review-trades
Skill36 starsChanged 3 days agoMITView on GitHub
Review the desks' closed trades - rebuild the trade ledger from public fills, test every slice for fluke or edge, list backtest proposals. Read only; never edits live config or places an order. Runs daily from /desk-loops and once after any close.
In this repository6 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- desk-loopsSkill
- desk-tickSkill
- event-calendarSkill
- desk-tickSkill
- pathiel-agentSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 0 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 35
Something new?: If new_leaks names a slice or new_proposals is above 0: say so in one short message (the slice, its label, n, and the lever …
- Very specific: line 62
Never edit live config, .claude/agents/desk-tick.md, the desk-tick skill, or a live constant from this skill.
- Very specific: line 65
Never feed the report into a thesis prompt (SCORECARD_TEST_2026-10-31.md: the desk's own record in its prompt made money worse).
≈ “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
review-trades
The learning loop (operator, 2026-11-02: "continuously evolve, learn from what we did right, fix what we did wrong, see if mistakes and successes are just flukes or a predictions"). One script call; no agent, no LLM, no MCP.
Run it from the repo root:
python3 -m services.review runIt fetches the wallet's fills (public Hyperliquid reads), updates
$PATHIEL_STATE_DIR/review/ledger.jsonl, writesdocs/strategy/learning/REVIEW_<UTC date>.mdand prints one line that startsREVIEW <utc> trades=....Print that line. Nothing else when it says
new_leaks=noneandnew_proposals=0. 2b. Check the call grades are current (read only, no network):python3 -m services.strategies.evals.grading_lag_checkIt prints one
GRADING OK|FAIL ...line. On FAIL, print it and the rows under it:stale(a call past its horizon with no grade),sweep ... STOPPED(calls pending and the grader's heartbeatstrategies/grade_sweep.jsonis missing or older than 2h) andmissed(a pending call the last sweep never read) all mean the dashboard server's hourly sweep (pathiel/server.py_grade_loop) is not running or is on old code; say so and name the restart. A highpendingcount withsweep=0.xh agoand no rows is fine: those calls are open, the sweep read them and left them. Never grade from here.- Something new? If
new_leaksnames a slice ornew_proposalsis above 0: say so in one short message (the slice, its label, n, and the lever the report proposes, from the report's "What to try next"), and append the summary line to/tmp/oil-loop/progress.logasREVIEW <utc> <rest of the line>. A new LEAK goes to the operator as a yes/no, the same day (operator, 2026-11-04: "aren't we grading and growing... too many tests not enough results"). When
new_leaksnames a slice, send ONEPushNotificationand print the same question:LEAK <slice>: <n> trades, <wins> win(s), <net $>. Turn on <lever>? yes/no<lever>is that slice's line under "What to try next" (itsTryand what it does in plain words). Ask once per new leak. A yes is the go: make the change in the desk rules with a gate test and a real-fills eval (services/strategies/evals/no_break_real_fills.pyis the pattern), commit, and say what to restart. A no: note it in the next report run and do not ask again for that slice. The review itself still changes nothing.- If it fails (network, a parse error): print the last line of the error once and stop. Do not retry in a loop; the next scheduled run will.
Rules
- LEANING proposals are backtested on the operator's OK, with the command the report gives, and adopted only on the operator's go. A LEAK (10+ trades, labeled LEAK) skips the backtest: it goes straight to the operator as the yes/no in step 4.
- Never edit live config,
.claude/agents/desk-tick.md, the desk-tick skill, or a live constant from this skill. Never call a pathiel MCP tool here. The review only reads. - Never feed the report into a thesis prompt (SCORECARD_TEST_2026-10-31.md: the desk's own record in its prompt made money worse).
- n is small: an EDGE or LEAK needs at least 10 trades in one slice. Say LEANING, FLUKE or NOISE as the report does; never round them up.
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.

