schwab-data-sweep
Collect a single Schwab MCP data snapshot (accounts, quotes, indicators, option chains) with a five-minute cache so trading agents can reuse consistent inputs. Use whenever an options persona needs fresh risk, market, or chain data before recommending trades.
What this skill does
# Schwab Data Sweep
Reliable trade proposals in this workspace start from the same broker payloads. This skill centralizes that workflow so every persona reuses the identical snapshot and cache policy.
## Inputs
- `primary_symbol` (string): Underlying or index to analyze. Prefix indices/volatility products with `$` (e.g., `$SPX`, `$VIX`, `$VIX1D`) to avoid equity substitutions.
- `additional_symbols` (list, optional): Extra tickers for quotes (e.g., the wheel watchlist or hedge ETFs). Keep the list tight to minimize MCP latency.
- `include_option_chain` (bool, default true): Fetch option chain data for `primary_symbol`.
- `indicators` (list, optional): Indicator payloads to compute. Supported values: `atr`, `rsi`, `expected_move`, `historical_volatility`.
- `force_refresh` (bool, default false): Ignore cached payloads even if they are younger than five minutes.
## Outputs
Structured dictionary stored in memory for the calling agent:
- `timestamp`: ISO string + broker timezone from `mcp__schwab__get_datetime`.
- `account`: Payload from `mcp__schwab__get_account_with_positions()`.
- `quotes`: Map of symbol → quote (from `mcp__schwab__get_quotes()`).
- `historical`: Optional OHLCV data (from `mcp__schwab__get_price_history_every_day()` for 1M window).
- `option_chain`: Optional option chain snapshot (when requested).
- `indicators`: Any computed indicators with metadata about lookback and parameters.
## Instructions
1. **Cache Check**
- Maintain a per-symbol cache keyed by `primary_symbol` + sorted `additional_symbols`.
- Reuse the existing snapshot when `force_refresh` is false and the cached timestamp is ≤5 minutes old.
- When reusing, surface the original Schwab timestamp so downstream persona messaging reflects the data age.
2. **Authentication Guardrail**
- Call `mcp__schwab__get_account_numbers()` once per session if the MCP client indicates an unauthenticated state. Abort and return a `BLOCK` flag if authentication fails.
3. **Account & Capital Snapshot**
- Run `mcp__schwab__get_account_with_positions()` to capture net liquidity, cash, buying power, and open option positions.
- Derive helper metrics (wheel exposure %, margin headroom, overlapping SPX structures) for persona-specific reporting, but keep raw payloads intact in the output.
4. **Market Quotes**
- Assemble the quote request list: `{primary_symbol} ∪ additional_symbols ∪ {$VIX, $VIX1D}` when indices are relevant.
- Use `mcp__schwab__get_quotes(symbols=...)` with `fields="QUOTE,FUNDAMENTAL"` when single-name data is required for event checks.
- Normalize timestamps (store both the broker timezone and Eastern Time equivalent for later formatting).
5. **Historical Context**
- Call `mcp__schwab__get_price_history_every_day(primary_symbol, period_type="MONTH", period="ONE_MONTH")` to support ATR/expected-move math.
- Skip when the persona explicitly disables historical pulls to reduce latency.
6. **Indicator Bundle**
- For each indicator requested, call the matching Schwab MCP function:
- `atr` → `mcp__schwab__atr(symbol=primary_symbol, interval="DAY", length=14)`
- `rsi` → `mcp__schwab__rsi(symbol=primary_symbol, interval="DAY", length=14)`
- `expected_move` → `mcp__schwab__expected_move(symbol=primary_symbol, interval="DAY")`
- `historical_volatility` → `mcp__schwab__historical_volatility(symbol=primary_symbol, period=30)`
- Store both the numeric result and the parameters used so personas can echo them in final outputs.
7. **Option Chain Snapshot**
- When `include_option_chain` is true, call `mcp__schwab__get_option_chain(symbol=primary_symbol, include_quotes="true", strike_count=40)`.
- Cache the option chain alongside its Schwab timestamp; note in the output when the chain comes from outside regular trading hours.
8. **Packaging & Return**
- Combine all payloads into the output dictionary and persist it in the cache with the broker timestamp.
- Return the object plus a `cache_metadata` block containing: `source_timestamp`, `eastern_timestamp`, `cache_expires_at`, and `force_refresh_used` flag.
## Usage Notes
- Personas should call this skill exactly once per planning cycle, then reference the cached snapshot for prerequisite checks, sizing, and proposal outputs.
- When a user asks for “updated marks” or more than five minutes have elapsed, set `force_refresh=true`.
- If a required symbol is missing from Schwab (e.g., delisted or after-hours only), return a `FLAG` status with guidance instead of silently omitting the data.
## Examples
```yaml
# 0DTE iron condor sweep
primary_symbol: $SPX
additional_symbols: [$VIX, $VIX1D]
indicators: [atr, rsi, expected_move]
include_option_chain: true
```
```yaml
# Wheel candidate sweep for a single-name equity
primary_symbol: AAPL
additional_symbols: [$VIX]
indicators: [atr, rsi, historical_volatility]
include_option_chain: true
```
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.