backtesting-frameworks

Files (2)

• SKILL.md
• sandbase-api-map.md · references/

SKILL.md (first lines)

# Backtesting Frameworks

Use this Skill to produce a bounded, verifiable Backtesting Frameworks outcome. Preserve the user's chosen stack, source material, and authorization boundaries.

Read [the SandBase API map](references/sandbase-api-map.md) only when the task genuinely needs an external data source or generative model.

## Workflow

1. Inspect the available files, runtime, versions, inputs, and existing conventions before deciding what to change.
2. Restate the requested outcome, constraints, acceptance checks, and any assumption that could change the result.
3. Produce the smallest complete implementation, analysis, or artifact that satisfies those checks.
4. Verify the real output with appropriate tests, previews, calculations, or source comparison; do not infer success from file creation alone.
5. Return the deliverable, evidence of validation, material assumptions, and unresolved limitations.

## Quality gates

- Inspect shapes, types, units, missing values, sampling, target leakage, and train/test boundaries before modeling or transformation.
- Pin or record relevant library versions, random seeds, parameters, and environment assumptions for reproducibility.
- Validate against a baseline or independent calculation and report diagnostics, uncertainty, failure modes, and resource use.
- Use user-provided or authorized data, preserve an audit trail, verify calculations independently, and label professional-review requirements; do not present the result as investment, accounting, or audit assurance.
- Control look-ahead bias, survivorship bias, transaction costs, benchmark choice, and time alignment; keep hypothetical results clearly labeled.

## SandBase boundary

Keep the core Backtesting Frameworks work local. Use SandBase only for an explicitly requested external dataset or model inference step that is not part of the local analysis.

1. Call `sandbase_discover` with a short capability query.
2. Call `sandbase_inspect` for viable candidates and compare the live schema, coverage, limits, output, execution mode, and price.
3. Prefer a dedicated tool or API the user already has. Send only the minimum necessary data.
4. Before any paid call, show the endpoint, important arguments, current unit price, call count, and total estimate or uncertainty, then obtain confirmation.
5. Use `sandbase_account` before an approved multi-call batch and call `sandbase_run` only with current schema-defined arguments.
6. Poll asynchronous work with `sandbase_run_get` using the same run ID; never resubmit merely because it is pending.
7. Use `sandbase_runs` only to recover status or reconcile observed cost.

If SandBase is unavailable, continue with local work and authorized sources when possible. Do not silently switch providers, fabricate external results, or claim a generation or retrieval succeeded.

## Handoff

Provide the completed artifact or findings, concise reproduction steps, checks actually run, source or asset provenance, SandBase endpoint and run IDs when used, observed cost when available, and any follow-up that still requires user action.

From sandbaseai/sandbase-skills, Apache-2.0.

More from sandbaseai/sandbase-skills