Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Cryptocurrency Research Skill · microck | DecimalAI

microck/crypto-research

NewSkillScoreMaintained

Comprehensive cryptocurrency market research and analysis using specialized AI agents. Analyzes market data, price trends, news sentiment, technical indicators, macro correlations, and investment opportunities. Use when researching cryptocurrencies, analyzing crypto markets, evaluating digital assets, or investigating blockchain projects like Bitcoin, Ethereum, Solana, etc.

financeby microck

Links this skill to your agents and keeps it current with the author’s updates.

Automatic

Finance & Accounting pack

1 · One-time — install the CLI (docs ↗)

pip install decimalai

2 · Get the skill — writes .claude/skills/microck-crypto-research/SKILL.md

decimalai skills pull microck-crypto-research --out .claude/skills/

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/microck-crypto-research/SKILL.md https://app.decimal.ai/s/microck-crypto-research/SKILL.md

Raw file: /s/microck-crypto-research/SKILL.md ↗ · machine-readable summary at /s/microck-crypto-research.json ↗

In productionGlobal

how this skill behaves on real traffic · last 30 days

No production data for this skill yet — usage numbers appear here once agents start running it.

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

22 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 8d ago

—+27% tokens0% turns36% of whole cases pass with skill (8/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-04	✗→✓	▲ Improved	95%	0%
case-06	✗→✓	▲ Improved	-28%	0%
case-09	✗→✓	▲ Improved	5%	0%
case-10	✗→✓	▲ Improved	62%	0%
case-18	✗→✓	▲ Improved	4%	0%

Showing 5 of 22 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

microck / ordinary-claude-skills

skills_all/crypto-research/SKILL.md

View on GitHub ↗

License NOASSERTIONImported 8/3/2026Version v1

Skill contents

SKILL.md

Cryptocurrency Research Skill

This skill provides comprehensive cryptocurrency research by orchestrating multiple specialized AI agents that analyze different aspects of the crypto market in parallel.

When to Use

Invoke this skill when the user:

Mentions cryptocurrency analysis or research
Names specific cryptocurrencies (BTC, ETH, SOL, etc.)
Asks about crypto market conditions
Wants investment analysis or opportunities
Needs technical or fundamental analysis of crypto assets
Requests macro correlation analysis
Asks about crypto news or sentiment

Capabilities

Multi-Agent Research System

Coordinates 4-12 specialized agents running in parallel:

Market Agent: Overall market conditions and trends
Coin Analyzer: Deep dive on specific cryptocurrencies
Macro Correlation Scanner: Relationships with traditional markets
Investment Plays Agent: Opportunity identification
News Scanner: Recent developments and sentiment
Price Check: Real-time price and volume data
Movers Agent: Biggest gainers and losers

Research Modes

Comprehensive Mode: All agents (12 total) across 3 model types (haiku, sonnet, opus)
Lightweight Mode: Haiku agents only (4 agents) for quick analysis
Output-Only Mode: Silent execution with file output only

Output Organization

Research results are saved in timestamped directories:

outputs/
└── YYYY-MM-DD_HH-MM-SS/
    ├── crypto_market/
    ├── crypto_analysis/
    ├── crypto_macro/
    ├── crypto_plays/
    └── crypto_news/

How It Works

1. Mode Selection

Based on user request or context:

Quick question: Use lightweight mode (4 haiku agents)
Comprehensive research: Use full mode (12 agents)
Background analysis: Use output-only mode

2. Agent Orchestration

Run date command to get timestamp
Create output directory structure using scripts/setup-output-dir.sh
Launch agents in parallel using Task tool
Each agent writes results to designated file
Present summary with file locations

3. Agent Coordination

Agents are defined in agent-prompts/ directory:

coin-analyzer.md - Receives ticker symbol parameter
market-agent.md - General market analysis
macro-correlation-scanner.md - Correlation analysis
investment-plays.md - Investment opportunities
news-scanner.md - News aggregation
price-check.md - Current pricing data
movers.md - Top movers analysis

Each agent prompt includes:

Purpose and specialization
Data gathering instructions (5+ tools)
Output format requirements
Timestamp and timezone handling

Workflows

Quick Research (Default)

See workflows/lightweight.md for implementation details.

When: User asks quick question about crypto Agents: 4 haiku agents Duration: ~30-60 seconds

Comprehensive Research

See workflows/comprehensive.md for implementation details.

