agentleFS
ntaffziintaffzii/Skill-Agents/skills/trading/SKILL.md

trading

Skill4 starsChanged 2 months agoMITView on GitHub

Route and manage trading/investing workflow skills — market breadth and uptrend participation scoring, exposure/posture synthesis, risk-based position sizing, drawdown circuit breaker, periodic portfolio review, dividend/value screening, and trade journaling. Use when the user asks for market-regime checks, position sizing, risk gates, portfolio review, or trade journaling/stats.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    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. Very specific:

    Use this skill to find the right trading/investing skill in skills/trading/.

    line 8
  2. Distinctive:

    No skill in this category executes trades, connects to a broker, or claims to predict future returns.

    line 35

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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

Trading Skills

Use this skill to find the right trading/investing skill in skills/trading/.

Purpose

skills/trading/ is a workflow toolkit for a time-constrained individual investor — long-term/dividend/ETF core holdings, plus disciplined swing trading as a satellite strategy, plus general market-awareness. It structures market review, risk management, and trade journaling. It is not a signal service and does not place trades. Every skill in this category treats the human as the decision-maker; the skills compute numbers and structure checklists, they don't recommend trades.

Pattern inspired by tradermonty/claude-trading-skills (MIT) — see NOTICE.md for attribution. That source repo has 71 skills; this starter set (9 skills) covers the three areas actually in use here (long-term/dividend investing, disciplined swing trading, general market awareness) rather than replicating the full catalog. Expand it the same way thai/ was expanded — pick one gap at a time, verify it, register it.

Skills in this category

SkillPurposeArea
market-breadth-analyzer% of a universe trading above a moving average, from a CSVMarket regime
uptrend-analyzer% of a universe in an established "stage 2" uptrend structureMarket regime
exposure-coachCombines breadth + uptrend + drawdown state into one exposure-ceiling readMarket regime
position-sizerRisk-based share sizing (fixed-fractional, ATR-based, Kelly)Swing / risk
drawdown-circuit-breakerMechanical size-reduction/halt rule after account drawdownSwing / risk
portfolio-managerPeriodic core-portfolio review checklist (concentration, rebalance, dividends)Core portfolio
dividend-value-screenerValue/dividend-quality screening checklist, yield-trap detectionCore portfolio
trader-memory-coreTrade journal schema + win rate / R-multiple / expectancy statsTrade memory
backtest-expertSimulate a long-only rule (or MA-crossover) against historical prices — win rate, drawdown, profit factorStrategy validation

Suggested chain for a daily/weekly market check: market-breadth-analyzer + uptrend-analyzer → exposure-coach → (if opening new risk) position-sizer, gated by drawdown-circuit-breaker → close the loop with trader-memory-core after the trade closes. Before trusting a rule enough to trade it at all, run it through backtest-expert first.

Rules

  • Every skill in this category must carry a "not financial advice" disclaimer. Treat it as load-bearing — do not remove it during later edits.
  • No skill in this category executes trades, connects to a broker, or claims to predict future returns. If a request implies an automated signal/execution service, say so explicitly and decline that framing rather than building toward it.
  • Illustrative thresholds (risk %, drawdown triggers, exposure bands) are starting heuristics, not validated rules — every skill that uses one says so and tells the user to tune it against their own history.
  • Code-bearing skills operate on data the user supplies (CSV, account numbers, journal entries) — none of them fetch live market data. If live data integration is ever added, it needs its own explicit skill/tool with its own API-key and rate-limit handling, not folded silently into these.

Known limitations

  • This is a starter set (9 of the source repo's 71 skills), chosen for long-term/dividend investing, disciplined swing trading, and general market awareness. Screener skills that need live technical/fundamental data (breakout screeners, earnings calendars, full CANSLIM/VCP screening) are still out of scope — the source repo's docs/en/skills/ catalog is the reference if/when those get added.
  • Market-structure heuristics (uptrend definition, breadth interpretation bands, exposure thresholds) reflect common, widely-cited conventions, not a single "correct" methodology — different traders/strategies define these differently.

Download now (ZIP)

Does it work?

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

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

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.