trading-desk
Skill2 starsChanged 5 months agoMITView on GitHub
End-to-end institutional trade pipeline with a hard Portfolio-Manager approve/reject gate. Use when the user wants a full desk workup before committing real money - "run the full process on X", "desk review for X", "take X through the whole pipeline", "should I actually buy X - do it properly". Chains research → risk gate → pre-trade discipline → trade ticket, and REFUSES to emit a ticket on reject.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- F0rger123/ultimate-claude-trading-skilltheir own version, first seen Nov 15, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- F0rger123/ultimate-claude-trading-skill★ 1same name
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.
In this repository29 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- adversarial-researchSkill
- auto-rebalanceSkill
- cash-deploymentSkill
- daily-briefingSkill
- dividend-strategySkill
- earnings-analyzerSkill
- earnings-postmortemSkill
- employer-stockSkill
- health-checkSkill
- macro-impactSkill
- momentum-scannerSkill
- optimize-allocationSkill
- pead-trackerSkill
- perf-optimizerSkill
- portfolio-healthSkill
- portfolio-reviewSkill
- position-reviewSkill
- pre-trade-checkSkill
- profile-setupSkill
- risk-assessmentSkill
- sector-rotationSkill
- stock-analysisSkill
- stock-compareSkill
- tax-loss-reviewSkill
- top-trades-todaySkill
- trade-journalSkill
- weekly-mirrorSkill
The file
We split this skill into the rules it gives an agent
6 rules. About 0 are common, 4 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 13
No single stage can wave a trade through.
- Distinctive: line 20
Before any position-sized entry (not a quick quote check)
- Very specific: line 31
Run the adversarial-research skill (bull / bear / consensus) on the ticker.
- Very specific: line 45
Run the pre-trade-check skill.
- Distinctive: line 49
APPROVE: only if: thesis present, no risk-gate halt, crowding < 70 (or contrarian), pre-trade-check PASS, and reward:risk ≥ 1.5.
- Distinctive: line 75
Never fabricate numbers - every figure traces to a tool call (see the data-grounding rule in stock-analysis).
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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.
Files
Trading Desk (Analyst → Research → Risk → PM Gate → Execution)
Goal
One orchestrated pass that mirrors an institutional desk: independent analysis, adversarial debate, portfolio-level risk check, behavioral discipline gate, and a final Portfolio-Manager decision that GATES whether a trade ticket is emitted. No single stage can wave a trade through. Output ends in APPROVE + ticket or REJECT + reasons - never a ticket on reject.
When to invoke
- User wants the complete process on a name before real capital
- A high-conviction idea needs a disciplined second look
- Before any position-sized entry (not a quick quote check)
Pipeline (run in order; each stage can veto)
Stage 0 - Mandate (REQUIRED):
mcp__aifolimizer__get_profile- capital, account types (never hardcode)mcp__aifolimizer__get_ticker_decision_history(ticker=TICKER, max_decisions=5) +mcp__aifolimizer__get_ticker_reflection(symbol=TICKER, n=3) +mcp__aifolimizer__get_cross_ticker_lessons(max_lessons=3) - load prior decisions BEFORE the desk forms a view. If a prior decision exists and this run flips it, the PM must state explicitly WHY (new data / catalyst / price); never silently contradict a logged decision.- Confirm ticker, direction (BUY/ADD/TRIM/SELL), horizon, rough size. If the user can't state a thesis, stop here (REJECT: no thesis).
Stage 1 - Analyst + adversarial research:
- Run the
adversarial-researchskill (bull / bear / consensus) on the ticker. - Capture: fair-value estimate, key bull driver, key bear risk, base-rate.
- For US names, fold in
mcp__aifolimizer__get_dcf_valuationas a quantitative fair-value anchor.
Stage 2 - Risk gate (HARD veto):
mcp__aifolimizer__get_risk_gate_state- if BUYs are halted (drawdown / VIX / loss-streak), a BUY/ADD is auto-REJECTED regardless of conviction.mcp__aifolimizer__get_positioning_signals- crowding ≥70 on a BUY/ADD = veto (defer; negative expected alpha for late entries).mcp__aifolimizer__get_concentration_warnings- if this trade breaches single-name/sector limits, veto or force size-down.
Stage 3 - Pre-trade discipline gate (HARD veto):
- Run the
pre-trade-checkskill. If it returns REJECT, the desk REJECTS.
Stage 4 - Portfolio-Manager decision:
- Synthesize stages 1-3 into one explicit verdict:
- APPROVE only if: thesis present, no risk-gate halt, crowding < 70 (or contrarian), pre-trade-check PASS, and reward:risk ≥ 1.5.
- Otherwise REJECT with the specific failing gate(s).
- State conviction (HIGH/MED/LOW) - drives sizing in the ticket.
Stage 5 - Execution (ONLY if APPROVE):
mcp__aifolimizer__get_trade_ticketwith the action + conviction → entry zone, stop, exit ladder, sizing.mcp__aifolimizer__log_recommendationto forward-track the call.- Optionally
mcp__aifolimizer__log_hypothesisto register the thesis with acceptance/invalidation criteria.
Output
DESK VERDICT: APPROVE | REJECT
Ticker | Direction | Conviction
Gate results: research ✓/✗ · risk ✓/✗ · crowding ✓/✗ · pre-trade ✓/✗ · R:R ✓/✗
[If APPROVE] Trade ticket: entry zone, stop, exit ladder, size, account
[If REJECT] Failing gate(s) + what would have to change to revisitRules
- A veto at ANY hard gate (Stage 2 risk halt, Stage 3 pre-trade REJECT) overrides high conviction. Do not emit a ticket.
- Never fabricate numbers - every figure traces to a tool call (see the data-grounding rule in stock-analysis).
- Tax note on the ticket: Non-Reg trims realize 50%-inclusion cap gains.
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
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.

