CtrlK
BlogDocsLog inGet started
Tessl Logo

app-coding-standards

Provides coding standards for the Expensify App's React Native code, including performance patterns, consistency rules, and clean React architecture. Use when writing, modifying, or reviewing App code.

68

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

78%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 well-structured, token-efficient index document that practices strong progressive disclosure by pointing one level deep to per-rule files. Its weakness is actionability: the body itself offers navigation rather than executable guidance, relying on the linked rule files for the concrete detail.

Suggestions

Add a brief inline 'how to pick the right rule' heuristic or one short worked example so the body is actionable without forcing a file open for every decision.

Make the 'During review' path self-contained instead of deferring entirely to .claude/agents/code-inline-reviewer.md, which may not exist in every checkout.

Confirm the rules/*.md files referenced in the quick-reference list actually exist in the bundle, since none were present in this evaluation directory.

DimensionReasoningScore

Conciseness

The body is a lean index — a category table and one-line rule links — with no padding and no explanation of concepts Claude already knows; every line earns its place.

5 / 5

Actionability

Concrete per-rule links and a category-to-prefix table give navigable pointers, but the body's own guidance ('consult the relevant standard files') is high-level and contains no inline executable code or commands; the actionable detail lives entirely in the linked files.

3 / 5

Workflow Clarity

Two clearly labeled usage scenarios (During development / During review) frame a single-purpose lookup skill whose action — find the relevant rule file via the table — is unambiguous; no validation checkpoints are needed for a non-destructive index, with only minor gaps (the review path defers to an external agent file).

4 / 5

Progressive Disclosure

Exemplary progressive disclosure: a concise overview with a category table and well-signaled, one-level-deep references to rules/*.md files, making navigation easy. (No bundle files were present in the evaluation directory to verify the referenced paths resolve.)

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 strong, third-person description that clearly states what the skill provides and when to use it, with concrete trigger phrases and a well-scoped niche. The only gap is slightly uneven category coverage (UI is omitted from the description though present in the body).

DimensionReasoningScore

Specificity

Names the domain (Expensify App React Native code) and lists several specific coverage areas — 'performance patterns, consistency rules, and clean React architecture' — but omits the UI category shown in the body, leaving minor gaps.

4 / 5

Completeness

Explicitly answers both 'what' ('Provides coding standards... including performance patterns, consistency rules, and clean React architecture') and 'when' ('Use when writing, modifying, or reviewing App code') with concrete trigger phrases.

5 / 5

Trigger Term Quality

'writing, modifying, or reviewing App code' are natural phrases a user would say; good keyword coverage, though a few synonyms or variations (e.g. 'reviewing PRs', 'refactoring') are missing.

4 / 5

Distinctiveness Conflict Risk

Highly niche — scoped to the Expensify App's React Native code — with distinct triggers and minimal risk of firing for unrelated skills.

5 / 5

Total

18

/

20

Passed

Validation

87%

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

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

relative_links

Relative link issues: 48 missing

Warning

Total

14

/

16

Passed

Repository
Expensify/App
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.