CtrlK
BlogDocsLog inGet started
Tessl Logo

api-patterns

API design principles and decision-making. REST vs GraphQL vs tRPC selection, response formats, versioning, pagination.

57

1.14x
Quality

37%

Does it follow best practices?

Impact

92%

1.14x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./plugins/antigravity-awesome-skills-claude/skills/api-patterns/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

27%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This skill is essentially a table of contents and navigation document that references 10+ supporting files, none of which are provided in the bundle. Without those files, the skill delivers almost no actionable content—just a checklist of considerations and a list of basic anti-patterns that Claude already knows. The structure and organization show good intent, but the skill body alone provides minimal value.

Suggestions

Provide the referenced bundle files (api-style.md, rest.md, response.md, etc.) or inline the most critical content—at minimum, the API style decision tree and response format examples should be directly in SKILL.md.

Add concrete, executable examples: show a sample REST endpoint design, a response envelope JSON schema, or a GraphQL schema snippet directly in the skill body.

Replace the generic anti-patterns list with specific before/after code examples (e.g., show a bad endpoint vs. a good one with actual code).

Remove the boilerplate 'When to Use' and 'Limitations' sections which add no skill-specific value.

DimensionReasoningScore

Conciseness

The content is mostly efficient with a clean table-based content map, but includes some unnecessary filler like the motivational tagline 'Learn to THINK, not copy fixed patterns', the boilerplate 'When to Use' and 'Limitations' sections that add little value, and the anti-patterns section states things Claude already knows (e.g., don't use verbs in REST endpoints).

2 / 3

Actionability

The skill body contains no concrete code, no executable examples, no specific API designs, and no actual implementation guidance. It is entirely a navigation document with checklists and references to other files, but since no bundle files are provided, there is zero actionable content available. The anti-patterns and checklist are vague guidance rather than concrete instructions.

1 / 3

Workflow Clarity

The decision checklist provides a reasonable sequence of considerations before designing an API, but there are no validation checkpoints, no feedback loops, and no clear step-by-step workflow for actually designing or implementing an API. The checklist is more of a pre-flight check than a workflow.

2 / 3

Progressive Disclosure

The content map references 10 separate files (api-style.md, rest.md, response.md, etc.) and related skills, but NO bundle files are provided. This means every reference is a dead link, making the skill essentially an empty shell. The structure would be good if the files existed, but without them the progressive disclosure fails entirely.

1 / 3

Total

6

/

12

Passed

Description

47%

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 provides good keyword coverage for API design topics and names specific technologies, which aids discoverability. However, it lacks action verbs describing concrete capabilities and entirely omits a 'Use when...' clause, making it unclear when Claude should select this skill over others. Converting the topic list into explicit actions and adding trigger guidance would significantly improve it.

Suggestions

Add a 'Use when...' clause, e.g., 'Use when the user asks about choosing between REST, GraphQL, or tRPC, designing API endpoints, or deciding on pagination or versioning strategies.'

Replace topic nouns with concrete action phrases, e.g., 'Guides selection between REST, GraphQL, and tRPC; designs response formats; recommends versioning and pagination strategies.'

Consider adding common user phrasings like 'API architecture', 'endpoint design', 'which API style', or 'API best practices' to improve trigger term coverage.

DimensionReasoningScore

Specificity

Names the domain (API design) and lists several specific topics (REST vs GraphQL vs tRPC selection, response formats, versioning, pagination), but these read more like topic areas than concrete actions. No action verbs like 'design', 'evaluate', or 'implement' are used.

2 / 3

Completeness

Describes 'what' at a topic level but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. Per rubric guidelines, a missing 'Use when...' clause caps completeness at 2, and the 'what' is also weak (topics rather than actions), warranting a 1.

1 / 3

Trigger Term Quality

Includes strong natural keywords users would say: 'API design', 'REST', 'GraphQL', 'tRPC', 'versioning', 'pagination', 'response formats'. These are terms developers naturally use when seeking API design guidance.

3 / 3

Distinctiveness Conflict Risk

The mention of specific technologies (REST, GraphQL, tRPC) and specific concerns (versioning, pagination) provides some distinctiveness, but 'API design principles' is broad enough to potentially overlap with general backend development or architecture skills.

2 / 3

Total

8

/

12

Passed

Validation

90%

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

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

Total

10

/

11

Passed

Repository
sickn33/antigravity-awesome-skills
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.