Grammar Check

---
name: grammar-check
description: "Create or review grammar check deliverables with audience, evidence, voice, and conversion-quality controls. Use when the user explicitly asks for grammar check work."
---

# Grammar Check

Use this Skill to produce a bounded, verifiable Grammar Check 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

- Define the audience, desired action, channel, voice, claims, and evidence standard before drafting.
- Separate verified facts from interpretation and recommendation; never fabricate citations, testimonials, or performance claims.
- Revise for structure, specificity, consistency, and accessibility while preserving the user's intended meaning and brand constraints.

## Focus checks

- Identify each grammar, logic, or flow issue with a targeted correction; do not rewrite the whole text or flatten intentional voice unless the user asks.

## SandBase boundary

Keep the core Grammar Check work local. Use SandBase only for current external evidence, search, scraping, enrichment, or model inference that is not already available through the user's authorized tools.

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.