api-patterns

Connect Query patterns for API calls. Use when working with mutations, queries, or data fetching.

1.15x

Quality

67%

Does it follow best practices?

Impact

97%

1.15x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./frontend/.claude/skills/api-patterns/SKILL.md

Quality

Content

65%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-organized, token-efficient overview that routes the reader to detail files, but its references are dangling (no bundle files exist) and it offers no inline executable example or validation step for its mutation/cache workflows.

Suggestions

Ship the referenced bundle files (rules/, use-connect-query.md, api-invalidate-cache.md, api-toast-errors.md, protobuf-no-edit.md) so the routing table resolves to real content.

Add one short inline code example for the canonical fetch-mutate-invalidate flow so the skill is actionable without the bundle.

Include an explicit validation/checkpoint step after cache invalidation or proto regeneration (e.g., verify the cache refreshed or the build passes) to lift workflow clarity above 3.

Dimension	Reasoning	Score
Conciseness	The body is lean with zero padding: a one-line intro, a routing table, key locations, and a single regenerate command — every token earns its place and it assumes Claude's competence.	5 / 5
Actionability	It routes actions to specific files and gives one concrete command (`task proto:generate`), but the actual executable API-call guidance is deferred to referenced files and no code example is inline, leaving key details missing.	3 / 5
Workflow Clarity	The quick-reference table implies a fetch → mutate → invalidate → handle-errors flow but presents no explicit sequenced workflow, and operations like cache invalidation and proto regeneration lack validation checkpoints, capping it at 3.	3 / 5
Progressive Disclosure	Structure and signaling are good (a routing table mapping actions to files plus a rules/ pointer), but the referenced files (use-connect-query.md, api-invalidate-cache.md, api-toast-errors.md, protobuf-no-edit.md, rules/) do not exist in the bundle, so navigation cannot actually resolve.	3 / 5
	Total	14 / 20 Passed

Description

70%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 concise, third-person description with an explicit 'Use when' trigger and relevant natural keywords. It is specific to the Connect Query niche but could enumerate more concrete actions to lift specificity and completeness.

Suggestions

List 2-3 concrete actions (e.g., 'invalidate query caches, wire optimistic mutations, surface protobuf errors as toasts') to raise specificity and completeness.

Add common synonyms or phrasings users might say (e.g., 'TanStack Connect Query', 'RPC hooks') to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	It names the domain ("Connect Query patterns for API calls") and concrete sub-tasks ("mutations, queries, or data fetching"), but does not enumerate several specific actions, so it sits at the 'names domain and 1-2 concrete actions' anchor rather than 4.	3 / 5
Completeness	It answers both what ("Connect Query patterns for API calls") and when ("Use when working with mutations, queries, or data fetching") with an explicit trigger clause, but the 'what' is thin enough that it doesn't fully reach the concrete, comprehensive bar of 5.	4 / 5
Trigger Term Quality	"mutations, queries, or data fetching" are natural terms developers say with Connect Query, giving good keyword coverage; it stops short of the comprehensive synonym/extension coverage of a 5.	4 / 5
Distinctiveness Conflict Risk	"Connect Query" pins a specific framework niche, keeping conflict risk low, but the broad triggers (queries, mutations, data fetching) leave minor overlap with general data-fetching skills, so it is 'mostly distinct' rather than fully clear-cut.	4 / 5
	Total	15 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: redpanda-data/console
Path: frontend/.claude/skills/api-patterns/SKILL.md
Commit: 2deda0a

Reviewed: 2 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.