Thought, RODES, Chain of Density, RACE, RISE, STAR, SOAP, CLEAR, GROW)

Master advanced prompt engineering techniques to maximize LLM performance, reliability, and controllability.

Expert guide on prompt engineering patterns, best practices, and optimization techniques. Use when user wants to improve prompts, learn prompting strategies, or debug agent...

Defend AI systems against prompt injection and indirect prompt attacks using input controls, tool permissions, output validation, and isolation boundaries.

A comprehensive collection of battle-tested prompts inspired by and community best practices.

Agent governance skill for MCP tool calls — Cedar policy authoring, shadow-to-enforce rollout, and Ed25519 receipt verification.

Comprehensive techniques for capturing, analyzing, and documenting network protocols for security research, interoperability, and debugging.

Authorized reverse engineering of custom binary protocols, Protobuf/gRPC schemas, WebSocket frames, and PCAP-driven protocol recovery.

Build a throwaway prototype to flesh out a design — a runnable terminal app for state/business-logic questions, or several radically different UI variations toggleable from one...