CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

no-explicit-any

Use when reviewing TypeScript files for type safety regressions, during code review of functions that handle external data, or when the codebase has ESLint warnings for @typescript-eslint/no-explicit-any.

Quality

69%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/no-explicit-any/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

72%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 body is a well-structured, efficient overview with a concrete decision framework for replacing any and exemplary progressive disclosure to a real, well-organized reference file. Its main gaps are the absence of any inline verification step in the body and no worked code example, both of which are deferred entirely to the reference file.

Suggestions

Add a brief verification step to the Fix section, e.g., 'After fixing, run tsc --noEmit and re-run ESLint to confirm no no-explicit-any warnings remain', rather than leaving verification only in the reference file.

Include one compact before/after inline example (any vs. unknown narrowing) so the replacement pattern is anchored without opening the reference.

Trim the intro paragraph's explanation of why any is unsafe, since that is a TypeScript concept Claude already knows.

DimensionReasoningScore

Conciseness

The body is a lean ~45 lines with terse, purposeful sections (Check/Fix/Explain/Code Review), but the intro paragraph ('a function returning any propagates unchecked types to every caller') and bullets like 'unknown is the safe alternative — it requires a type check before use' partially re-explain TypeScript basics Claude already knows. These are minor over-explanations that could be trimmed, matching anchor 4 rather than the fully lean anchor 5.

4 / 5

Actionability

Concrete decision guidance throughout: 'Replace the any types... with unknown (for values of unknown shape), appropriate generics (for type-consistent operations), or Zod validation (for external data)' and 'Flag every explicit or implicit any, any type assertion that lacks a preceding type guard'. As an instruction-only skill the guidance is specific and actionable, though no inline code example anchors the patterns (those are deferred to references/rule.md), so it stops short of anchor 5's copy-paste readiness.

4 / 5

Workflow Clarity

The four modes (Check/Fix/Explain/Code Review) are clearly delineated with unambiguous single actions, but the check-to-fix sequence is only implicit and there is no verification step in the body — verification lives solely in references/rule.md. Since fixing any types across a file is a batch code-modification without inline validation, this matches anchor 3 ('checkpoints missing or implicit') and the batch-operation cap holds it at 3.

3 / 5

Progressive Disclosure

The body is a well-organized overview (~45 lines, clear sections) that appropriately splits detail out of itself, ending with a clearly signaled one-level-deep reference: 'For full implementation details, code examples, and framework-specific guidance, see references/rule.md'. The referenced file exists, is well-structured with code examples and an ESLint config, and there is no nested-referencing indirection — matching anchor 5 exactly.

5 / 5

Total

16

/

20

Passed

Description

52%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 has strong, explicit trigger coverage and a distinctive niche anchored by the specific ESLint rule name, but it is entirely trigger-focused: it never states what the skill actually does (detecting and replacing any with unknown, generics, or type guards). Adding a leading capability statement would move it from anchor-level 'when-only' to the stronger what-plus-when pattern.

Suggestions

Prepend a capability statement, e.g., 'Flags and replaces explicit any with unknown, generics, or type guards, and explains the tradeoffs at each usage site.' before the 'Use when...' triggers.

Add natural trigger terms users would actually say, such as 'any type', 'explicit any', 'remove any', or 'type guards', to broaden keyword coverage.

Tighten the second trigger ('during code review of functions that handle external data') to reference type-related concerns, reducing overlap risk with general validation or sanitization skills.

DimensionReasoningScore

Specificity

The description names the domain concretely ('reviewing TypeScript files for type safety regressions', 'ESLint warnings for @typescript-eslint/no-explicit-any') giving 1-2 concrete action contexts, but it never states the skill's own capabilities (e.g., flagging or replacing any with unknown/generics/type guards), so coverage is not comprehensive. It sits between anchor 2 (minimal actions) and 4 (several specific actions listed), fitting anchor 3.

3 / 5

Completeness

It has three explicit 'Use when...' triggers but no statement of what the skill does — only 'when' is present without 'what', matching anchor 2's example pattern ('Use when working with documents'). It is not anchor 3 because there is no clear 'what', and not anchor 1 because the 'when' is explicit and specific rather than vague.

2 / 5

Trigger Term Quality

Includes natural terms users would say: 'TypeScript', 'type safety', 'code review', 'ESLint', and 'explicit any' (via the rule name). A few natural variations are missing, such as 'any type', 'fix any', 'type guards', or 'unknown', so it falls short of the comprehensive synonym coverage of anchor 5.

4 / 5

Distinctiveness Conflict Risk

The named ESLint rule '@typescript-eslint/no-explicit-any' is highly distinctive and creates a clear niche with minimal conflict risk, but the broader second trigger ('code review of functions that handle external data') could overlap with closely related validation/sanitization or general TypeScript review skills, matching 'mostly distinct; minor overlap risk' rather than anchor 5.

4 / 5

Total

13

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository

thedaviddias/Front-End-Checklist

Path

skills/no-explicit-any/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.