arc-search
Semantic and full-text search across indexed collections. Use when user mentions searching a collection, semantic search, vector search, knowledge base, or finding content in indexed code, markdown, or PDFs.
Découvrez les skills Recherche, comparez leurs dépôts et consultez leurs instructions.
Semantic and full-text search across indexed collections. Use when user mentions searching a collection, semantic search, vector search, knowledge base, or finding content in indexed code, markdown, or PDFs.
MeiliSearch index management for full-text search. Use when user mentions managing indexes, creating index, listing indexes, verifying index health, exporting or importing indexes, or viewing indexed items in M...
Docker container management for Qdrant and MeiliSearch services. Use when user mentions starting services, stopping services, checking container status, viewing logs, restarting containers, or resetting databas...
Qdrant collection management for semantic search. Use when user mentions managing collections, creating collection, listing collections, verifying collection integrity, exporting or importing collections, or vi...
This skill should be used when the user asks to review, consolidate, organize, or clean up memories. Triggers on requests like "review what you remember," "consolidate my memories," "what patterns do you notice...
Simplifies and refines code for clarity, consistency, and maintainability while preserving all functionality. Focuses on recently modified code unless instructed otherwise.
Code review workflow using GitHub CLI. Use when reviewing pull requests, checking PR diffs, adding review comments, or approving/requesting changes on PRs.
Investigate why code was written a certain way. Use when tracing decision history through git blame, commit logs, PRs, and issues to understand the reasoning behind code changes.
Guide for MEV concepts, common attacks, mitigations, and how to organize MEV-related resources in README.md.
Guide for EVM/solidity smart contract security work: vulnerability taxonomy, review workflow, and where to place resources in README.md.
Guide for wallet security topics: MPC/TSS, key management, wallet UX security, phishing, and how to categorize related resources in README.md.
Guide for Solana/Sealevel security research and where to organize Solana-specific resources in README.md.
Guide for security tooling (analyzers, fuzzers, decompilers, compilers) and consistent placement in README.md.
Guide for understanding and contributing to the awesome-web3-security curated resource list. Use this skill when adding resources, organizing categories, or maintaining README.md consistency (no duplicates).
Critical rules and best practices for working with markdown files.
Use for code review - runs all reviewers in parallel on uncommitted changes
MANDATORY when writing commit messages. Structures commits with type prefix, what+why body, and architectural file tree.
Use when executing implementation plans. Modes: batched with checkpoints, subagent per task, or parallel agents for independent failures.
MANDATORY for all naming decisions - variables, functions, files, folders, classes, database tables, routes, CSS classes. Must be followed when creating or renaming any identifier. Non-negotiable baseline for c...
MANDATORY when writing tests. Test behavior, not implementation. Functional tests are primary. Unit tests ONLY for state mutations. Includes fixing flaky tests with condition-based waiting.
Use when encountering bugs, test failures, or unexpected behavior. Combines systematic debugging framework, root cause tracing, and defense-in-depth validation.
Use when exploring/explaining code, designing/updating architecture, or when asked to visualize structure. Shows annotated file trees inline.
Use when building UI components, styling pages, or making visual/interaction decisions. Guides design thinking, anti-patterns, CSS architecture, and responsive patterns.
Use when planning implementation - either writing detailed plans for engineers or structuring complex decisions via questions.
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.