Generate and prioritize US equity long-side edge research tickets from EOD observations, then export pipeline-ready candidate specs for trade-strategy-pipeline Phase I. Use when users ask to turn hypotheses/anomalies into reproducible research tickets, convert validated ideas into `strategy.yaml` + `metadata.json`, or preflight-check interface compatibility (`edge-finder-candidate/v1`) before running pipeline backtests.
How this skill is triggered — by the user, by Claude, or both
Slash command
/trading-strategy-tools:edge-candidate-agentThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Convert daily market observations into reproducible research tickets and Phase I-compatible candidate specs.
Convert daily market observations into reproducible research tickets and Phase I-compatible candidate specs. Prioritize signal quality and interface compatibility over aggressive strategy proliferation. This skill can run end-to-end standalone, but in the split workflow it primarily serves the final export/validation stage.
strategy.yaml + metadata.json for trade-strategy-pipeline Phase I.edge-finder-candidate/v1 before pipeline execution.PyYAML installed.trade-strategy-pipeline repository for schema/stage validation.uv available when running pipeline-managed validation via --pipeline-root.strategies/<candidate_id>/strategy.yaml: Phase I-compatible strategy spec.strategies/<candidate_id>/metadata.json: provenance metadata including interface version and ticket context.scripts/validate_candidate.py (pass/fail + reasons).daily_report.mdmarket_summary.jsonanomalies.jsonwatchlist.csvtickets/exportable/*.yamltickets/research_only/*.yamlRecommended split workflow:
skills/edge-hint-extractor: observations/news -> hints.yamlskills/edge-concept-synthesizer: tickets/hints -> edge_concepts.yamlskills/edge-strategy-designer: concepts -> strategy_drafts + exportable ticket YAMLskills/edge-candidate-agent (this skill): export + validate for pipeline handoffskills/edge-candidate-agent/scripts/auto_detect_candidates.py--hints for human ideation input--llm-ideas-cmd for external LLM ideation loopreferences/pipeline_if_v1.mdreferences/signal_mapping.mdreferences/research_ticket_schema.mdreferences/ideation_loop.mdreferences/research_ticket_schema.md.skills/edge-candidate-agent/scripts/export_candidate.py.skills/edge-candidate-agent/scripts/validate_candidate.py.trade-strategy-pipeline and run dry-run first.Daily auto-detection (with optional export/validation):
python3 skills/edge-candidate-agent/scripts/auto_detect_candidates.py \
--ohlcv /path/to/ohlcv.parquet \
--output-dir reports/edge_candidate_auto \
--top-n 10 \
--hints path/to/hints.yaml \
--export-strategies-dir /path/to/trade-strategy-pipeline/strategies \
--pipeline-root /path/to/trade-strategy-pipeline
Create a candidate directory from a ticket:
python3 skills/edge-candidate-agent/scripts/export_candidate.py \
--ticket path/to/ticket.yaml \
--strategies-dir /path/to/trade-strategy-pipeline/strategies
Validate interface contract only:
python3 skills/edge-candidate-agent/scripts/validate_candidate.py \
--strategy /path/to/trade-strategy-pipeline/strategies/my_candidate_v1/strategy.yaml
Validate both interface contract and pipeline schema/stage rules:
python3 skills/edge-candidate-agent/scripts/validate_candidate.py \
--strategy /path/to/trade-strategy-pipeline/strategies/my_candidate_v1/strategy.yaml \
--pipeline-root /path/to/trade-strategy-pipeline \
--stage phase1
validation.method: full_sample.validation.oos_ratio omitted or null.pivot_breakout with vcp_detectiongap_up_continuation with gap_up_detectionid mismatch.interface_version: edge-finder-candidate/v1.--dry-run in pipeline before full execution.skills/edge-candidate-agent/scripts/export_candidate.pyGenerate strategies/<candidate_id>/strategy.yaml and metadata.json from a research ticket YAML.
skills/edge-candidate-agent/scripts/validate_candidate.pyRun interface checks and optional StrategySpec/validate_spec checks against trade-strategy-pipeline.
skills/edge-candidate-agent/scripts/auto_detect_candidates.pyAuto-detect edge ideas from EOD OHLCV, generate exportable/research tickets, and optionally export/validate automatically.
references/pipeline_if_v1.mdCondensed integration contract for edge-finder-candidate/v1.
references/signal_mapping.mdMap hypothesis families to currently exportable signal families.
references/research_ticket_schema.mdTicket schema used by export_candidate.py.
references/ideation_loop.mdHint schema and external LLM ideation command contract.
Provides behavioral guidelines to reduce common LLM coding mistakes, focusing on simplicity, surgical changes, assumption surfacing, and verifiable success criteria.
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Creates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.
npx claudepluginhub pasie15/claude-trading-skills-marketplace --plugin trading-strategy-tools