本文へ移動
cccskills
無料GitHub で公開

price-action

Price action market structure analysis, trend vs trading range classification, Always In directional framework, buying/selling pressure analysis, market cycle phase identification, the price action methodology

インストール方法を見る

含まれるファイル(4)

  • SKILL.md9.4 KB
  • references/knowledge-frameworks.md2.8 KB
  • references/market-structure.md9.5 KB
  • references/modes.md718 B

SKILL.md(原文)

インストールする前に、エージェントに与えられる指示の中身を確認できます。

Methodology inspired by publicly taught price action trading frameworks; all text is an original paraphrase.

Defaults

ParameterDefault ValueRationale
trend_confirmation_bars3Minimum consecutive bars for trend confirmation
trading_range_threshold20 barsPullback > 20 bars becomes a full Trading Range
reversal_failure_rate80%In a trending market, ~80% of reversal attempts fail and become flags
inertia_rule60-4060% probability trend continues, 40% probability reversal

Preflight

Run canonical pre-flight per contracts/preflight.md. Include the X-Agentii-Trace header on every tool call per contracts/x-agentii-trace-header.md — carry the _run_id from your first tool result and name yourself (and your parent, if you were spawned).

Data Source Priority

  1. Price action framework — references/market-structure.md (bundled market structure methodology)
  2. Real-time price data — get_realtime_quote for OHLCV and VIX context
  3. Technical setups — search_technical_setups for matching pattern setups

Methodology

Retrieval Scope

structured_only

Retrieval Strategy

This skill follows Branch (d) Simple Lookup from contracts/retrieval.md: the methodology framework is bundled in references/market-structure.md. Real-time price data supplements via get_realtime_quote. Matched technical setups via search_technical_setups(market_condition=...). No unstructured document retrieval.

Temporal Scope

See frontmatter temporal_scope block.

Tool Allowlist

See frontmatter allowed_tools.

Protocol

This skill implements the price action trading framework: market structure analysis using price action alone — no indicators except a 20-bar EMA. The core thesis: every market is always in one of two states — Trend or Trading Range. If uncertain, it is a Trading Range. Detailed methodology, definitions, and decision rules are in references/market-structure.md.

Step 1 — Macro Context (Mode C — degrade-gracefully)

Assess the broader market environment before analyzing individual setups.

  1. Query get_realtime_quote for a broad market proxy (SPY/SPX) to assess VIX levels.
  2. Determine the macro regime from upstream analysis (expansion/contraction/stagflation/recovery).
  3. VIX assessment: elevated (> 25) → tighten position sizing, favor defined-risk setups. Low (< 15) → standard sizing.

Step 2 — Market Structure Identification

Answer the most important question in price action: Trend or Trading Range?

  1. Cycle Phase Identification:
    • Trend = Series of higher highs/lows (bull) or lower highs/lows (bear). Contains breakout→channel sub-phases.
    • Trading Range = Sideways movement. ≥ 20 bars = full TR. < 20 bars within a trend = Pullback.
    • Reversal Signal = Trading Range at a trend extreme that transitions into opposite trend.
  2. Trend Strength Classification:
    • Strong Trend (Breakout/Spike): Big bodies, small tails, consecutive bars with little overlap.
    • Weak Trend (Channel): Bars with visible tails and overlap, contained between two parallel lines.
  3. Pullback vs Trading Range Rule:
    • Pullback = < 20 bars pause; breakout likely in trend direction.
    • Trading Range = ≥ 20 bars; direction lost; breakout equally likely either way.
    • Fractal check: what appears as a pullback on this timeframe may be a trading range on a lower timeframe.

Step 3 — Directional Bias

Determine the directional bias using the Always In framework.

  1. Ask: "If forced to enter the market right now, long or short?" Your answer = Always In direction.
  2. If unclear: the market is in a Trading Range. Confusion = hallmark of TR.
  3. Directional bias rules:
    • Always In Long → only consider long setups; ignore short signals even if they look strong.
    • Always In Short → only consider short setups; ignore long signals.
    • No clear Always In → Trading Range mode: Buy Low, Sell High, scalp only.

