CtrlK
BlogDocsLog inGet started
Tessl Logo

base/typescript-engineering

Use this skill whenever the user asks you to write, edit, review, refactor, debug, or design TypeScript or TSX code. It is especially relevant for application code, backend routes, React/UI work, schemas, runtime boundaries, persistence, async workflows, API contracts, tests, lint/typecheck fixes, and code review. Apply it even when the user does not explicitly mention "TypeScript" if the files or project are TypeScript-based.

89

1.26x
Quality

85%

Does it follow best practices?

Impact

95%

1.26x

Average score across 5 eval scenarios

SecuritybySnyk

Passed

No known issues

Overview
Quality
Evals
Security
Files

Evaluation results

94%

5%

Harden The Order Webhook

Criteria
Without context
With context

Existing conventions

100%

100%

Boundary schema

90%

100%

Parse once

100%

100%

Unknown narrowed

100%

100%

Null normalized

100%

75%

Thin route

62%

100%

Typed outcomes

100%

100%

Secure query

100%

100%

Auth nearby

87%

100%

Domain constants

0%

50%

Focused tests

100%

90%

Check evidence

100%

100%

95%

-1%

Stabilize Bulk Invites

Criteria
Without context
With context

Small state

100%

100%

Async union

100%

100%

Exhaustive render

75%

75%

Feature logic

100%

100%

Small handlers

100%

100%

State separation

100%

100%

No mirror

100%

100%

Semantic controls

75%

87%

Optional absence

100%

100%

Named exports

100%

83%

UI tests

100%

91%

No new package

100%

100%

96%

13%

Repair Customer Import History

Criteria
Without context
With context

Shape separation

90%

100%

No giant type

100%

100%

Schema source

100%

100%

Boundary transforms

87%

100%

Null handling

75%

100%

Version metadata

100%

100%

Append history

100%

100%

Migration path

12%

50%

Stable ordering

87%

100%

Readonly snapshots

33%

100%

Focused tests

90%

100%

No leakage

100%

100%

94%

8%

Make Shipment Sync Reliable

Criteria
Without context
With context

Visible effects

87%

100%

Explicit deps

75%

100%

No global state

100%

100%

Handled promises

100%

100%

Abort timeout

90%

100%

Retry policy

80%

80%

Typed outcomes

100%

100%

Error context

100%

75%

Safe concurrency

100%

100%

Bounded work

25%

75%

Deterministic tests

80%

100%

No Result sprawl

100%

100%

99%

11%

Review A TypeScript Pull Request

Criteria
Without context
With context

Findings first

100%

100%

Behavior focus

91%

100%

Line grounded

100%

100%

Boundary validation

90%

100%

Contract risk

87%

100%

Async risk

100%

100%

Type soundness

87%

100%

Security risk

100%

100%

Test gap

25%

100%

Severity order

100%

100%

No style nitpick

83%

83%

Open questions

90%

100%

Evaluated
Agent
Claude
Model
Claude Sonnet 4.6

Table of Contents