CtrlK
BlogDocsLog inGet started
Tessl Logo

xberg-typescript-toolchain

Work on Xberg TypeScript or JavaScript packages with the repository's actual poly, pnpm, npm, Vitest, napi-rs, wasm-pack, and integration-package boundaries. Load for TS/JS tooling or package changes, not Rust-only binding generation.

69

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

80%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A tight, high-signal reference skill that conveys repo-specific toolchain rules efficiently. Its main gap is the absence of an explicit, sequenced change workflow with validation checkpoints for dependency and package operations.

Suggestions

Add a short sequenced 'Making a change' workflow (e.g. poly fmt . -> typecheck -> vitest -> verify dependency ownership) with an explicit validation step before committing dependency changes.

Include one worked example showing a representative TS/JS package change end-to-end so the scattered directives anchor to a concrete procedure.

Surface a quick verification step (e.g. 'Confirm the changed package is in the root tsconfig project references before trusting a root typecheck') as a labeled checkpoint.

DimensionReasoningScore

Conciseness

Lean, repository-specific facts that assume Claude's competence; no padding or explanation of what TypeScript, Vitest, or pnpm are, and every bullet earns its place.

5 / 5

Actionability

Provides concrete commands ('poly lint .', 'poly fmt .') and specific paths (tsconfig.json, integrations/node/), but the directives are scattered constraints rather than a single copy-paste-ready example covering a common change.

4 / 5

Workflow Clarity

The bullets imply a change workflow (lint/fmt, typecheck, test, dependency ownership) but steps are not sequenced and there is no validation checkpoint; dependency/package changes are batch/destructive-ish, which caps this dimension at 3.

3 / 5

Progressive Disclosure

Under 50 lines with no need for external references, organized as a clear titled list of well-grouped bullets, which satisfies the simple-skill exception for progressive disclosure.

5 / 5

Total

17

/

20

Passed

Description

87%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A highly specific, well-scoped description that clearly states both capability and trigger conditions with an explicit boundary. The only weakness is slightly generic action verbs and a few missing natural synonyms.

DimensionReasoningScore

Specificity

Names concrete tooling (poly, pnpm, npm, Vitest, napi-rs, wasm-pack) and integration-package boundaries rather than vague actions, though the primary verb 'Work on' is somewhat generic.

4 / 5

Completeness

Explicitly answers what ('Work on Xberg TypeScript or JavaScript packages with...') and when ('Load for TS/JS tooling or package changes, not Rust-only binding generation') with a concrete negative trigger.

5 / 5

Trigger Term Quality

Includes natural developer phrases like 'TS/JS tooling or package changes', but misses common synonyms such as 'frontend' or 'npm packages'.

4 / 5

Distinctiveness Conflict Risk

Targets a repo-specific Xberg toolchain niche with distinct triggers and an explicit exclusion ('not Rust-only binding generation'), minimizing conflict with other skills.

5 / 5

Total

18

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
xberg-io/xberg
Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.