CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

api-patterns

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

53

Quality

67%

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 ./plugins/antigravity-bundle-full-stack-developer/skills/api-patterns/SKILL.md

The canonical home for this skill is api-patterns in sickn33/agentic-awesome-skills

SKILL.md
Quality
Evals
Security

Quality

Content

53%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-organized, concise overview with a genuinely good content-map design, but it is undermined by a broken bundle: all 10 promised reference files are missing, leaving the skill as an index of nonexistent content with only checklists and one script as real guidance. The workflow checklist also lacks validation checkpoints and follow-through steps.

Suggestions

Ship the 10 reference files listed in the content map (or trim the map to files that actually exist) — currently every 'When to Read' path is a dead link, which is the single biggest defect.

Replace the filler 'When to Use' section with either a concrete trigger statement or remove it entirely; 'This skill is applicable to execute the workflow or actions described in the overview' adds no information.

Add validation/follow-through to the decision workflow, e.g., after choosing an API style, verify against the consumer requirements gathered in step 1 and point to the specific reference file to execute the decision.

DimensionReasoningScore

Conciseness

The body is lean — tables, checklists, and short bullet lists with almost no explanation of concepts Claude already knows. Minor trimmable padding remains: the vacuous filler section 'When to Use: This skill is applicable to execute the workflow or actions described in the overview' and the meta tagline 'Learn to THINK, not copy fixed patterns', keeping it below 5.

4 / 5

Actionability

There is some concrete guidance — a decision checklist, specific anti-patterns like 'Use verbs in REST endpoints (/getUsers)', and the executable command 'python scripts/api_validator.py <project_path>' — but the actual instructions (decision tree, naming rules, error formats) live in reference files, so key executable detail is missing from what is actually available. It is not a 2 because the checklist, anti-patterns, and script command are specific and usable as far as they go.

3 / 5

Workflow Clarity

The 'Decision Checklist' provides a recognizable sequence (ask about consumers → choose style → define response format → plan versioning → consider auth → rate limiting → documentation), but there are no validation checkpoints or feedback loops, and no guidance on what to do after each step (e.g., which reference file to act on). This matches 'steps listed but checkpoints missing or implicit' rather than 4.

3 / 5

Progressive Disclosure

The content-map pattern is well-designed on paper (file, description, when-to-read columns plus a selective reading rule), but scoring against the actual bundle: none of the 10 referenced files (api-style.md, rest.md, response.md, graphql.md, trpc.md, versioning.md, auth.md, rate-limiting.md, documentation.md, security-testing.md) exist — no references/ directory is present at all, so every navigation path is broken and the detailed content is entirely unavailable. Only scripts/api_validator.py exists.

2 / 5

Total

12

/

20

Passed

Description

66%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 solid, domain-specific description with good concrete capability keywords, but it lacks any explicit 'when to use' trigger clause, capping completeness. Adding a 'Use when...' sentence with natural trigger phrases would lift it substantially.

Suggestions

Add an explicit trigger clause, e.g., 'Use when designing or reviewing an API, choosing between REST/GraphQL/tRPC, or planning versioning, pagination, or response formats.'

Include a few more natural synonyms users say, such as 'endpoints', 'OpenAPI/Swagger', or 'API auth', to broaden trigger coverage.

DimensionReasoningScore

Specificity

The description lists several specific capabilities — 'REST vs GraphQL vs tRPC selection, response formats, versioning, pagination' — going beyond the generic opener 'API design principles and decision-making'. It falls short of 5 because the concrete actions are topic names rather than actions, and coverage gaps exist (auth, rate limiting, documentation are handled by the skill but not mentioned).

4 / 5

Completeness

The 'what' is clear (API style selection, response formats, versioning, pagination), but there is no 'Use when...' clause or equivalent explicit trigger guidance — the 'when' is only weakly implied by the domain itself. Per the judging guidelines, a missing 'Use when...' clause caps completeness at 3; it is not a 4 because no situational trigger is stated at all.

3 / 5

Trigger Term Quality

Natural terms users would say are present: 'REST', 'GraphQL', 'tRPC', 'versioning', 'pagination', 'API design'. A few commonly-said phrases are missing (e.g., 'endpoints', 'OpenAPI', 'auth'), keeping it below the comprehensive-synonym coverage of a 5.

4 / 5

Distinctiveness Conflict Risk

The niche (API style selection and design decisions) is well-differentiated with distinct triggers like 'REST vs GraphQL vs tRPC'. Minor overlap risk remains with closely related backend-development and general web-development skills, which keeps it below the 'clear niche, minimal conflict' of a 5.

4 / 5

Total

15

/

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

frontmatter_unknown_keys

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

Warning

Total

15

/

16

Passed

Repository

administrakt0r/AI-Agents-Safe-Coding-Skills

Path

plugins/antigravity-bundle-full-stack-developer/skills/api-patterns/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.