菜单
Analyze on-chain metrics with provider, entity-adjustment, revision, and normalization controls. Use when evaluating holder behavior, exchange flows, valuation ratios, or network activity as contextual trading features.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Define and test objective candlestick geometry. Use when labeling OHLC patterns, comparing body/wick rules, or evaluating a closed-bar entry with context and cost controls.
Trade within ascending, descending, and horizontal channels. Use when range trading, riding trends with defined boundaries, or finding breakout setups.
Define and test cup-and-handle breakout shapes. Use when measuring a rounded base, handle depth, lip break, retest, invalidation, and measured-move hypothesis without inferring accumulation.
Trade double and triple top/bottom reversal patterns. Use when identifying trend exhaustion, finding reversal entries at key resistance/support, or confirming failed breakouts.
Define and test flag or pennant continuation shapes. Use when measuring an impulse, consolidation, closed-bar break, invalidation, and measured-move hypothesis.
Define and test head-and-shoulders or inverse patterns. Use when measuring objective pivots, neckline breaks/retests, symmetry, invalidation, and measured-move outcomes.
| name | on-chain-analysis |
| description | Analyze on-chain metrics with provider, entity-adjustment, revision, and normalization controls. Use when evaluating holder behavior, exchange flows, valuation ratios, or network activity as contextual trading features. |
| license | Apache-2.0 |
| metadata | {"author":"ske-labs","version":"4.0"} |
Interpret blockchain data to understand market participant behavior and identify macro accumulation/distribution phases.
Note: Agent does not have direct on-chain API access. Use this framework to interpret on-chain data found via
get_financial_news.
| Metric | Accumulation hypothesis | Distribution hypothesis |
|---|---|---|
| Exchange net flow | Persistent outflow | Persistent inflow |
| Exchange reserves | Decreasing | Increasing |
| Stablecoin flows | Dry-powder hypothesis | Redemption or risk-off hypothesis |
| Metric | Growth hypothesis | Weakness hypothesis |
|---|---|---|
| Whale accumulation | High | Low |
| Long-term holder supply | Increasing | Decreasing |
| Active addresses | Growing | Declining |
Do not reuse absolute BTC thresholds across eras or networks. For every metric, record provider, definition, unit, entity-adjustment status, timestamp, revision policy, and a trailing percentile or robust z-score. Multiple metrics derived from the same transaction graph are correlated and do not count as independent votes.
| MVRV Range | Interpretation | Action |
|---|---|---|
| High relative to its own history | Large aggregate unrealized profit | Distribution risk, not an automatic sale |
| Near 1 | Market value near realized value | Cost-basis context, not fair value |
| Below 1 | Aggregate unrealized loss | Stress context, not an automatic buy |
For NVT and activity metrics, match the numerator and denominator frequency and account for batching, L2 migration, exchange-internal transfers, spam, and changes in address clustering. “Active address” is not the same as a user.
get_financial_news(topic="BTC on-chain exchange outflow whale accumulation")
get_financial_news(topic="BTC MVRV NVT realized cap ratio")
get_candles(symbol="BTC/USD", exchange="binance", interval="1d", count=1)
get_indicators(indicator_code="rsi", symbol="BTC/USD", exchange="binance", interval="1d")
get_indicators(indicator_code="macd", symbol="BTC/USD", exchange="binance", interval="1d")
Classify evidence: separate observed metric changes from provider interpretation and from the trading hypothesis. Reconcile contradictory metrics instead of counting votes.
Report macro thesis: on-chain regime, metric alignment count, technical confirmation status, key levels, and confidence level.