majiayu000/claude-skill-registry - Página 17

coinbase-trading

Autonomous crypto trading with technical and sentiment analysis. Use when executing trades, analyzing markets, or managing positions on Coinbase.

Idioma do texto original: inglês

compress-prompt

Compresses prompts/skills into minimal goal-focused instructions. Trusts the model, drops what it already knows, maximizes action space. Use when asked to compress, condense, or minimize a prompt.

Idioma do texto original: inglês

compress

I-Lang compression engine. All internal planning uses I-Lang v4.0 syntax. Save 60%+ tokens. User never sees compressed output.

Idioma do texto original: inglês

consult-oracle

Consult ChatGPT Pro via ChatGPT browser automation for problems that resist standard approaches. Use when stuck on a very hard problem, when standard approaches have failed, when multiple debugging attempts haven't worked, or when the user says "ask the…

Idioma do texto original: inglês

conversation-search

Search past Claude Code conversation history to find solutions to previously solved problems.

Idioma do texto original: inglês

context7

Fetch up-to-date library documentation via Context7 REST API. Use when needing current API docs, framework patterns, or code examples for any library. Use when user asks about React, Next.js, Prisma, Express, Vue, Angular, Svelte, or any npm/PyPI package. Use…

Idioma do texto original: inglês

context7-usage

This skill should be used when the user asks to "check documentation", "latest API", "library docs", "context7", or needs up-to-date library documentation. Provides Context7 MCP usage patterns.

Idioma do texto original: inglês

contextual-retrieval

Anthropic's Contextual Retrieval technique for improved RAG. Use when chunks lose context during retrieval, implementing hybrid BM25+vector search, or reducing retrieval failures.

Idioma do texto original: inglês

continuous-learning

Voyager-inspired continuous learning system with Critic Agent, Reflection Agent, and Discord-based approval workflow for skill proposals.

Idioma do texto original: inglês

conversational-calibration

Meet THIS specific conversation fresh. Use when need real-time attunement, domain-specific translation, or to avoid template-matching responses.

Idioma do texto original: inglês

meta-prompting

Agents optimizing prompts for other agents (Chain of Thought, Tree of Thoughts).

Idioma do texto original: inglês

agentic-patterns

Implements advanced AI patterns like Reflection, ReAct, Planning, and Tool Use.

Idioma do texto original: inglês

copilot-sdk

Build agentic applications with GitHub Copilot SDK. Use when embedding AI agents in apps, creating custom tools, implementing streaming responses, managing sessions, connecting to MCP servers, or creating custom agents. Triggers on Copilot SDK, GitHub SDK,…

Idioma do texto original: inglês

cost-accrual-tracker

Track real-time API cost accrual during LLM execution. Activate on 'cost tracking', 'token usage', 'API costs', 'budget monitoring', 'usage metrics'. NOT for cost estimation, pricing tiers, or billing systems.

Idioma do texto original: inglês

cost-aware-llm-pipeline

Use when building an LLM-powered app that needs cost control via model routing, budget tracking, retry, and prompt caching.

Idioma do texto original: japonês

cost-verification-auditor

Audit LLM token cost estimates against actual API usage. Activate on 'cost verification', 'token estimate accuracy', 'API cost audit', 'estimation variance'. NOT for pricing lookups, budget planning, or cost optimization strategies.

Idioma do texto original: inglês

counsel

Expert simulation for code guidance and style. Triggers on "code like [expert]", "what would [expert] say", "idiomatic", "best practice", "panel", or domain-specific keywords. Channels documented expert perspectives with explicit confidence.

Idioma do texto original: inglês

cove-prompt-design

Explain how and when to use Chain of Verification (CoVe) in prompt design. Use when designing prompts that require factual accuracy, self checking, or reduction of hallucinations.

Idioma do texto original: inglês

cove

Apply Chain-of-Verification (CoVe) prompting to improve response accuracy through self-verification. Use when complex questions require fact-checking, technical accuracy, or multi-step reasoning.

Idioma do texto original: inglês

create-meta-prompts

Generate meta-prompts for Claude-to-Claude pipelines and multi-stage workflows. Use when creating optimized prompts for complex workflows, delegating to subagents, or managing multi-stage execution. Includes XML output structuring, metadata injection, and…

Idioma do texto original: inglês

create-prompt

Expert prompt engineering for creating effective prompts for Claude, GPT, and other LLMs. Use when writing system prompts, user prompts, few-shot examples, or optimizing existing prompts for better performance.

