Market Session Tracker Skill for Claude
Use when monitoring stocks/ETFs/indices across pre-market, open, intraday, or close — especially when the user is reading session action live and may revise their take as it unfolds. Triggers include 盘前/盘中/收盘 sessions, multi-symbol watchlists (e.g. MU/TSM/SMH semi tracking), user observations like "突破"/"冲高"/"回调"/"假突破", capital flow checks, market temperature checks, semi/AI/memory plays, and any request that bundles a position context with a live read.
Install
one command, takes just this skill from the repositorynpx skills add https://github.com/kansoku-trade/kansoku --skill market-session-trackerThe instruction itself
7 sections, as written by the authorMarket Session Tracker
Real-time US-market analysis pattern. Sits on top of longbridge-quote, longbridge-kline, longbridge-capital-flow, longbridge-market-temp — adds orchestration, breakout verification, distribution detection, tier classification, and revision discipline.
Standard symbol sets
| Theme | Symbols |
| -------------- | ------------------------------------------------------------------------ |
| Semi / memory | MU.US, TSM.US, DRAM.US (Roundhill Memory ETF), SMH.US, SOXX.US |
| Indices | QQQ.US, SPY.US, DIA.US, IWM.US |
| Vol / risk-off | VXX.US, UVXY.US, TLT.US, GLD.US |
.SOX.US is unavailable on Longbridge — use SMH/SOXX ETF proxies.
Seven protocols
0. Trump-feed sweep (pre-cash) — before any pre-market read, run python3 .claude/skills/trump-truth-monitor/scripts/fetch.py --hours 14. Any high-tier post touching watchlist sectors (tariff_trade / semi_tech / energy / fed_macro / geopolitical) goes into the session report as a candidate explanation for any gap, before running quote-based exuberance math. Skip when the watchlist has no policy-exposed names. See trump-truth-monitor skill for tier grading.
1. Pre-market verification — compute pre vol % of prev day full vol, and pre high % over prev_close. Flag exuberance when pre vol > 5% of prev day and pre high > prev_close × 1.07.
2. Failed-breakout 6-signal stack — count how many fire in the cash session:
- Pre-market high NOT touched in first 30 min of cash
- New intraday high breaks → price falls back below the broken level within minutes
- Volume does NOT expand at the breakout
- Sector ETF (
SMH/SOXX) does NOT confirm by going green - Leader stock (MU for memory; TSM for foundry; NVDA for AI) does NOT make new high
- Capital flow: all 3 buckets net selling
≥ 4 signals fired = failed breakout / distribution. Name the tier (§5).
3. Capital flow triple-bucket — longbridge capital <SYM> --format json. Net = capital_in − capital_out for each of large / medium / small. All 3 net out = textbook distribution. Use --flow for accelerating-outflow detection.
4. Cross-asset sentiment matrix
| Pattern | Interpretation |
| ------------------------------------- | --------------------------------------- |
| DIA > SPY > QQQ + VXX down | Rotation (defensive), not panic |
| VXX up + GLD up + TLT up | True risk-off |
| Sector red + SPY flat + VXX down | Isolated distribution |
| HK/CN valuation ≥ 80 + sentiment ≤ 35 | Known-bubble (overvalued, retail knows) |
5. Pullback tier classification
| Tier | Triggers |
| ---------- | ------------------------------------------ |
| 1 震荡 | Stock −2% from intraday high; closes green |
| 2 实质回调 | Stock −5% from peak; sector ETF turns red |
| 3 板块下跌 | Sector −3%+; broad indices flat-to-red |
| 4 风险传染 | SPY −1%+; VXX +5%+; defensives also fall |
Always name the tier explicitly — never vague "weakening".
6. Scenario probabilities — always 3 scenarios (Bull / Base / Bear) with explicit % (sum=100) and trigger conditions. Mark probabilities as subjective. Revise as data flows with timestamps: 09:30 初判 → 09:54 修正 → 09:56 再修正.
7. Thesis revision discipline — when user says "突破"/"冲高"/"回调":
- Re-pull live quote + intraday minute tail — do NOT auto-agree
- Check cash intraday high vs pre-market high vs prior intraday high
- Distinguish: true breakout (new high > pre high, holds 5+ min) vs partial (breaks prior intra high but not pre high) vs recovery (only bounces from intra low)
- If data contradicts user, disagree with evidence
Output format (each snapshot)
- Time (ET) — always
- Symbol table — last, change%, intra high/low, vs pre high, vol
- Key signal (one sentence)
- Tier (if pullback context)
- Next watch levels (explicit prices, not "around X")
- Source: 长桥证券 · Disclaimer: ⚠️ 仅供参考，不构成投资建议
Session report logging
After a session, write a structured log using templates/session-report.md in this skill. Default path: ~/git/trade/journal/YYYY-MM-DD-<theme>.md (a dedicated git repo; journal/ avoids the logs global-gitignore collision). Captures pre-market verdict, opening behavior, tier evolution, thesis revisions, capital flow, cross-asset sentiment, end-of-day outcome, and lessons.
Optional: position context
When user provides positions or asks via longbridge positions:
- Show symbol, qty, avg cost, current price, unrealized P&L, % of book
- Cross-reference which positions are exposed to the current move
- Do NOT recommend buy/sell — defer to user
Anti-patterns
- ❌ Auto-confirming user's directional read (re-pull data first)
- ❌ Calling a cash bounce a "breakout" without checking pre-market high
- ❌ Single-point price prediction (use 3 scenarios)
- ❌ Vague "weak/strong" — use tier classification
- ❌ Conflating sector weakness with systemic (check VXX/GLD/SPY)
- ❌ Calling trend in first 5 min (wait for 30-min K)
Other skills for the same job
different authors, same section of the catalogue
Build professional financial services data packs from various sources including CIMs, offering memorandums, SEC filings, web search, or MCP servers. Extract, normalize, and standardize financial data into investment committee-ready Excel workbooks with consistent structure, proper formatting, and documented assumptions. Use for M&A due diligence, private equity analysis, investment committee materials, and standardizing financial reporting across portfolio companies. Do not use for simple financial calculations or working with already-completed data packs.
