agentleFS
Sign inStart free
ChainGPT-orgChainGPT-org/chaingpt-claude-skill/skills/strategy/SKILL.md

strategy

Skill7 starsChanged 53 days agoMITView on GitHub

Build trading strategy plans via the ChainGPT plugin: DCA (dollar-cost-averaging), grid trading, Hyperliquid funding-rate arbitrage, copy-trading from a target wallet, and DCA backtesting against historical price data. The strategy tools COMPUTE THE PLAN; Claude executes the steps one by one via Tier 1-3 tools (research, risk, dex, defi, hl, pm) — every action still gated by the mainnet acknowledgement refusal. Triggers: DCA, dollar cost average, grid trade, funding arb, copy trade, copy trading, strategy, backtest, replay strategy, recurring buy, periodic buy, ladder.

We split this skill into the rules it gives an agent

3 rules. 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 19 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    When the user asks "build me a DCA into ETH for $1000 over a week":

    line 22
  2. Very specific:

    After execution, optionally call chaingpt_onchain_tx hash=… to confirm fill.

    line 27
  3. Distinctive:

    Never auto-loop without the user's express turn-by-turn confirmation.

    line 29

“Common” is measured: kept by at least 6 in 10 of the 19 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

ChainGPT Strategy Skill

You build trading strategy plans — not execute them autonomously. Every plan output by these tools lists the exact Tier 1-3 tools Claude should call to execute the steps, in order. Each executing step still goes through the existing mainnet-ack gates. This keeps the agent layer reviewable and refusal-safe.

Tools

ToolWhatOutput
chaingpt_strategy_dca_planDCA schedule for one tokenList of buys (timestamp + USD size) + the exact MCP calls to execute each
chaingpt_strategy_grid_planGrid-trading ladderBuy + sell limit levels with sizes; HL / PM / DEX-flavored execution
chaingpt_strategy_funding_arb_planHL funding-rate carry suggesterSide / leverage / hourly+daily carry estimate + execution sequence
chaingpt_strategy_copy_planMirror a target wallet's swapsStep-by-step: fetch txs → decode → risk-check each outToken → scale + mirror
chaingpt_backtest_dcaReplay DCA against CoinGecko historyDCA P&L vs buy-and-hold baseline

Execution discipline

When the user asks "build me a DCA into ETH for $1000 over a week":

  1. Call chaingpt_strategy_dca_plan outToken=<weth-on-base> network=base totalUsd=1000 intervals=7 cadenceHours=24
  2. Show the plan to the user. Surface the per-buy size, cadence, and pre-flight tools. Get confirmation.
  3. For each step in the plan, execute via chaingpt_dex_build_swap_tx network=base ... acknowledgeMainnet=true. The user signs each one externally.
  4. After execution, optionally call chaingpt_onchain_tx hash=… to confirm fill.

Never auto-loop without the user's express turn-by-turn confirmation. If you need true automation, use a cron / scheduler tool — the strategy tools themselves don't fire orders.

Refusal protocol

These planner tools are read-only, so they don't refuse — but the executing tools they recommend (chaingpt_dex_build_swap_tx, chaingpt_hl_place_order_payload, chaingpt_pm_place_order_payload) all require acknowledgeMainnet: true. Surface that to the user before any execution.

What this skill does NOT do

  • Custody. Plans are returned; user signs every step externally.
  • Scheduling. See skills/scheduled-autonomy/SKILL.md; keep human confirmation and durable claims.
  • ERC-4337. Session-key support exists in beta; see skills/agent-wallet/SKILL.md. Agent-wallet signing is off by default.
  • Persistence. Save plans with chaingpt_strategy_save_plan; claim due steps before execution.
  • Live order-management. Cancellation + replacement is the user's responsibility; planner doesn't track open orders.

Backtesting caveats

chaingpt_backtest_dca uses CoinGecko's free /market_chart endpoint. Caveats:

  • Max 90 days of daily candles on the free tier (some coins).
  • Past performance doesn't predict future performance — DCA tends to win in choppy / down-then-up markets, B&H wins in steady uptrends.
  • Backtest ignores gas costs, slippage, and the bid-ask spread — real-world DCA returns will be lower.

Credit accounting

Strategy planners + backtester cost 0 ChainGPT credits — the data comes from public APIs (Hyperliquid, CoinGecko). Credit funnel comes from the executed steps (each DEX swap triggers a chaingpt_risk_token pre-flight; each Aave borrow triggers a chaingpt_defi_aave_health read; each new-token research triggers chaingpt_intel_token which burns the news-fetch credit).

Download now (ZIP)

  • Other versions22 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 22

    1. menkesu/awesome-pm-skills★ 441same name
    2. andreaskelm/pm-brain★ 234same name
    3. galiprandi/job-seeker★ 64same name
    4. thesun4sky/jobstack★ 50same name
    5. rainday/smart-blog-skills★ 35same name
    6. skyf0xx/gambit★ 29same name
    7. superuser-pal/awesome-second-brain★ 14same name
    8. BhaskarManam/pstack★ 4same name
    9. EmanueleMinotto/minottobot★ 4same name
    10. HKTITAN/isb-skills★ 4same name

    12 more not listed

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • Used alongsideProjects with it also use north-star, brand-voice and 4 more.

    Other files people use alongside this one.

    Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
    • UMwaiSkill

      north-star

      Evaluate whether current work serves the project's ultimate goal. Scores branches, goals, and commits against declared pillars/objectives. Flags drift and misalignment.

      Also in 3 projects that use this

    • Dokkabei97Skill

      brand-voice

      Defines and enforces brand voice guidelines for startups. Creates tone, style, messaging frameworks and provides consistency checks across all content. Ensures every piece of communication sounds like it comes from the same brand.

      Also in 4 projects that use this

    • MetaSkill

      roadmap

      Build, continue, inspect, or visualize a source-grounded mathematical roadmap and theorem DAG in an existing Autoform Markdown blueprint. Use for source research, repository-wide inventories of existing and planned mathematics, scope, coverage, milestones, and roadmap articles; do not create repository infrastructure or prove Lean declarations.

      Also in 3 projects that use this

    • AnthropicSkill

      brief

      Generate contextual briefings for legal work — daily summary, topic research, or incident response. Use when starting your day and need a scan of legal-relevant items across email, calendar, and contracts, when researching a specific legal question across internal sources, or when a developing situation (data breach, litigation threat, regulatory inquiry) needs rapid context.

      Also in 4 projects that use this

    • AWSSkill

      retro

      Conduct a retrospective on a coding session.

      Also in 3 projects that use this

    • OpenAISkill

      audit

      Audit or critique a product flow, journey, workflow, funnel, onboarding path, checkout path, settings path, screen, or multi-step product experience by capturing screenshots first, then reporting UX, design, and accessibility findings inline from that evidence. Use Figma only when the user explicitly asks for a board. Use when the user asks to audit, review, critique, inspect, assess, analyze, evaluate, or give feedback on a product experience.

      Also in 3 projects that use this

  • In this repository23 other files it gives its agents.

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

Reviews can't be read right now.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free