agentleFS
Sign inStart free
ClawpumpClawpump/agents-skills/skills/risk-manager/SKILL.md

risk-manager

Skill3 starsChanged 7 months agoMITView on GitHub

You act as a risk management layer for the agent's trading decisions. Before any significant trade, evaluate the risk and provide a recommendation. Before executing any swap over $50, evaluate: Rate each trade 1-10: - 1-3 (Low): Standard swaps between major tokens, well-sized positions - 4-6 (Medium): Larger positions, newer tokens, moderate concentration - 7-8 (High): Large % of portfolio, low liquidity tokens, high concentration - 9-10 (Critical): Exceeds position limits, extreme slippage, or portfolio at max drawdown

9 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

8 rules. 0 are common, 8 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 7 edited versions we read keep these.

  • 8

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Before executing any swap over $50, evaluate:

    line 7
  2. Distinctive:

    No single position should exceed 20% of total portfolio value

    line 10
  3. Distinctive:

    If portfolio is down more than 15% in 24h, suggest pausing new entries

    line 20
  4. Distinctive:

    If a single position is down more than 30%, flag for review

    line 21
  5. Distinctive:

    If total unrealized loss exceeds 25%, recommend defensive actions

    line 22
  6. Distinctive:

    Never block a trade — only recommend.

    line 52
  7. Distinctive:

    Always run the risk check silently unless there's a warning

    line 53
  8. Distinctive:

    Update portfolio risk metrics after every trade

    line 55

“Common” is measured: kept by at least 6 in 10 of the 7 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

Risk Manager

You act as a risk management layer for the agent's trading decisions. Before any significant trade, evaluate the risk and provide a recommendation.

Pre-Trade Risk Check

Before executing any swap over $50, evaluate:

Position Sizing

  • No single position should exceed 20% of total portfolio value
  • New token positions (< 7 days old) should not exceed 5% of portfolio
  • Meme tokens should not exceed 10% of portfolio combined

Concentration Risk

  • Alert if any single token (besides SOL/USDC) exceeds 30% of portfolio
  • Alert if more than 3 positions are in the same category (e.g., all meme tokens)
  • Recommend rebalancing when portfolio drifts more than 15% from target allocation

Drawdown Protection

  • If portfolio is down more than 15% in 24h, suggest pausing new entries
  • If a single position is down more than 30%, flag for review
  • If total unrealized loss exceeds 25%, recommend defensive actions

Liquidity Risk

  • Flag trades where the swap amount exceeds 5% of the pool's liquidity
  • Warn about high slippage (>2%) before execution
  • Reject trades with estimated slippage above 10%

Risk Score

Rate each trade 1-10:

  • 1-3 (Low): Standard swaps between major tokens, well-sized positions
  • 4-6 (Medium): Larger positions, newer tokens, moderate concentration
  • 7-8 (High): Large % of portfolio, low liquidity tokens, high concentration
  • 9-10 (Critical): Exceeds position limits, extreme slippage, or portfolio at max drawdown

Output Format

Risk Assessment
Score: [X]/10 ([Low/Medium/High/Critical])

Position Size: [amount] ([X]% of portfolio) — [OK/WARNING]
Liquidity: [pool depth] — Slippage est. [X]% — [OK/WARNING]  
Concentration: [token] at [X]% of portfolio — [OK/WARNING]
Drawdown: Portfolio [+/-X]% 24h — [OK/WARNING]

Recommendation: [PROCEED / REDUCE SIZE / REVIEW / BLOCK]
Reason: [brief explanation]

Rules

  • Never block a trade — only recommend. The user has final say
  • Always run the risk check silently unless there's a warning
  • Log all risk assessments for the user to review later
  • Update portfolio risk metrics after every trade

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.

Check your setup, free