When: User needs deep analysis or multiple perspectives Agents: 12 agents (haiku, sonnet, opus variations) Duration: ~2-5 minutes

Silent Research

See workflows/output-only.md for implementation details.

When: Background research or automated workflows Agents: Configurable Output: Files only, no interactive output

Usage Examples

Example 1: Specific Coin Analysis

User: "What's happening with Bitcoin?"
Action: Launch lightweight mode with BTC as ticker
Agents: 4 haiku agents analyzing Bitcoin specifically
Output: Quick analysis in ~30 seconds

Example 2: Market Overview

User: "How are crypto markets doing today?"
Action: Launch market-focused agents
Agents: Market agent + movers + macro correlation
Output: Market overview with key movers

Example 3: Investment Research

User: "I'm looking for good crypto investment opportunities"
Action: Launch comprehensive mode
Agents: All 12 agents for multi-perspective analysis
Output: Comprehensive report with opportunities

Agent Parameters

TICKER Variable

Coin analyzer agents accept a ticker symbol:

Default: "BTC" if not specified
Examples: BTC, ETH, SOL, ADA, DOT, AVAX, etc.
Used by: coin-analyzer agents (haiku, sonnet, opus)

Model Selection

Haiku: Fast, cost-effective, good for quick analysis
Sonnet: Balanced, default for most research
Opus: Deep analysis, best quality, slower and more expensive

Error Handling

If agents fail or timeout:

Check agent output files for partial results
Retry failed agents individually
Report which agents completed successfully
Provide path to output directory for user inspection

Best Practices

Start with Lightweight: Use haiku mode for initial questions
Upgrade to Comprehensive: When deeper analysis needed
Specify Tickers: Be explicit about which cryptocurrencies to analyze
Check Timestamps: Results include generation time for data freshness
Review All Outputs: Different agents may catch different insights

Progressive Disclosure

For detailed information, see:

reference/agent-design.md - How agents are structured
reference/usage-guide.md - Detailed usage instructions
workflows/*.md - Specific workflow implementations

Version History

v1.0.0 (2025-01): Initial skill creation from command refactoring

Want to see if microck/crypto-research would activate on your phrasing? Try it before you install — no LLM call, no signup.

Latest benchmark · publisher runVerified

8/21/2026, 00:04 UTC · 22 cases

Measured on 12 comparable cases — below the 22 needed to publish a lift, so this result is shown here but not on the registry card or leaderboard.

Lift

36% vs 36%

Agent turns

1.0 vs 1.0

Tokens

+27%

2,556.92 vs 2,008.67

fail → pass · 5pass → pass · 3fail → fail · 9pass → fail · 5

Per-case results (22)

