wojons/skills

accessibility-audit

Use when you need comprehensive accessibility auditing including WCAG compliance, legal requirements mapping, and user testing with disabilities

Langue du texte source : anglais

adversarial-thinking

Apply systematic adversarial thinking patterns including devil's advocate, assumption busting, red teaming, and white hat security approaches

Langue du texte source : anglais

ai-collab-dev

A 10-step methodology for building software with AI collaboration - from north star through automated Ralph loop execution with zero human-in-the-loop code writing

Langue du texte source : anglais

api-documentation

Use when you need to generate comprehensive API documentation for REST/HTTP, gRPC, GraphQL, and RPC APIs

Langue du texte source : anglais

assumption-buster

Aggressively challenge and attempt to disprove assumptions through counterexamples, edge cases, and adversarial thinking

Langue du texte source : anglais

assumption-testing

Identify, document, and explicitly test assumptions rather than leaving them implicit and untested

Langue du texte source : anglais

baby-steps

Core operational directive for incremental development using the Baby Steps Methodology - break work into smallest possible meaningful changes with validation at every step

Langue du texte source : anglais

best-practice-guide

Analyze project documentation to identify missing context, then generate and store best practice guides using web search when available

Langue du texte source : anglais

cloud-cost-optimization

Use when you need to analyze and optimize cloud costs across multiple cloud providers (AWS, Azure, GCP)

Langue du texte source : anglais

code-migration

Guide framework and library migrations with incremental strategies, breaking change analysis, compatibility testing, and automated migration tools

Langue du texte source : anglais

completeness-validator

Validate true completion vs superficial "done" - ensure code is wired up, tested, and production-ready using multilingual completion semantics

Langue du texte source : anglais

context-pack

Pack codebases, folders, or ZIP archives into LLM-friendly context format with smart filtering, file selection, and markdown structure

Langue du texte source : anglais

data-flow-architect

Design and document comprehensive data flow architectures across systems, services, networks, databases, and protocols using systematic methodology

Langue du texte source : anglais

data-validation

Use when you need to validate data quality, types, schemas, and consistency across systems

Langue du texte source : anglais

database-optimization

Use when you need to optimize database performance, schema design, indexing, and query performance across different database systems

Langue du texte source : anglais

dependency-upgrade

Analyze and safely upgrade dependencies with breaking change detection, version compatibility checks, impact analysis, and migration planning

Langue du texte source : anglais

devils-advocate

Challenge ideas, assumptions, and decisions by playing devil's advocate to identify weaknesses and prevent groupthink

Langue du texte source : anglais

distributed-tracing-logs

Implement distributed tracing using logs, including trace context propagation, span logging, correlation IDs, and OpenTelemetry integration for observability

Langue du texte source : anglais

dogfooding

Use when you need to test and validate the skills repository using the skills system itself, practicing "eating your own dog food"

Langue du texte source : anglais

exhaustive-specification

Write exhaustive specifications for autonomous AI systems that leave nothing to chance, covering every detail from UI to database schemas with adversarial refinement

Langue du texte source : anglais

gap-analysis

Identify discrepancies between documented requirements and actual implementation through systematic comparison and analysis

Langue du texte source : anglais

git-release

Create consistent releases and changelogs

Langue du texte source : anglais

hypercognitive-skill-compiler

Transform complex skill requirements into complete Agent Skills using exhaustive hypercognitive compiler thinking patterns

Langue du texte source : anglais

incident-response

Use when you need to manage incidents and conduct post-mortem analysis to improve system reliability and security

Langue du texte source : anglais

index

Maintain directory organization with index files (_index.md/_index.yaml/_index.json) and consistency prompts (_prompt.md)

Langue du texte source : anglais

log-analysis-parsing

Parse, analyze, search, and extract insights from logs using various techniques including regex, parsing engines, and log analysis tools

Langue du texte source : anglais

log-management-system

Implement comprehensive log management including rotation, retention, forwarding, aggregation, storage, and lifecycle management

Langue du texte source : anglais

logging-fundamentals

Implement proper logging practices including log levels, structured logging, context propagation, and logging best practices for applications and systems

Langue du texte source : anglais

logging-performance-optimization

Optimize logging performance including overhead reduction, async logging, buffering, sampling, and performance impact analysis for high-throughput systems

Langue du texte source : anglais

notebooklm-federated-specs

Manage federated specification files merged into NotebookLM notebooks for token-efficient context access, human learning materials, deep dive analysis, and on-demand research

Langue du texte source : anglais

observability-logging

Use logs as part of comprehensive observability strategy including metrics, traces, alerts, and dashboards for system understanding and operational excellence

Langue du texte source : anglais

opencode-config

Configure OpenCode settings using JSON or Markdown files for project-specific or global preferences

Langue du texte source : anglais

performance-profiling

Analyze system and application performance using Linux kernel-level tools (perf, ftrace, eBPF, SystemTap) and application-level profiling to identify bottlenecks and optimize performance

Langue du texte source : anglais

ralph-wiggum-loop

Enterprise-grade AI-driven development workflow engine with steering packet architecture for real-time control, plugin system, agent orchestration, monitoring, and complex workflow patterns. Build-verify loops that iterate until success.

Langue du texte source : anglais

react-review

Review React components for best practices and performance issues

Langue du texte source : anglais

reality-validation

Compare system behavior against real-world expectations and domain knowledge rather than just technical specifications

Langue du texte source : anglais

redteam

Think and act like an attacker to identify security vulnerabilities, weaknesses, and penetration vectors through adversarial security testing

Langue du texte source : anglais

security-scan

Use when you need comprehensive security scanning across applications, infrastructure, and dependencies with LLM-based analysis

Langue du texte source : anglais

sherlock-debugging

Apply Sherlock Holmes' deductive method to debug code, diagnose system issues, and solve technical puzzles using systematic elimination and logical reasoning

Langue du texte source : anglais

skill-builder

Build basic to intermediate Agent Skills using structured templates and validation tools

Langue du texte source : anglais