ssmdstorm
Multi-agent orchestration for ssmd market data system tasks. Extends waldstorm with domain-specific experts for secmaster, data feeds, trading APIs, and data quality. Use when working on connectors, exchanges, NATS pipelines, market metadata, or user says "ssmdstorm", "market data task", "exchange work".
What this skill does
# ssmdstorm
Multi-agent orchestration for ssmd market data system work. Extends waldstorm with domain-specific experts.
## Overview
ssmdstorm adds 7 ssmd-specific experts to waldstorm's general panel, plus 4 exchange domain agents from shadowagent:
**ssmd experts (dlawskillz):**
| Expert | Focus Area |
|--------|------------|
| Secmaster | Market metadata, sync, lifecycle, CDC, Redis cache |
| Data Feed | Connectors, WebSocket, NATS streams, sharding |
| Access Feed | Trading APIs, orderbook, fills, positions |
| Data Quality | NATS vs API reconciliation, trade verification, DQ Python tools |
| CLI | ssmd CLI commands (Deno ops + Go GitOps), env management |
| Symbology | DB tables, NATS subjects, SQL queries for cross-exchange data |
| Parquet Backfill | Parquet generation: ssmd-parquet-gen CLI, feed/stream/prefix mappings, K8s Jobs, GCS verification |
| Harman Deploy | Harman OMS K8s deployment, new exchange instance setup, CR configuration |
| Integration Test | Kalshi demo integration tests, harman live tests, end-to-end validation |
| ssmd Architecture | Data pipeline end-to-end: component dependencies, data flow, NATS streams, CDC, impact analysis |
| Harman Architecture | OMS end-to-end: order lifecycle, EMS/OMS split, pump model, reconciliation, exchange adapters |
**Exchange domain agents (shadowagent):**
| Agent | Focus Area |
|-------|------------|
| Kalshi | Kalshi exchange: API, fees, market mechanics, crypto tickers |
| Kraken | Kraken Futures: perpetuals, funding rates, WebSocket API |
| Polymarket | Polymarket: CLOB, Gamma API, token model, sharding |
| Symbology | Cross-exchange identifier formats, ticker anatomy |
## Expert Selection Guide
| Task Domain | ssmd Experts | + shadowagent | + General Experts | + varlab-ops |
|-------------|--------------|---------------|-------------------|--------------|
| Market metadata work | Secmaster, CLI | - | Database, Senior Dev | - |
| Adding new exchange | Data Feed | shadow:{exchange} | DevOps, Security | Operations |
| Trading API integration | Access Feed, Secmaster | shadow:{exchange} | Security, API Designer | - |
| Data pipeline architecture | ssmd Architecture | shadow:{exchange} | Senior Dev, Performance | - |
| OMS architecture decisions | Harman Architecture | shadow:{exchange} | Security, Senior Dev | - |
| Pipeline deployment | Data Feed, CLI | - | DevOps, Platform/Infra | Operations |
| Signal development | Data Feed, Secmaster, CLI | shadow:{exchange} | Performance, QA | - |
| CDC/cache work | Secmaster | - | Database, Performance | - |
| Orderbook integration | Access Feed, Data Feed | shadow:{exchange} | Performance, Security | - |
| CLI operations | CLI | - | DevOps | - |
| Data quality checks | Data Quality, CLI | shadow:{exchange} | QA | - |
| Parquet backfill/regen | Parquet Backfill, Data Quality | - | DevOps | Operations |
| Ticker/ID mapping | Symbology | shadow:symbology | Database | - |
| Cross-exchange correlation | Symbology, Data Feed | shadow:symbology | Performance | - |
| End-to-end deploy (code + K8s) | Data Feed, CLI | shadow:{exchange} | Security, Performance | Operations |
### Cross-Skill Pairing
Tasks that span code AND infrastructure need experts from **both** ssmdstorm and varlab-ops. The selection guide above includes the varlab-ops column for these cases. Common cross-skill patterns:
| Pattern | Why Both Skills |
|---------|----------------|
| New exchange end-to-end | ssmd: connector code, NATS subjects, writer. varlab-ops: K8s deployment, NATS stream, archiver CR, network policy |
| Image build + deploy | ssmd: Rust/Deno changes, tag format. varlab-ops: deployment YAML, Flux reconcile, image pull |
| Scale operations | ssmd: CLI commands. varlab-ops: Flux suspend/resume, kubectl context |
### Trigger Keywords
When analyzing a task description, match these keywords to experts:
| Keywords | Expert |
|----------|--------|
| websocket, connector, exchange, feed, subscribe, channel | Data Feed |
| secmaster, market metadata, sync, CDC, Redis, lifecycle | Secmaster |
| orderbook, fill, position, trading, order, balance | Access Feed |
| nats count, match rate, reconciliation, missing trades, dq | Data Quality |
| cli, scale, deploy, env, schedule, deno task | CLI |
| ticker, symbol, pair_id, token_id, condition_id, identifier, cross-exchange | Symbology |
| parquet, backfill, regenerate, parquet-gen, jsonl to parquet | Parquet Backfill |
| harman deploy, new harman instance, harman CR, exchange instance | Harman Deploy |
| integration test, demo API, live test, harman test, end-to-end test | Integration Test |
| architecture, component dependency, impact analysis, data flow, pipeline design | ssmd Architecture |
| order lifecycle, EMS, OMS, pump model, reconciliation, exchange adapter, session model | Harman Architecture |
| kalshi, prediction market, contract, series, category, CFTC | shadow:kalshi |
| kraken, perpetual, funding rate, PF_, FF_, futures | shadow:kraken |
| polymarket, CLOB, condition_id, token, Gamma API, UMA | shadow:polymarket |
| ticker format, pair anatomy, cross-exchange mapping | shadow:symbology |
| mcp, api key, data access, market lookup, datasets:read, query parquet | Symbology, Data Feed |
| deployment, kustomization, flux, network policy, PVC | Operations (varlab-ops) |
| securityContext, input validation, sanitization, auth | Security (waldstorm) |
| max_message_size, buffer, latency, throughput, memory | Performance (waldstorm) |
## Instructions
### Step 1: Understand the Task
Same as waldstorm - gather task description, constraints, context.
### Step 2: Select Experts
**Always include at least one ssmd expert.** Use the selection guide above.
**MANDATORY:** Always include the **QA/Testing Expert** (`dlaw:qa-testing-expert`) in every expert panel. Complete unit test coverage is required for all code changes.
**Agent definitions** in `agents/` provide each ssmd expert as a spawnable agent with `memory: local` for persistent learnings across sessions.
Available ssmd agents (dlawskillz, in `./agents/`):
- `ssmd-secmaster` - Market metadata, sync, CDC
- `ssmd-data-feed` - Connectors, NATS, archiving
- `ssmd-access-feed` - Trading APIs, orderbook, fills
- `ssmd-data-quality` - NATS vs API reconciliation, trade verification, DQ Python tools
- `ssmd-cli` - ssmd CLI commands (Deno ops + Go GitOps), env management
- `ssmd-symbology` - DB tables, NATS subjects, SQL queries for cross-exchange data
- `ssmd-parquet-backfill` - Parquet generation CLI, feed/stream/prefix mappings, K8s Jobs, GCS verification
- `ssmd-harman-deploy` - Harman OMS K8s deployment, new exchange instance setup
- `ssmd-integration-test` - Kalshi demo integration tests, harman live tests, end-to-end validation
- `ssmd-architecture` - Data pipeline architecture: component deps, data flow, NATS, CDC, impact analysis
- `harman-architecture` - OMS architecture: order lifecycle, EMS/OMS, pump, reconciliation, exchange adapters
Available exchange agents (shadowagent, `shadow:` prefix):
- `shadow:kalshi` - Kalshi exchange: API, fees, market mechanics, crypto tickers
- `shadow:kraken` - Kraken Futures: perpetuals, funding rates, WebSocket API
- `shadow:polymarket` - Polymarket: CLOB, Gamma API, token model, sharding
- `shadow:symbology` - Cross-exchange identifier formats, ticker anatomy
Combine with waldstorm's general agents (Security, DevOps, etc.) as needed.
### Step 3-9: Follow waldstorm
Use team primitives (TeamCreate, TaskCreate, Task tool for teammates, SendMessage) to run expert analysis, then synthesize, plan, and execute per waldstorm workflow. This includes:
- **Step 6 (ECC Code Review):** After synthesis, optionally invoke `everything-claude-code:code-review` for an independent structured review of proposed changes. Recommended for any task touching data pipelines, trading APIs, or security-sensitive code.
- **Step 7 (Writing Plans):** Use `superpowers:writing-plans` to save implementation plan
- **Step 8 (Executing Plans):** Use `suRelated 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.