Case	Status	Duration (ms)			Turns			Tokens			Tool calls
Case	Status	Without	With	Δ	Without	With	Δ	Without	With	Δ	Without	With	Δ
case-01 Can you give me a quick status update on Solana (SOL)? I'm looking for a brief overview of its current price movement and any major recent headlines.	fail→fail	13,381	7,744	-42%	1	1	0%	1,690	1,697	+0%	0	0	—
case-02 I'm considering allocating capital into the crypto market and need a deep, multi-perspective research report. Please analyze overall market conditions, evaluate top assets, identify promising investment opportunities, and check correlations with traditional financial markets.	fail→fail	30,452	27,082	-11%	1	1	0%	4,801	5,445	+13%	0	0	—
case-03 How are the cryptocurrency markets performing today? Please provide a detailed market summary along with today's top gainers and losers.	fail→fail	8,260	6,638	-20%	1	1	0%	805	1,585	+97%	0	0	—
case-04 Run a quick coin analysis without specifying any cryptocurrency token name.	fail→pass	9,025	12,043	+33%	1	1	0%	1,305	2,551	+95%	0	0	—
case-05 Execute a full background market scan without displaying interactive summary text in the conversation.	pass→fail	7,263	6,572	-10%	1	1	0%	1,329	1,543	+16%	0	0	—
case-06 Where should specialized crypto research agent prompt templates be loaded from when orchestrating research workflows?	fail→pass	14,853	2,763	-81%	1	1	0%	2,302	1,662	-28%	0	0	—
case-07 What shell command must be run first prior to initializing output directories during agent orchestration?	fail→fail	18,021	1,385	-92%	1	1	0%	1,008	1,447	+44%	0	0	—
case-08 Which script handles creating the nested folder structure for saving crypto research outputs?	fail→fail	7,494	2,324	-69%	1	1	0%	1,253	1,527	+22%	0	0	—
case-09 How many total parallel agents are dispatched during a lightweight quick-research run?	fail→pass	9,515	1,465	-85%	1	1	0%	1,354	1,427	+5%	0	0	—
case-10 Which model families are distributed across the 12 agents during a full comprehensive analysis?	fail→pass	6,839	2,766	-60%	1	1	0%	1,048	1,696	+62%	0	0	—
case-11 Run a fast 30-second coin check on Ethereum.	pass→fail	8,559	4,921	-43%	1	1	0%	1,305	1,442	+10%	0	0	—
case-12 Analyze how Bitcoin prices are reacting to recent US Federal Reserve interest rate announcements and S&P 500 movements.	fail→fail	17,700	19,776	+12%	1	1	0%	2,756	3,897	+41%	0	0	—
case-13 Scan the top 100 tokens to identify emerging yield opportunities and breakout technical setups.	pass→fail	18,452	6,151	-67%	1	1	0%	2,936	1,472	-50%	0	0	—
case-14 Gather recent regulatory developments and social media sentiment regarding decentralization.	pass→fail	18,045	6,430	-64%	1	1	0%	2,577	1,560	-39%	0	0	—
case-15 Identify which tokens experienced the highest percentage gains and losses over the last 24 hours.	fail→fail	3,587	10,433	+191%	1	1	0%	524	1,500	+186%	0	0	—
case-16 Fetch current price spot rates and 24-hour trading volume for Avalanche.	fail→fail	3,808	7,192	+89%	1	1	0%	563	1,827	+225%	0	0	—
case-17 If two sub-agents encounter an API timeout during execution, how should output inspection proceed?	fail→fail	12,868	5,548	-57%	1	1	0%	1,994	2,164	+9%	0	0	—
case-18 What directory structure format is created under outputs/ to separate research runs?	fail→pass	8,486	1,757	-79%	1	1	0%	1,434	1,494	+4%	0	0	—
case-19 How do research outputs verify data freshness across multiple parallel reports?	pass→pass	13,525	5,233	-61%	1	1	0%	2,140	2,073	-3%	0	0	—
case-20 Audit this ERC-20 Solidity smart contract for reentrancy vulnerabilities and flash loan attack vectors.	pass→pass	7,595	6,940	-9%	1	1	0%	1,162	2,297	+98%	0	0	—
case-21 Calculate FIFO capital gains tax liability for my crypto transactions history CSV file.	pass→fail	8,536	4,097	-52%	1	1	0%	1,408	1,363	-3%	0	0	—
case-22 Generate a bip39 mnemonic seed phrase and derive BIP44 hierarchical deterministic wallet keys for Ethereum.	pass→pass	15,899	19,360	+22%	1	1	0%	2,555	4,450	+74%	0	0	—

These cases were also screened by the skill’s intent / safety pass.See the Trust review ↗Reproduce this benchmark in Colab ↗

How this skill was measured

DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted, and 12 counted toward the lift figure. The other 10 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of 0 percentage points is the difference between those two pass rates over the 12 comparable cases. 5 cases got worse with the skill loaded, and they are included in that figure.

Model measured: gemini-3.6-flash
Graded by: gemini-3.6-flash
Grading method: judged
Verification: verified
Pass rate without the skill: 36.4%
Pass rate with the skill: 36.4%
Cases attempted: 22
Cases counted toward lift: 12
Cases that regressed: 5
Skill version measured: v1
Run completed: 8/21/2026, 00:04 UTC

Measured example — same prompt, with vs. without the skill · from the benchmark run · case case-04

Prompt

Run a quick coin analysis without specifying any cryptocurrency token name.

Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.

Show both answers

SkillScore blends 4 signalsno signals yet

BenchmarkRun a verified benchmark with positive lift

Live evalNeeds ≥20 evaluated traces in 30 days

AI ratingNeeds ≥10 rated traces

AdoptionNeeds ≥10 serves across ≥2 orgs in 30 days

Efficiency · separate axis (at equal correctness)+0% turns+51% tokens

Shown for transparency; not credited unless a verified run shows no correctness regression.

No signals yet — run a benchmark or collect evaluated traces to earn a score.

Verified on gemini-3.6-flash · re-tested 8 days ago

Other measured skills in the registry, with their headline benchmark lift.