type-check

运行 TypeScript 类型检查

Quality

74%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/type-check/SKILL.md

Quality

Content

100%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.

The content is a model of a lean single-purpose skill: one clear, executable command with no padding and no unnecessary structure, fully appropriate for its scope.

Dimension	Reasoning	Score
Conciseness	The body is a single heading, one orienting sentence, and the exact command — lean with no padding or over-explanation of concepts Claude already knows, matching the "every token earns its place" anchor.	5 / 5
Actionability	It provides a fully executable, copy-paste-ready command (`pnpm --filter @graphif/project-graph type-check`) that directly performs the task, matching the "fully executable; copy-paste ready commands" anchor.	5 / 5
Workflow Clarity	This is a simple, single-purpose, non-destructive skill under 50 lines whose single action is unambiguous, so per the simple-skills note workflow clarity scores 5; no validation checkpoint is required for a read-only type check.	5 / 5
Progressive Disclosure	The skill is under 50 lines with no need for external references and is well-organized with a heading and command block, so per the simple-skills note progressive disclosure scores 5 with just well-organized sections.	5 / 5
	Total	20 / 20 Passed

Description

48%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.

The description is concise and names a specific, distinct capability, but it is too terse: it states only a generic action and omits any explicit "Use when" trigger guidance, which caps completeness and lowers trigger-term coverage.

Suggestions

Add an explicit trigger clause, e.g. "运行 TypeScript 类型检查。Use when the user asks to type-check, verify types, or fix type errors in the project."

Enrich trigger terms with natural synonyms users say, such as "type check", "tsc", and "type errors".

Specify the concrete action more precisely (e.g. "Runs the project's TypeScript type-check via pnpm and reports type errors") to lift specificity above a single generic verb.

Dimension	Reasoning	Score
Specificity	The phrase "运行 TypeScript 类型检查" names the domain (TypeScript type checking) but the only action is the generic verb "运行" (run), matching the anchor for naming the domain with minimal or generic actions; it does not reach level 3 because there are not 1-2 distinct concrete actions enumerated.	2 / 5
Completeness	It gives a clear "what" (runs TypeScript type checking) but provides no "Use when..." clause or equivalent trigger guidance, so per the rubric guideline completeness is capped at 3 for a clear what with missing when.	3 / 5
Trigger Term Quality	It contains relevant keywords ("TypeScript", "类型检查"/type checking) a user might say, but it misses common variations and synonyms such as "type check", "tsc", or "type errors", matching the "some relevant keywords but missing common variations" anchor.	3 / 5
Distinctiveness Conflict Risk	It targets a clear, specific niche (TypeScript type checking) with minimal conflict risk, though it could overlap slightly with general lint/build skills, placing it at "mostly distinct; minor overlap risk" rather than the fully distinct level 5.	4 / 5
	Total	12 / 20 Passed

Validation

93%

Warnings & errors only

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

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
description_field	'description' is very short (18 chars), consider making it more detailed	Warning

	Total	15 / 16 Passed

Repository: graphif/project-graph
Path: .agents/skills/type-check/SKILL.md
Commit: f187e86

Reviewed: 5 days ago

Table of Contents

Discovery Implementation Validation

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.