CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

lint-new

Create a new ESLint rule with tests for eslintPluginScraps. Use when asked to "create a lint rule", "add an eslint rule", "scaffold a rule", "write a new scraps rule", or "new design system lint rule". Covers rule creation, test authoring, registration, and autofix implementation.

86

1.28x
Quality

97%

Does it follow best practices?

Impact

54%

1.28x

2 of 3 eval scenarios. Add 1 more for a full score.

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

93%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.

An exemplary skill body for a code-scaffolding task: dense, project-specific, and fully executable, with details correctly pushed into three conditionally-loaded reference files. The only weakness is that the two verification steps don't include an explicit fix-and-retry loop, leaving workflow clarity just short of the top anchor.

DimensionReasoningScore

Conciseness

The body is lean and assumes competence: no explanation of what ESLint or ASTs are, just decision tables, file paths, and templates. Every section adds information Claude cannot infer (shared utility locations, plugin registration specifics, autofix policy), matching the 5-anchor 'every token earns its place'. It does not fit the 4-anchor because there is no over-explanatory padding to trim.

5 / 5

Actionability

Fully executable guidance throughout: exact file paths for rule and spec files, copy-paste TypeScript rule/test templates, concrete test commands ('pnpm test-ci "static/oxlint/eslintPluginScraps/src/rules/$ARGUMENTS.spec.ts"'), registration snippets for both the rules index and eslint.config.ts, and explicit naming conventions. Not a 4: there are no minor gaps — the common cases (no-options rule, fixable rule) are covered end to end.

5 / 5

Workflow Clarity

Clear four-step sequence (choose archetype → check utilities → create files → register) with explicit validation checkpoints (run the test command after creating the rule and again after registration). It falls short of the 5-anchor because feedback loops for error recovery ('if tests fail, fix and re-run') are not spelled out — verification is present but the retry path is implicit. Above the 3-anchor since checkpoints are explicit, not missing.

4 / 5

Progressive Disclosure

Clean overview-plus-references structure: the archetype table routes to the right reference conditionally, schema-patterns.md is loaded only 'if your rule needs configurable options', and all three referenced files exist and are one level deep with clear 'load this reference when' signaling. Matches the 5-anchor; the body keeps only templates and decisions inline while detail lives in references. Not a 4: navigation and placement are unambiguous.

5 / 5

Total

19

/

20

Passed

Description

100%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 model description: concrete multi-action 'what', an explicit 'use when' clause with five natural trigger phrases, third-person imperative voice, and a well-bounded niche tied to a named plugin. No fluff, no over-claims, and every capability listed is verifiable against the skill body.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions — 'Create a new ESLint rule with tests', 'rule creation, test authoring, registration, and autofix implementation' — giving comprehensive coverage of the skill's capabilities with no vague filler. It clearly matches the 5-anchor ('lists multiple specific concrete actions; comprehensive coverage') and is not the 4-anchor because there are no minor coverage gaps.

5 / 5

Completeness

Both questions are answered explicitly: what ('Covers rule creation, test authoring, registration, and autofix implementation') and when ('Use when asked to...') with concrete trigger phrases. This mirrors the 5-anchor example structure exactly; the 'when' clause is present and explicit, so it cannot be a 3, and nothing is vague so it is not a 4.

5 / 5

Trigger Term Quality

It enumerates five natural trigger phrases users would actually say: 'create a lint rule', 'add an eslint rule', 'scaffold a rule', 'write a new scraps rule', 'new design system lint rule' — covering synonyms and domain variations comprehensively. Not a 4: no common natural phrasing for this task is missing.

5 / 5

Distinctiveness Conflict Risk

The description names a clear niche — a specific plugin ('eslintPluginScraps') and design-system lint rules — with distinct trigger phrases, so it is unlikely to fire for unrelated skills. 'scaffold a rule' is slightly generic but is anchored by the plugin and lint context, keeping conflict risk minimal (5-anchor), rather than the 4-anchor's 'minor overlap risk'.

5 / 5

Total

20

/

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

getsentry/sentry

Path

.agents/skills/lint-new/SKILL.md

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.