メニュー
このリポジトリの skills
SkillsMP は Sidiora-Labs/centra-llm-agents から 186 件の skill を収集しています。skill を開くとソースと詳細を確認できます。
Sidiora-Labs/centra-llm-agents収集済み skill 186 件中 40 件を表示しています。
Performance optimization guidelines for React/React Native applications. Use when optimizing app performance, fixing UI freezes/lag, reducing re-renders, handling concurrent operations, or analyzing performance bottlenecks. Triggers on performance,…
原文の言語: 英語
Write-time code quality enforcement using Plankton — auto-formatting, linting, and Claude-powered fixes on every file edit via hooks.
原文の言語: 英語
Security-first PR review checklist. Use when reviewing diffs/PRs, especially changes involving auth, networking, sensitive data, or dependency/lockfile updates. Focus on secret/PII leakage risk, supply-chain risk (npm + node_modules inspection),…
原文の言語: 英語
Translate PRD intent, roadmap asks, or product discussions into an implementation-ready capability plan that exposes constraints, invariants, interfaces, and unresolved decisions before multi-service work starts. Use when the user needs an ECC-native…
原文の言語: 英語
Use this skill to validate the "why" before building, run product diagnostics, and pressure-test product direction before the request becomes an implementation contract.
原文の言語: 英語
Operate execution flow across GitHub and Linear by triaging issues and pull requests, linking active work, and keeping GitHub public-facing while Linear remains the internal execution layer. Use when the user wants backlog control, PR triage, or…
原文の言語: 英語
Use to know about Planning Artifacts used in project management.
原文の言語: 英語
Analyze raw prompts, identify intent and gaps, match ECC components (skills/commands/agents/hooks), and output a ready-to-paste optimized prompt. Advisory role only — never executes the task itself. TRIGGER when: user says "optimize prompt", "improve my…
原文の言語: 英語
Pythonic idioms, PEP 8 standards, type hints, and best practices for building robust, efficient, and maintainable Python applications.
原文の言語: 英語
Python testing strategies using pytest, TDD methodology, fixtures, mocking, parametrization, and coverage requirements.
原文の言語: 英語
PyTorch deep learning patterns and best practices for building robust, efficient, and reproducible training pipelines, model architectures, and data loading.
原文の言語: 英語
Conducts structured Q&A discussions with users, handling multiple choice, single choice, and open-ended questions one at a time - tracks progress, validates answers, and provides summary reports for complete discussions
原文の言語: 英語
Deploy an app to Railway — build/start command detection, service config, environment variables, private networking, databases, and health checks. Use when deploying any web app or service to Railway.
原文の言語: 英語
Use when performing ralph wiggum style long-running development loops with pacing control.
原文の言語: 英語
React and Next.js performance optimization guidelines. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching,…
原文の言語: 英語
React Router v7 framework mode (Remix) playbook for chat/realtime/collaborative apps — loaders/actions, nested routes, streaming, optimistic UI, and why not Next. Use when the app class is chat/realtime.
原文の言語: 英語
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation
原文の言語: 英語
Decision framework for choosing between regex and LLM when parsing structured text — start with regex, add LLM only for low-confidence edge cases.
原文の言語: 英語
Cross-stack source code asset audit — classifies every file, detects embedded third-party libraries, and delivers actionable four-level verdicts per module with interactive HTML reports.
原文の言語: 英語
Use when completing tasks, implementing major features, or before merging to verify work meets requirements - dispatches superpowers:code-reviewer subagent to review implementation against plan or requirements before proceeding
原文の言語: 英語
Evidence-first current-state research workflow for ECC. Use when the user wants fresh facts, comparisons, enrichment, or a recommendation built from current public evidence and any supplied local context.
原文の言語: 英語
Use when errors occur deep in execution and you need to trace back to find the original trigger - systematically traces bugs backward through call stack, adding instrumentation when needed, to identify source of invalid data or incorrect behavior
原文の言語: 英語
Scan skills to extract cross-cutting principles and distill them into rules — append, revise, or create new rule files
原文の言語: 英語
Idiomatic Rust patterns, ownership, error handling, traits, concurrency, and best practices for building safe, performant applications.
原文の言語: 英語
Rust testing patterns including unit tests, integration tests, async testing, property-based testing, mocking, and coverage. Follows TDD methodology.
原文の言語: 英語
Use this skill to prevent destructive operations when working on production systems or running agents autonomously.
原文の言語: 英語
Multi-agent adversarial verification with convergence loop. Two independent review agents must both pass before output ships.
原文の言語: 英語
Research-before-coding workflow. Search for existing tools, libraries, and patterns before writing custom code. Invokes the researcher agent.
原文の言語: 英語
Audits security and supply-chain risk between two git refs for pre-release security review.
原文の言語: 英語
Hunt for exploitable, bounty-worthy security issues in repositories. Focuses on remotely reachable vulnerabilities that qualify for real reports instead of noisy local-only findings.
原文の言語: 英語
Use this skill when adding authentication, handling user input, working with secrets, creating API endpoints, or implementing payment/sensitive features. Provides comprehensive security checklist and patterns.
原文の言語: 英語
Scan your Claude Code configuration (.claude/ directory) for security vulnerabilities, misconfigurations, and injection risks using AgentShield. Checks CLAUDE.md, settings.json, MCP servers, hooks, and agent definitions.
原文の言語: 英語
Analyze and fix production errors from Sentry crash reports. Use when investigating AppHang, ANR, crashes, or production errors. Includes complete workflow from JSON analysis to bug fix implementation with evidence-based methodology. Triggers on sentry,…
原文の言語: 英語
Sentry error tracking and monitoring. Use when configuring Sentry, filtering errors, analyzing crash reports, or debugging production issues. Covers platform-specific setup (desktop/mobile/web/extension) and error filtering strategies.
原文の言語: 英語
Audit, plan, and implement SEO improvements across technical SEO, on-page optimization, structured data, Core Web Vitals, and content strategy. Use when the user wants better search visibility, SEO remediation, schema markup, sitemap/robots work, or keyword…
原文の言語: 英語
Expert SEO strategist specializing in technical SEO, content optimization, and search engine rankings. Masters both on-page and off-page optimization, structured data implementation, and performance metrics to drive organic traffic and improve search…
原文の言語: 英語
Use when auditing Claude skills and commands for quality. Supports Quick Scan (changed skills only) and Full Stocktake modes with sequential subagent batch evaluation.
原文の言語: 英語
Master smart contract security best practices to prevent common vulnerabilities and implement secure Solidity patterns. Use when writing smart contracts, auditing existing contracts, or implementing security measures for blockchain applications.
原文の言語: 英語
State management patterns using Jotai or similar atomic state libraries. Use when working with atoms, global state, feature state, or context atoms. Triggers on jotai, atom, state, globalAtom, contextAtom, store, persistence, settings, zustand.
原文の言語: 英語
Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.
原文の言語: 英語