Step 4 — Pressure Analysis

Identify which side (bulls/bears) is applying dominant pressure.

  1. Bar-by-bar assessment:
    • Close near high = bulls dominated through bar's life.
    • Close near low = bears dominated.
    • Long tail above = bears aggressively sold higher prices → failed breakout upward.
    • Long tail below = bulls aggressively bought lower prices → failed breakout downward.
  2. Every tail is a failed breakout — it was once a strong trend body that got reversed. Tails signal the failure of one side.
  3. Context override: A small body in a strong trend behaves as a trend bar. A big body in a sideways market behaves as a trading range bar. Context always overrides individual bar appearance.

Step 5 — Momentum Assessment

Assess momentum using the 20-60 day framework: Technical Analysis (patterns/formations) provides the big picture over weeks to months. Price Action (momentum) provides the near-term directional signal over days to weeks. Both must align for a trade to have favorable timing.

  1. RSI (Relative Strength Index) — 14-day and 20-day:

    • Above 70 = overbought; below 30 = oversold.
    • RSI reversing from overbought = momentum fading from the upward move.
    • Avoid entering longs when RSI is overbought and falling; avoid shorts when RSI is oversold and rising.
    • Treat "overbought" and "oversold" with caution: a strong trend can stay overbought/oversold for extended periods.
  2. Moving Averages — SMA and EMA at 20, 60, 120, and 250 periods:

    • Price above rising MA = bullish momentum confirmed.
    • Price below falling MA = bearish momentum confirmed.
    • MA convergence/flattening = momentum weakening, potential transition.
  3. MACD (Moving Average Convergence Divergence):

    • Standard: (12, 26, 9). Extended: (20, 60, 10) and (20, 60, 20) for longer timeframes.
    • MACD line crossing above signal line = bullish momentum shift.
    • MACD line crossing below signal line = bearish momentum shift.
    • Divergence between MACD and price = potential reversal signal.
  4. Heikin Ashi Candles: Use for smoothing price action and identifying sustained momentum. Consecutive Heikin Ashi bars without lower shadows = strong bull momentum. Without upper shadows = strong bear momentum.

  5. Timing Assessment (Traffic-Light System):

    • Green: Market structure + momentum + Always In direction all aligned → favorable entry timing.
    • Amber: Partial alignment, some conflicting signals → caution; reduce position size or wait.
    • Red: Conflicting signals across structure/momentum/direction → do not enter; wait for clearer conditions.

Step 6 — Setup Context Handoff

Produce the market structure output to be consumed by downstream skills.

  1. Output classification:
    • market_condition: trending_up / trending_down / ranging
    • trend_strength: strong / weak / none
    • always_in_direction: long / short / neutral
    • cycle_phase: breakout / channel / trading_range / reversal
  2. Handoff to chart-patterns: The context above determines which patterns are valid. In a strong bull trend, only long patterns are valid — all short patterns are ignored regardless of how strong they appear.
  3. MCP retrieval: search_technical_setups(market_condition=<derived>) for rough matching against gold.technical_setups.

Output File

{ticker}/{YYYY-MM-DD_HHMM}_price-action_{affix}.md

Output Structure

  1. Executive Summary — Market state (Trend/TR), Always In direction, cycle phase with confidence level
  2. Market Structure Analysis — Trend strength, cycle phase, pullback vs trading range classification with specific bar counts
  3. Always In Assessment — Directional bias, rationale, confidence level
  4. Pressure Analysis — Bull/bear dominance assessment, key tail/bodie signals on recent bars
  5. Transition Signals — Early warning signals of cycle phase change (channel flattening, TR forming at extreme)
  6. Pattern Context — Valid pattern directions for downstream chart-patterns skill
  7. Coverage Gaps — Data limitations and degraded-mode annotations

Error Handling

ErrorFallback
No price data availableProceed with static market structure principles; flag degraded
search_technical_setups unreachableSkip MCP step; provide manual pattern analysis
Ambiguous market stateClassify as Trading Range; note ambiguity

Memory Load

See contracts/memory-load.md.

