tradermonty/claude-trading-skills

edge-pipeline-orchestrator

Orchestrate the full edge research pipeline from candidate detection through strategy design, review, revision, and export.

Quelltext ansehen

Verwendung

  1. Installationsbefehl kopieren und das Quellpaket vor der Installation in der eigenen Agentenumgebung prüfen.
  2. Benötigte Werkzeuge, Zugangsdaten und Hosts im Original prüfen.
  3. Eingabe und gewünschtes Ergebnis beschreiben und die Ausgabe mit den Quellen abgleichen.
npx skills add https://github.com/tradermonty/claude-trading-skills --skill edge-pipeline-orchestrator

Vor dem Start

  • Die Installation umfasst weder Modellabo noch API-Kontingent oder Dateizugriffsrechte.
  • Sterne und Installationen zeigen Aktivität, keine unabhängige Qualitäts- oder Sicherheitsprüfung.
Originales Skill-Dokument

Aus dem Quell-Repository gerendert; Überschriften, Beispiele, Code, Tabellen, Links und Bilder bleiben erhalten.

Edge Pipeline Orchestrator

Coordinate all edge research stages into a single automated pipeline run.

When to Use

  • Run the full edge pipeline from tickets (or OHLCV) to exported strategies
  • Resume a partially completed pipeline from the drafts stage
  • Review and revise existing strategy drafts with feedback loop
  • Dry-run the pipeline to preview results without exporting

Prerequisites

  • API keys: None required. The orchestrator runs the edge pipeline subskills through subprocess calls.
  • Sibling skills: The orchestrator resolves skills/edge-candidate-agent, skills/edge-hint-extractor, skills/edge-concept-synthesizer, skills/edge-strategy-designer and skills/edge-strategy-reviewer by repository path. Install or check out all of them together; a standalone install of this skill alone will not run.
  • Python: 3.9+ with PyYAML>=6.0 (see requirements.txt).
  • Inputs: A tickets directory, an OHLCV CSV for --from-ohlcv, or an existing drafts directory, depending on the mode shown under CLI Usage.

Workflow

  1. Load pipeline configuration from CLI arguments
  2. Run auto_detect stage if --from-ohlcv is provided (generates tickets from raw OHLCV data)
  3. Run hints stage to extract edge hints from market summary and anomalies
  4. Run concepts stage to synthesize abstract edge concepts from tickets and hints
  5. Run drafts stage to design strategy drafts from concepts
  6. Run review-revision feedback loop:
  • Review all drafts (max 2 iterations)
  • PASS verdicts accumulated; REJECT verdicts accumulated
  • REVISE verdicts trigger apply_revisions and re-review
  • Remaining REVISE after max iterations downgraded to research_probe
  1. Export eligible drafts (PASS + exportreadyv1 + exportable entry_family)
  2. Write pipelinerunmanifest.json with full execution trace

CLI Usage

bash
# Full pipeline from tickets
python3 scripts/orchestrate_edge_pipeline.py \
  --tickets-dir path/to/tickets/ \
  --output-dir reports/edge_pipeline/

# Full pipeline from OHLCV
python3 scripts/orchestrate_edge_pipeline.py \
  --from-ohlcv path/to/ohlcv.csv \
  --output-dir reports/edge_pipeline/

# Resume from drafts stage
python3 scripts/orchestrate_edge_pipeline.py \
  --resume-from drafts \
  --drafts-dir path/to/drafts/ \
  --output-dir reports/edge_pipeline/

# Review-only mode
python3 scripts/orchestrate_edge_pipeline.py \
  --review-only \
  --drafts-dir path/to/drafts/ \
  --output-dir reports/edge_pipeline/

# Dry run (no export)
python3 scripts/orchestrate_edge_pipeline.py \
  --tickets-dir path/to/tickets/ \
  --output-dir reports/edge_pipeline/ \
  --dry-run

Output

All artifacts are written to --output-dir:

output-dir/
├── pipeline_run_manifest.json
├── tickets/          (from auto_detect)
├── hints/hints.yaml  (from hints)
├── concepts/edge_concepts.yaml
├── drafts/*.yaml
├── exportable_tickets/*.yaml
├── reviews_iter_0/*.yaml
├── reviews_iter_1/*.yaml  (if needed)
└── strategies/<candidate_id>/
    ├── strategy.yaml
    └── metadata.json

Claude Code LLM-Augmented Workflow

Run the LLM-augmented pipeline entirely within Claude Code:

  1. Run autodetect to produce `marketsummary.json + anomalies.json`
  2. Claude Code analyzes data and generates edge hints
  3. Save hints to a YAML file:
yaml
- title: Sector rotation into industrials
  observation: Tech underperforming while industrials show relative strength
  symbols: [CAT, DE, GE]
  regime_bias: Neutral
  mechanism_tag: flow
  preferred_entry_family: pivot_breakout
  hypothesis_type: sector_x_stock
  1. Run orchestrator with --llm-ideas-file and --promote-hints:
bash
python3 scripts/orchestrate_edge_pipeline.py \
  --tickets-dir path/to/tickets/ \
  --llm-ideas-file llm_hints.yaml \
  --promote-hints \
  --as-of 2026-02-28 \
  --max-synthetic-ratio 1.5 \
  --strict-export \
  --output-dir reports/edge_pipeline/

Optional Flags

  • --as-of YYYY-MM-DD — forwarded to hints stage for date filtering
  • --strict-export — export-eligible drafts with any warn finding get REVISE instead of PASS
  • --max-synthetic-ratio N — cap synthetic tickets to N × real ticket count (floor: 3)
  • --overlap-threshold F — condition overlap threshold for concept deduplication (default: 0.75)
  • --no-dedup — disable concept deduplication

Note: --llm-ideas-file and --promote-hints are effective only during full pipeline runs. --resume-from drafts and --review-only skip hints/concepts stages, so these flags are ignored.

Resources

  • references/pipeline_flow.md — Pipeline stages, data contracts, and architecture
  • references/revision_loop_rules.md — Review-revision feedback loop rules and heuristics
aus demselben Repository

Weitere Skills

Alle Skills
tradermonty
Community

crypto-regime-analyzer

Quantifies crypto market regime health using free, keyless public data (CoinGecko + Binance funding). Generates a 0-100 composite score across 6 components (100 = risk-on) with a posture recommendation. No API key required. Use when user asks about crypto market conditions, whether it's alt season, BTC dominance, crypto risk-on vs risk-off, funding rates, or whether crypto exposure should be increased or reduced.

Installationen / 1h
4
GitHub Stars
5327
Aktualisiert
15. Nov.
tradermonty
Community

drawdown-circuit-breaker

Evaluate account-level drawdown circuit breaker rules from trader-memory-core state and decide whether new trade risk is allowed today. Uses realized P&L, losing-streak cooldowns, and weekly/monthly drawdown limits without any external API.

Installationen / 1h
3
GitHub Stars
5327
Aktualisiert
15. Nov.
tradermonty
Community

edge-strategy-designer

Convert abstract edge concepts into strategy draft variants and optional exportable ticket YAMLs for edge-candidate-agent export/validation.

Installationen / 1h
3
GitHub Stars
5327
Aktualisiert
15. Nov.
tradermonty
Community

edge-strategy-reviewer

Critically review strategy drafts from edge-strategy-designer for edge plausibility, overfitting risk, sample size adequacy, and execution realism. Use when strategydrafts/.yaml exists and needs quality gate before pipeline export. Outputs PASS/REVISE/REJECT verdicts with confidence scores.

Installationen / 1h
3
GitHub Stars
5327
Aktualisiert
15. Nov.