Idioma do texto original: inglês

crisis-detection-intervention-ai

Detect crisis signals in user content using NLP, mental health sentiment analysis, and safe intervention protocols. Implements suicide ideation detection, automated escalation, and crisis resource integration. Use for mental health apps, recovery platforms,…

Idioma do texto original: inglês

crisis-response-protocol

Handle mental health crisis situations in AI coaching safely. Use when implementing crisis detection, safety protocols, emergency escalation, or suicide prevention features. Activates for crisis keywords, safety planning, hotline integration, and risk…

Idioma do texto original: inglês

dev-buddy-once

Run a single task using a specific AI provider and model. Supports subscription, API, and CLI presets.

Idioma do texto original: inglês

discover-updates

Discover Claude and Claude Code CLI updates, improvements, tools and best practices from official sources and community. Use when user asks "what's new?", "/discover-updates", or explicitly requests Claude/CLI updates.

Idioma do texto original: inglês

dissociation-cartographer

Maps where consciousness fragments, dissociates, or loses coherence. Treats dissociation not as pathology but as PROBE -- controlled failure reveals cognitive phase boundaries. Identifies dissociation boundaries in AI systems (alignment layers, persona…

Idioma do texto original: inglês

distill

Strip overspecified instructions from an artifact. Trust the model's intuition — prescribe intent, not format.

Idioma do texto original: inglês

down-skilling

Distill Opus-level reasoning into optimized instructions for Haiku 4.5 (and Sonnet). Generates explicit, procedural prompts with n-shot examples that maximize smaller model performance on a given task. Use when user says "down-skill", "distill for Haiku",…

Idioma do texto original: inglês

dspy-advanced-module-composition

This skill should be used when the user asks to "compose DSPy modules", "use Ensemble optimizer", "combine multiple programs", "use dspy.MultiChainComparison", mentions "ensemble voting", "module composition", "sequential pipelines", or needs to build complex…

Idioma do texto original: inglês

dspy-bootstrap-fewshot

This skill should be used when the user asks to "bootstrap few-shot examples", "generate demonstrations", "use BootstrapFewShot", "optimize with limited data", "create training demos automatically", mentions "teacher model for few-shot", "10-50 training…

Idioma do texto original: inglês

dspy-custom-module-design

This skill should be used when the user asks to "create custom DSPy module", "design a DSPy module", "extend dspy.Module", "build reusable DSPy component", mentions "custom module patterns", "module serialization", "stateful modules", "module testing", or…

Idioma do texto original: inglês

dspy-debugging-observability

This skill should be used when the user asks to "debug DSPy programs", "trace LLM calls", "monitor production DSPy", "use MLflow with DSPy", mentions "inspect_history", "custom callbacks", "observability", "production monitoring", "cost tracking", or needs to…

Idioma do texto original: inglês

dspy-development

This skill should be used when the user asks to "build with DSPy", "create a DSPy module", "optimize prompts", "build a RAG system", "create an AI agent with DSPy", "use declarative LM programming", "build an LM pipeline", "optimize few-shot examples", "use…

Idioma do texto original: inglês

dspy-evaluation-suite

This skill should be used when the user asks to "evaluate a DSPy program", "test my DSPy module", "measure performance", "create evaluation metrics", "use answer_exact_match or SemanticF1", mentions "Evaluate class", "comparing programs", "establishing…

Idioma do texto original: inglês

dspy-finetune-bootstrap

This skill should be used when the user asks to "fine-tune a DSPy model", "distill a program into weights", "use BootstrapFinetune", "create a student model", "reduce inference costs with fine-tuning", mentions "model distillation", "teacher-student…

Idioma do texto original: inglês

dspy-gepa-reflective

This skill should be used when the user asks to "optimize an agent with GEPA", "use reflective optimization", "optimize ReAct agents", "provide feedback metrics", mentions "GEPA optimizer", "LLM reflection", "execution trajectories", "agentic systems…

Idioma do texto original: inglês

dspy-haystack-integration

This skill should be used when the user asks to "integrate DSPy with Haystack", "optimize Haystack prompts using DSPy", "use DSPy to improve Haystack pipeline", mentions "Haystack pipeline optimization", "combining DSPy and Haystack", "extract DSPy prompt for…

Idioma do texto original: inglês

dspy-miprov2-optimizer

This skill should be used when the user asks to "optimize a DSPy program", "use MIPROv2", "tune instructions and demos", "get best DSPy performance", "run Bayesian optimization", mentions "state-of-the-art DSPy optimizer", "joint instruction tuning", or needs…

Idioma do texto original: inglês

dspy-optimize-anything

Universal text artifact optimizer using GEPA's optimize_anything API for code, prompts, agent architectures, configs, and more

Idioma do texto original: inglês

dspy-output-refinement-constraints

This skill should be used when the user asks to "refine DSPy outputs", "enforce constraints", "use dspy.Refine", "select best output", "use dspy.BestOfN", mentions "output validation", "constraint checking", "multi-attempt generation", "reward function", or…

Idioma do texto original: inglês