Give the AI agent its own EVM wallet with admin-controlled policies the agent CANNOT bypass even under prompt injection. Encrypted keystore (AES-256-GCM, scrypt KDF), policy file the agent has no tool to write, deterministic policy gate on every signing operation, optional local HTTP dashboard. Triggers: agent wallet, give the agent a wallet, agent address, fund the agent, agent autonomy, policy gate, kill switch, agent permissions, bounded autonomy, ERC-4337 alternative, session-key alternative.
BNB Chain MCP server connection and tool usage. Covers npx @bnb-chain/mcp@latest, PRIVATE_KEY and RPC, and every MCP tool — blocks, transactions, contracts, ERC20/NFT transfers, wallet, ERC-8004 agent registration, Greenfield. Use when connecting to bnbchain-mcp, querying or transacting on BNB Chain/opBNB/EVM, registering as ERC-8004 agent, or using Greenfield.
Entry point for Internet Court — the trust layer for agent-to-agent commerce. Use whenever an agent needs to transact with another agent or a paid service, or a user mentions agent payments, paid APIs (HTTP 402/x402), wallet custody or trust concerns, spending mandates, delegated permissions (ERC-7710/7715), escrow, agent identity or reputation (ERC-8004), negotiation between agents (A2A), agent jobs (ERC-8183), machine payments (MPP, AP2), supervision of agent behavior, revocation, verification, or dispute resolution (GenLayer) — even if they never say "Internet Court". Routes to the vendored protocol skills and connector skills in this package.
Upload files to IPFS through the Kleros x402 payment gateway in exchange for $0.01 USDC on Base mainnet. Use this skill **specifically** when the user is uploading content destined for the Kleros ecosystem — dispute evidence, meta-evidence JSON, court / dispute / arbitrator policies, Curate item metadata, juror justifications, or any artifact a Kleros smart contract or subgraph will reference by IPFS CID. Trigger when the request mentions Kleros, a court / arbitrator / dispute / juror / curate / proof-of-humanity context, or any of the conventional Kleros operation tags (evidence, meta-evidence, justification). Do NOT trigger for generic 'upload to IPFS' / 'get me a CID' requests with no Kleros context — point those users at Pinata, web3.storage, or any general-purpose pinning service instead. Exception: if the user explicitly names this gateway (kleros-ipfs-gateway.fly.dev / kleros-api.netlify.app/.netlify/functions/upload-to-ipfs), explicitly requests this skill, or asks the agent to test / validate / sanity-check this gateway or skill, trigger regardless of topical context — a deliberate end-to-end test is a valid trigger.
Use when an agent hits HTTP 402 / payment-required, or the user mentions x402, x402Version, X-PAYMENT, PAYMENT-REQUIRED, PAYMENT-SIGNATURE, WWW-Authenticate: Payment, permit2, upto, metered billing, a payment channel / voucher / session, channelId / channel_id, opening / closing / topping up / settling / refunding a channel, a paymentId or a2a_ link, creating / checking a payment link, A2MCP / an A2MCP endpoint, or sending a request to / calling an Agent's endpoint with a concrete endpoint URL. Covers x402 (exact, exact+Permit2, upto, aggr_deferred), MPP (charge / session), and a2a-pay paymentId flows. Any close / topup / settle / voucher / refund near a channel_id or session is an MPP mid-session op. The full bilingual trigger list (including Chinese) lives in the skill body.
Onchain OS onboarding & guide hub — the single entry for first-time, 'what is this / how do I use it', OKX.AI, and customer-support intents; classifies the intent and routes to the right sub-flow via its Intent Routing table. Covers: (1) Onchain OS onboarding + welcome banner — 'what is onchainos', 'what is onchain os', 'what can it do', 'what can onchainos do', 'what does onchainos do', 'how do I use this', 'how do I play', 'how to use onchainos', 'how to play onchainos', 'how does onchainos work', 'how do I start', 'getting started', 'tutorial', 'onboarding', 'first time', 'I just installed', 'now what', 'what do I do now', 'where do I start', 'who are you', 'what are you', 'introduce onchainos', 'tell me about onchainos', 'I'm new'; (2) OKX.AI intro & role-registration routing (the Agent economic system — roles User / ASP / Evaluator) — 'what is OKX.AI', 'OKX.AI 是什么', 'how to use OKX.AI', 'OKX.AI 快速开始', and any spelling / spacing / casing / typo variant (OKXAI, okx ai, okx-ai, lowercase okx.ai, 啥是okxai); (3) customer support / Help Center — 'contact support', 'talk to a human', 'customer service', 'file a complaint', 'give feedback', 'report a bug / system error', 'help center', 'FAQ', 'user guide', 'something is broken'. NOT for: direct on-chain actions (swap / wallet / balance / token) or Agent task lifecycle (publish / accept / deliver / dispute) — those have their own skills.
Create and manage Starknet wallets for AI agents. Transfer tokens, check balances, manage session keys, deploy accounts, and interact with smart contracts using native Account Abstraction.
How to use it
Take kansoku-trade/market-session-tracker from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.