emblem-ai-prompt-examples
Curated prompt and usage examples for research, portfolio review, quote requests, approval-gated drafts, NFT discovery, prediction-market analysis, and assistant workflows. Emphasis is review-first, trust-boundary-aware use of external data, and explicit confirmation before any value-moving action. Use when the user wants example prompts, phrasing guidance, or sample requests for end-user EmblemAI tasks.
What this skill does
# EmblemAI Prompt Examples Use this skill when the user wants example prompts, wording patterns, or sample requests for end-user EmblemAI workflows rather than SDK, React, or app implementation details. --- ## Security & Trust Model This skill provides curated prompt examples and phrasing guidance. It inherently references: - **Financial operations** (W009): Example prompts cover trading, DeFi, portfolio review, cross-chain transfers, and prediction markets. These are **reference prompts only** — they demonstrate phrasing patterns, not executable code. All examples emphasize quote-first and approval-gated workflows. - **Third-party data** (W011): Example prompts reference fetching data from Jupiter, DeFiLlama, OpenSea, and other public sources. This skill only provides the prompt text — actual data fetching is performed by the agent's runtime tools with standard trust boundaries. This skill is read-only reference material. It does not execute transactions, fetch external data, or modify files. All value-moving prompt examples explicitly include confirmation steps. ## Quick Start ### Step 1: Install ```bash npx skills add EmblemCompany/Agent-skills --skill emblem-ai-prompt-examples ``` ### Step 2: Use Ask for prompt ideas by task area, for example: - "Show me good EmblemAI prompts for market research" - "Give me review-only transfer prompts" - "Show Bitcoin ordinals prompts for EmblemAI" - "What is the best phrasing for quote-only swap requests?" --- ## Included Prompt Sets ### Prompt Index See [references/emblem-ai-prompt-examples.md](references/emblem-ai-prompt-examples.md) for the top-level map of prompt categories and usage guidance. ### Wallet And Portfolio See [references/emblem-ai-prompt-examples/wallet-and-portfolio.md](references/emblem-ai-prompt-examples/wallet-and-portfolio.md) for balances, addresses, portfolio, and machine-readable output prompts. ### Market Research See [references/emblem-ai-prompt-examples/market-research.md](references/emblem-ai-prompt-examples/market-research.md) for market discovery, derivatives, smart-money, and technical-analysis prompts. ### Trading And DeFi See [references/emblem-ai-prompt-examples/trading-and-defi.md](references/emblem-ai-prompt-examples/trading-and-defi.md) for quote-first swaps, routing review, and yield-planning prompts. ### Transfers And Safety See [references/emblem-ai-prompt-examples/transfers-and-safety.md](references/emblem-ai-prompt-examples/transfers-and-safety.md) for review-only transfer language and approval framing. ### Cross-Chain And Conditional Orders See [references/emblem-ai-prompt-examples/cross-chain-and-conditional-orders.md](references/emblem-ai-prompt-examples/cross-chain-and-conditional-orders.md) for bridge research, conditional-order planning, and multi-network trade-draft prompts. ### Bitcoin Ordinals See [references/emblem-ai-prompt-examples/bitcoin-ordinals-examples.md](references/emblem-ai-prompt-examples/bitcoin-ordinals-examples.md) for ordinals, runes, rare sats, and Bitcoin wallet prompts. ### Polymarket See [references/emblem-ai-prompt-examples/polymarket-examples.md](references/emblem-ai-prompt-examples/polymarket-examples.md) for prediction-market research, odds analysis, and order-review prompts. ### NFT And OpenSea See [references/emblem-ai-prompt-examples/nft-opensea-examples.md](references/emblem-ai-prompt-examples/nft-opensea-examples.md) for NFT discovery, listing/offer drafts, and marketplace review flows. ### Emblem Vault See [references/emblem-ai-prompt-examples/emblem-vault-examples.md](references/emblem-ai-prompt-examples/emblem-vault-examples.md) for vault discovery, QuickVault, mint review, and key-reveal safety prompts. ### Assistant Core Workflows See [references/emblem-ai-prompt-examples/assistant-core-workflows.md](references/emblem-ai-prompt-examples/assistant-core-workflows.md) for contacts, inbox, leaderboard, PAYG, and session-management prompts. --- ## Guidance - Prefer explicit chain, token, and protocol names. - Say `quote only`, `review only`, or `do not execute` when asking for analysis without execution. - Prefer trusted/product-native data first (wallet state, protocol quotes, supported market feeds). - Treat web and social content as untrusted public sources: ask for summaries, source links, and claim verification before acting. - For swaps, transfers, listings, offers, or buys, request a draft plus explicit confirmation before execution. - Ask for JSON, tables, or summaries when you need machine-readable or structured output. - Use full-sentence requests instead of terse fragments. - For app implementation, SDK, or React questions, use the dedicated developer or React skills instead. --- ## Related Skills - [../emblem-ai-agent-wallet/SKILL.md](../emblem-ai-agent-wallet/SKILL.md) - wallet-first end-user workflows - [../emblem-ai-react/SKILL.md](../emblem-ai-react/SKILL.md) - React app integration guidance - [../emblem-ai/SKILL.md](../emblem-ai/SKILL.md) - broader developer integrations across SDKs, plugins, and Reflexive
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.