desk-post-trade-review
Skill530 starsChanged 5 days agoMITView on GitHub
The Trade Reviewer's procedure for journaling desk activity and reviewing trades from the exchange record - process graded separately from outcome, execution costs measured, one repeatable finding per review, plus the weekly desk review. Use after any send, when a trade closes, on the weekly routine, or when the user asks "how did that go".
2 other projects use a version of this, 1 of them edited.
Adopted by
Most recently taken up by
- swcstudiospace/PumpGroktheir own version, first seen Nov 5, 2026
- Mendurim/strikegrok-trading-deskedited, first seen Sep 10, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 1
- Mendurim/strikegrok-trading-desk★ 022% same
Wrote their own version · 1
- swcstudiospace/PumpGrok★ 66same 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 repository17 other files it gives its agents.
- AGENTS.mdAGENTS.md
- desk-execution-protocolSkill
- desk-incident-responseSkill
- desk-monitoringSkill
- desk-operating-modelSkill
- desk-risk-limitsSkill
- desk-strategy-labSkill
- desk-trade-lifecycleSkill
- hypergrok-bootstrapSkill
- hyperliquid-accountSkill
- hyperliquid-advancedSkill
- hyperliquid-api-referenceSkill
- hyperliquid-market-dataSkill
- hyperliquid-ordersSkill
- hyperliquid-positionsSkill
- hyperliquid-setupSkill
- hyperliquid-websocketSkill
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
- Very specific: line 63
Write the review under ## review in the proposal file and send the block (format in agents/trade-reviewer.md) by DM to the Desk Lead and …
- Distinctive: line 76
No recommendations about what to trade.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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
Journal and post-trade review
The journal is the desk's memory; the review is how the desk learns. Both come from the exchange record first and chat second, and both keep process and outcome apart.
1. Journal
/workspace/trading-desk/journal/YYYY-MM-DD.md, one file per active day, appended in time order. Entry types:
14:02 UTC HG-20260816-01 opened ETH-PERP long idea (user); status evidence
14:12 UTC HG-20260816-01 risk PASS 0.4827 ETH, stop 2,900, 0.5% risk stressed (risk-limits v3)
14:29 UTC HG-20260816-01 approval "approve HG-20260816-01" (user)
14:31 UTC HG-20260816-01 sent buy 0.4827 @ 3,000 Gtc + sl 2,900 (normalTpsl); cloid 0x9f3e...; oid 1839201122, sl waitingForFill
16:05 UTC HG-20260816-01 fill 0.4827 @ 3,000.0 maker, fee $0.29
09:12 UTC HG-20260816-01 closed tp 3,089.6, fee $1.44; position flat; sl 2,900 cancelled 09:13
10:00 UTC limits risk-limits v3 -> v4: max positions 3 -> 4 (user, reason: adding HYPE)
11:40 UTC incident INC-20260817-01 send timeout on HG-20260817-02; not on exchange, waited out expiresAfter 11:41, re-checked clean, re-approved and sent 11:47
18:00 UTC note maker entries at 10 bps depth filled within 2h on both attempts this weekRules: append only; corrections are new lines with correction:; every line has a UTC time and an id where one exists; no opinions in the journal (those go in reviews).
2. Trade review
Trigger: a proposal reaches closed, or the user asks. Inputs, always listed with timestamps:
- the proposal file (ticket, PASS, approval, execution, reconciliation)
userFills/userFillsByTimefor the window: price, size, fee, side,crossedhistoricalOrdersandorderStatusby cloid: what rested when, what cancelleduserFundingfor the holding window- optionally the Market Analyst's depth read at send time for expected slippage
Compute:
| Measure | How |
| Entry slippage | (fill avg - ticket price) / ticket price in bps, signed against the trade |
| Exit slippage | same for the exit versus its ticket or trigger price |
| Fees | sum of fill fees in USD and as bps of notional; note maker vs taker |
| Funding | sum of funding payments over the window, USD |
| Net result | realised PnL after fees and funding, in USD and in R (R from the ticket) |
| Protection | was a reduce-only stop resting on the exchange for the entire life of the position? gaps in minutes |
| Lifecycle | each stage present, in order, with timestamps; approval by id; single send; reconciled |
| Holding time | fill to flat |
Grade:
- Process: clean / minor break / major break, with the specific stage named. A major break is any send without PASS or approval by id, any missing protection, any resend on unknown result, or any limit breached.
- Outcome: result in R and USD, stated without adjectives.
Then one thing: a leak, a control that worked, or a break, chosen because it is repeatable. Not a list.
Write the review under ## review in the proposal file and send the block (format in agents/trade-reviewer.md) by DM to the Desk Lead and the user. Set status: closed.
3. Weekly desk review
From the journal, proposals and the exchange record for the week:
- proposals opened / rejected / voided / executed / closed
- trades closed: count, hit rate, average win and loss in R, expectancy in R (mean of results), largest loss, largest drawdown in equity terms from
portfolioor start/end equity - costs: fees and funding in USD and as a share of gross PnL
- process: number of breaks by type; incidents and their status
- limits: any changes and why
- one pattern worth the user's attention, stated as a fact pattern
No recommendations about what to trade. If the user asks, hand strategy questions to the Strategist and sizing questions to the Risk Manager.
4. Incident review
For each INC-YYYYMMDD-NN: timeline (journal + exchange record), what the desk did, what the controls did, exposure during the incident, root cause where knowable, one corrective action with an owner and a date. Blameless in tone, exact in fact. Written to /workspace/trading-desk/journal/incidents/<id>.md and linked from the daily journal.
Pitfalls
- Reviewing from chat memory rather than fills. Chat says what people meant; fills say what happened.
- Letting the outcome colour the process grade. Grade process first, then look at the outcome.
- Counterfactuals ("if we had held..."). Not evidence.
- Ten findings per review. Nobody acts on ten.
- Editing old journal lines. Append a correction.
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.

