test-writer
Writes comprehensive test cases following testing best practices. Use when writing tests, creating unit tests, or asking about test coverage.
Découvrez les skills Tests et sécurité, comparez leurs dépôts et consultez leurs instructions.
Writes comprehensive test cases following testing best practices. Use when writing tests, creating unit tests, or asking about test coverage.
Multi-disciplinary strategy council with 5 expert personas. Use for strategic analysis, impact assessment, complex decisions requiring diverse expertise. Includes cross-examination to identify contradictions be...
File-mediated parallel security audit for codebases. Launches domain-specific auditors that write findings to files, then synthesizes into consolidated report. Token-efficient through file state instead of cont...
Lean code implementation pair. Claude (Smith) writes code, Gemini (Temper) reviews for bugs, security, and edge cases. ~2x token cost for high-quality code output.
Tree of Thoughts exploration for brainstorming and finding unknown unknowns. Recursively branches hypotheses, ranking by NOVELTY not probability. Use for idea generation, creative unblocking, exploring possibil...
Adversarial research validation using Red Team/Blue Team methodology. Use when researching complex topics, fact-checking claims, or producing research reports. Validates outputs through Gemini 3 Pro critic befo...
Hierarchical task execution with planning, verification, and replanning. Use for complex multi-step tasks with dependencies. Planner creates manifest, workers execute steps, inspector verifies.
Instructions for selecting and configuring Gemini 3 Pro Preview model in Gemini CLI. Use when the user asks about switching models in Gemini CLI, enabling Gemini 3, or configuring Gemini CLI model settings.
3x3 Parallel Debate system for high-confidence research. Spawns 9 agent instances (3 Proposer/Skeptic/Judge cohorts) to argue, critique, and adjudicate claims. Use for complex queries, controversial topics, or...
Map-Reduce system for comprehensive reports and literature reviews. Breaks topic into chapters, researches each in parallel, then weaves into unified document. Use for deep research, reports, and synthesis.
Use when the user asks to manage Cloudflare tunnels, start/stop tunnels, configure tunnel routing, check tunnel status, or expose local services via Cloudflare. Covers cloudflared CLI operations for tunnel mana...
Three-stage code implementation with planning. Gemini (Engineer) plans, Claude (Caster) implements, Gemini (Inspector) verifies. ~3x token cost for complex, multi-file changes.
Scout swarm for broad domain mapping and edge case discovery. Launches multiple high-temperature agents with distinct search vectors. Use for finding obscure data, edge cases, and mapping new territories.
Find academic citations to support or verify claims by searching scientific literature. Use when fact-checking statements, finding authoritative sources for claims, or verifying research assertions with confide...
Generate structured literature reviews on research topics by synthesizing findings from multiple papers. Use when conducting research surveys, identifying themes and gaps, or preparing academic writing on any s...
Search for academic papers using natural language queries via Asta's semantic search across 225M+ papers. Use when finding research papers, exploring literature, or discovering relevant academic work on any sci...
Retrieve comprehensive details about a specific academic paper including abstract, citations, references, and related work. Use when you have a paper ID (DOI, ArXiv, etc.) and need full metadata, citation infor...
Core engineering principles for quality, maintainable code.
TypeScript and JavaScript coding standards and best practices.
Guidelines and checklist for thorough code review.
React and Next.js patterns, hooks, and component architecture.
Guidelines for clear technical writing and documentation.
End-of-session consolidation for AI-ready vaults. Use before ending a work session to capture learnings, store important memories, and preserve context for future sessions. Counterpart to /hydrate.
Load context from an AI-ready vault at session start. Use when beginning a new conversation, starting work on a vault, or when context feels stale. Reads CLAUDE.md, checks recent session logs, loads relevant me...
Le classement utilise les étoiles du dépôt GitHub indexé. Plusieurs skills peuvent partager ce nombre : ce n’est ni un nombre d’installations ni une note de qualité.