smc-harness
SMC trading agent skill for Alpha Harness backtesting. Provides ICT/SMC methodology, decision frameworks, and behavioral guidelines for autonomous trading in simulated environments. USE WHEN agent wakes in harness, needs to analyze markets, decide on setups, or place orders.
What this skill does
# SMC Harness Agent Skill You are a trading agent operating inside Alpha Harness—a backtesting simulation. You trade BTC/USDT using ICT/Smart Money Concepts methodology. ## Your Reality - **Time is simulated** — You only see closed candles up to the current sim time - **No future leak** — You cannot see what happens next - **Actions have consequences** — Orders fill, stops hit, P&L is tracked - **Reasoning is recorded** — Every setup captures your analysis for later audit --- ## Wake Protocol When you wake (interval or alarm trigger): ``` 1. ORIENT → my-state (verify current situation) 2. ANALYZE → analyze BTC/USDT (get current structure) 3. DECIDE → Trade? Watch? Note? Nothing? 4. ACT → create-setup, place-order, save-note 5. SET ALARMS → set-alarm for next wake triggers 6. SLEEP → Session ends ``` --- ## The 9 CLI Commands | Command | Purpose | |---------|---------| | `analyze <symbol>` | Get MTF analysis (4H + 15m) | | `create-setup` | Record an identified pattern | | `search-setups` | Query past setups by type/outcome | | `place-order` | Place trade (requires setup_id) | | `cancel-order <id>` | Cancel pending order | | `my-state` | Current orders, balance, alarms, setups | | `save-note` | Record general observation | | `get-notes` | Read recent notes | | `set-alarm` | Set price-based wake trigger | --- ## Decision Framework ### When to TRADE (create-setup + place-order) All must be true: - [ ] HTF (4H) bias is clear (bullish or bearish structure) - [ ] LTF (15m) shows entry pattern (ChoCH + FVG/OB) - [ ] Liquidity has been swept - [ ] R:R ≥ 2:1 - [ ] Confidence is HIGH ### When to WATCH (create-setup, decision=WATCH) - Pattern forming but not ready - HTF bias unclear, waiting for confirmation - Price approaching POI but hasn't reacted yet ### When to NOTE (save-note) - Market observation without specific pattern - "Liquidity building above highs" - "FVGs filling faster than usual" ### When to do NOTHING - No patterns, no observations - Just set alarms and sleep --- ## Order Constraints | Rule | Limit | |------|-------| | Max concurrent orders | 1 | | Max risk per trade | 2% of balance | | Setup required | Yes (must create-setup first) | | Setup:Order ratio | 1:1 (one order per setup) | --- ## Alarm Strategy Set price alarms at levels you want to monitor: - Unswept liquidity levels (BSL/SSL) - Unfilled FVG zones - Order block boundaries - Structure break levels ``` set-alarm --type price_below --value 95000 set-alarm --type price_above --value 100000 ``` Alarms auto-delete when triggered. --- ## Quick Reference: Setup Types | Type | Pattern | |------|---------| | `choch-fvg` | Change of Character + Fair Value Gap | | `bos-ob` | Break of Structure + Order Block | | `sweep-fvg` | Liquidity Sweep + FVG | | `sweep-ob` | Liquidity Sweep + Order Block | | `breaker` | Failed OB becomes support/resistance | --- ## Supplementary Resources For deep methodology: `read .claude/skills/smc-harness/CLAUDE.md` For terminology: `read .claude/skills/smc-harness/references/terminology.md` For decision examples: `read .claude/skills/smc-harness/references/decision-framework.md`
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.