Turn daily market observations, unusual activity, and news reactions into structured clues for investigating trading opportunities. Export hints.yaml for later analysis, with optional ideas from a language model added through an external command or a prepared file.
Extract edge hints from daily market observations and news reactions, with optional LLM ideation, and output canonical hints.yaml for downstream concept synthesis and auto detection.
Run score Not tested
See how to installReview the instructions the agent will receive before you install.
Convert raw observation signals (market_summary, anomalies, news reactions) into structured edge hints.
This skill is the first stage in the split workflow: observe -> abstract -> design -> pipeline.
hints.yaml input for concept synthesis or auto detection.PyYAMLmarket_summary.jsonanomalies.jsonnews_reactions.csv or news_reactions.jsonhints.yaml containing:
hints listmarket_summary, anomalies, optional news reactions).scripts/build_hints.py to generate deterministic hints.--llm-ideas-cmd — pipe data to an external LLM CLI (subprocess).--llm-ideas-file PATH — load pre-written hints from a YAML file (for Claude Code workflows where Claude generates hints itself).hints.yaml into concept synthesis or auto detection.Note: --llm-ideas-cmd and --llm-ideas-file are mutually exclusive.
Rule-based only (default output to reports/edge_hint_extractor/hints.yaml):
python3 skills/edge-hint-extractor/scripts/build_hints.py \
--market-summary /tmp/edge-auto/market_summary.json \
--anomalies /tmp/edge-auto/anomalies.json \
--news-reactions /tmp/news_reactions.csv \
--as-of 2026-02-20 \
--output-dir reports/
Rule + LLM augmentation (external CLI):
python3 skills/edge-hint-extractor/scripts/build_hints.py \
--market-summary /tmp/edge-auto/market_summary.json \
--anomalies /tmp/edge-auto/anomalies.json \
--llm-ideas-cmd "python3 /path/to/llm_ideas_cli.py" \
--output-dir reports/
Rule + LLM augmentation (pre-written file, for Claude Code):
python3 skills/edge-hint-extractor/scripts/build_hints.py \
--market-summary /tmp/edge-auto/market_summary.json \
--anomalies /tmp/edge-auto/anomalies.json \
--llm-ideas-file /tmp/llm_hints.yaml \
--output-dir reports/
skills/edge-hint-extractor/scripts/build_hints.pyreferences/hints_schema.mdNo reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Plan and assess backtests, which test trading rules against historical data. Examine sensitivity to rule changes, trading costs, and data bias, then use supplied performance metrics to generate a structured evaluation with reasons that block adoption.
Analyze chart images showing how broadly US stocks are participating in market trends. Assess medium-term conditions and short-term signals, then produce an English report with positioning guidance, alternative scenarios, and risks based on the visible data.
Assess how broadly US stock market gains are shared across stocks using public CSV data and optional charts. Produce English reports covering market conditions, trading signals, scenarios, and positioning for different investment timeframes.
Turn VCP screening results, which identify narrowing price swings, into breakout trade plans. Calculate entry, stop-loss, target prices, and position sizes using worst-case entries, while applying portfolio risk limits and producing Alpaca-compatible order templates.
Screen US growth stocks with William O'Neil's CANSLIM method, which evaluates seven factors including earnings, price strength, trading volume, and market direction. Receive ranked candidates with composite scores, factor breakdowns, market warnings, and data quality notes.
Combine three reports on crowded positions, failed reactions to news, and weekly price reversals into one trading setup status. Identify missing or invalid evidence and determine whether the setup is ready for planning.