Snapshot

See contracts/snapshot-synthesis.md.

Final Summary (TUI)

Include ### Key Citations block with 0-10 clickable /v/ URLs.

References

  • references/market-structure.md
  • contracts/citation-and-memory.md
  • contracts/output-frontmatter-schema.md
  • contracts/memory-load.md
  • contracts/snapshot-synthesis.md
  • contracts/preflight.md
  • contracts/retrieval.md

レビュー

まだレビューはありません。使ってみた感想をお寄せください。

同じリポジトリのスキル

概要と使いどころ

3-statement financial model, integrated IS BS CF, income statement projection, balance sheet forecast, cash flow statement, cross-statement balancing, financial model build, operating model, three statement model, integrated financial statements

日本語の概要は準備中です。原文の説明を表示しています。

agentii-ai/agentii-investment-intelligence2072026年9月29日 更新

Institutional-grade equity research skills for AI agents. 80 Claude-type skills across 14 verticals (equity-research-core, models-and-pitches, bio-pharm, scenarios, quantitative-analysis, idea-generation, options-derivatives, business-intelligence, industry-analysis, macro-strategy, portfolio-strategy, technical-analysis, risk-and-psychology, trading-as-business) powered by agentii.ai's agent-use-ready SEC filing data plane — SEC filings and 15K+ earnings call transcripts, 15.99M XBRL facts, and company profiles for 1,146+ US-public-equity tickers. Features the three-layer retrieval protocol (Document Discovery → Page Map → Deep Read, with deep-outline escalation) — measured, not asserted: 97.5% saved against a sequential read, and the page map itself is 10.0% of one (spec 062 T030, 2026-09-23) — server-side parallel multi-period search via search_cross_period, a full Excel/PPT generation pipeline with 3-tier office backend support, and the spec-046 governance layer (constitution, thesis and single-skill modes, mechanical gates, and a template-owned disclaimer on generated reports).

日本語の概要は準備中です。原文の説明を表示しています。

agentii-ai/agentii-investment-intelligence2072026年9月29日 更新

audit-xls

無料

Audit spreadsheet, formula error detection, hardcoded cell finder, cross-sheet reference audit, workbook auditor, Excel model audit, financial model QA, spreadsheet review, cell dependency trace, formula integrity check

日本語の概要は準備中です。原文の説明を表示しています。

agentii-ai/agentii-investment-intelligence2072026年9月29日 更新

Business model classification, business model analysis, structural analysis of how a company makes money, product offering decomposition, distribution channel analysis, customer segment analysis, revenue model identification, market sizing TAM SAM SOM, competitive positioning, business unit performance, management team & leadership analysis, what does the company sell, how does the company go to market, business model type platform service product, channel mix direct vs indirect, revenue concentration risk, CEO CFO executive backgrounds and changes

日本語の概要は準備中です。原文の説明を表示しています。

agentii-ai/agentii-investment-intelligence2072026年9月29日 更新

challenge

無料

Adversarial verification of research theses — cross-run/cross-thesis contradiction via the entity index, pre-mortem (Klarman/Kahneman: assume the loss already happened, reverse the path), inversion (Munger: invert, always invert), and wrong_if falsifiability review. ≈50-finding cap sorted by severity; content-derived finding IDs; incremental scoping with three backstops; lifecycle hooks at pillar-complete / thesis-complete / pre-reduction.

日本語の概要は準備中です。原文の説明を表示しています。

agentii-ai/agentii-investment-intelligence2072026年9月29日 更新

Chart pattern recognition, price action patterns, candlestick signal bars, pullback bar counting H1/H2/H3/H4, trend channels, micro channels, trading ranges, breakouts, major trend reversals 5-step sequence, wedges, double tops and bottoms, triangles, head and shoulders, climaxes, measured moves, support and resistance

日本語の概要は準備中です。原文の説明を表示しています。

agentii-ai/agentii-investment-intelligence2072026年9月29日 更新

agentii-ai のスキルをすべて見る

このスキルの問題を報告する