CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

91

1.18x
Quality

Does it follow best practices?

Impact

91%

1.18x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

77%

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

A high-quality, actionable engineering standards skill with executable examples and a validated multi-step workflow, weakened only by its length, some cross-section repetition, and the absence of any progressive disclosure into bundle files.

Suggestions

Consolidate the repeated 'parse/validate at the boundary' guidance into one canonical section and cross-reference it, rather than restating it in Ownership, Runtime Boundaries, and Async.

Move the detailed code examples (typed outcome, Zod schemas, config parsing, UI state machine) into a references/ file (e.g., EXAMPLES.md) and link to it from SKILL.md to reduce inline length and add one-level-deep progressive disclosure.

Extract the 'Review Mindset' checklist and review-output guidance into a separate references/REVIEW.md, keeping SKILL.md as a concise overview that points to it.

DimensionReasoningScore

Conciseness

The body is almost entirely dense prescriptive rules with no basic-concept filler, but at ~400 lines it restates the parse-at-the-boundary principle across Ownership, Runtime Boundaries, and Async sections, so it is mostly efficient yet could be tightened — not 'every token earns its place.'

2 / 3

Actionability

Provides concrete directive rules plus four fully executable examples (typed CreateUserOutcome, Zod webhook parsing, loadConfig, SubmitState UI switch), giving copy-paste-ready, specific guidance rather than vague direction.

3 / 3

Workflow Clarity

The 'How To Use This Skill' section is a clear 5-step sequence with an explicit validation checkpoint — "If any check fails, fix the failure before considering the change complete" — and the 'Review Mindset' section is a checklist with feedback/recovery framing.

3 / 3

Progressive Disclosure

Sections are well-organized with clear headers, but no references/, scripts/, or assets/ bundle files exist and all ~400 lines live inline in SKILL.md; content that could be offloaded (e.g., the full review checklist or example catalog) is inline, matching the 'structure present but content that should be separate is inline' anchor.

2 / 3

Total

10

/

12

Passed

Description

100%

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

The description is specific, uses natural trigger terms, and explicitly states both capability and invocation conditions, including the implicit-trigger guidance for TypeScript-based projects. It avoids first/second-person voice and over-claims.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "write, edit, review, refactor, debug, or design TypeScript or TSX code" — matching the anchor for listing several specific actions rather than vague language.

3 / 3

Completeness

Answers both what (the enumerated actions) and when, with explicit triggers "Use this skill whenever the user asks..." and "Apply it even when the user does not explicitly mention 'TypeScript' if the files or project are TypeScript-based."

3 / 3

Trigger Term Quality

Covers natural terms a user would say (TypeScript, TSX, React/UI, schemas, lint/typecheck fixes, code review); not jargon-only and not over-generic, so it sits above the "some relevant keywords" anchor.

3 / 3

Distinctiveness Conflict Risk

Scoped tightly to TypeScript/TSX with distinct triggers, making it unlikely to fire for unrelated skills; clearly a clear niche rather than a 'somewhat specific' overlap.

3 / 3

Total

12

/

12

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
idrevnii/perks
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.