himanshuj16/tradefloor/review
- community
Checking that the SKILL.md file is still in the repository.
Score tradefloor's past calls against what the market actually did - hit rate, Brier score against the base-rate reference, stop hits, realized returns - and report whether the calls show skill. Use when the user asks how past predictions did, wants a track record, or after a call's horizon has passed.
Install
npx vskill@latest install himanshuj16/tradefloor/reviewSKILL.md
tradefloor: review the record
Arguments: $ARGUMENTS
- Call
journal_review(symbol)(symbol optional, from$ARGUMENTSif given). - Reply with:
- Summary: scored calls, open calls, hit rate, Brier score for p(up) and the
base-rate reference Brier, and beats_base_rate.
- A table of scored calls, newest first: date, symbol, horizon, call, p(up),
realized return, outcome, hit, stop hit.
- Open calls with bars elapsed out of the horizon.
- Interpret without spin:
- Under 30 scored calls, the hit rate is noise. Say that first.
- Beating the base-rate Brier is the bar. A 60% hit rate on an asset that rose 60% of
the time is no skill.
- Separate
quantfromfullcalls if both exist, so the user can see whether the
agent layer adds anything over the price model.
- For the three worst misses, read the run folder (
run_dirin the entry) if it exists
and name, in one line each, what the desk missed.
If the journal is empty, say so and point to the direction and analyze procedures, which record calls automatically. The journal lives in ~/.tradefloor/journal.sqlite3 and is shared by every agent host.
Security
- Security scanPassed, 90 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/review/SKILL.md
Popularity
- 7-day trend score
- 5
Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/himanshuj16/tradefloor/review)