CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

thin-wrappers

Encapsulates infrastructure SDKs behind minimal domain-aligned interfaces. Use when accessing any external infrastructure to keep SDK usage contained, testing simple, and changes easy.

Quality

75%

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 ./.agents/skills/thin-wrappers/SKILL.md
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.

The body is a lean, well-organized instruction skill: concrete design guidance with specific transformation examples, a clear incremental migration workflow with progress checkpoints, and an exemplary progressive-disclosure split across three real, one-level-deep reference files. Only minor trims (a stray unexplained artifact line, a couple of filler sentences) and the lack of explicit validation checkpoints keep conciseness, actionability, and workflow clarity at 4 rather than 5.

DimensionReasoningScore

Conciseness

The body is efficient and assumes Claude's competence — no basic-concept explanations — but has minor trimmable elements: an unexplained 'STARTER_CHARACTER = 🏗️' artifact line and a few advisory filler sentences ('Simple is better', 'These illustrate the principles. Consider what fits your context.').

4 / 5

Actionability

For an instruction-only skill the guidance is concrete: specific analysis steps ('Find all import statements', 'Catalog which SDK methods are actually used'), a concrete transformation example (cache.set(key, value, ex=ttl, nx=True) → cache.set_if_not_exists(key, value, ttl)), and explicit naming contrasts (publish_order_created(order_id, customer_id) not publish(topic, message)); the minor gap is that complete worked implementations live only in the reference files.

4 / 5

Workflow Clarity

A clear 4-stage design process and a 5-step gradual-refactoring sequence are present with most checkpoints ('Each step should be independently committable and testable', 'Measure progress: Track remaining direct SDK calls'), though the design phase itself lacks explicit validation checkpoints and there is no error-recovery loop.

4 / 5

Progressive Disclosure

The SKILL.md is a concise overview with principles inline, and worked examples are appropriately split into three clearly labeled, well-signaled references (Cache/Redis, Queue/Messaging, Storage/S3) that all exist, contain no nested references, and leave no orphan bundle files — a clean one-level-deep structure.

5 / 5

Total

17

/

20

Passed

Description

58%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 is well-structured with third-person voice and an explicit 'Use when' clause answering both what and when. Its main weaknesses are a single-action 'what', a broad generic trigger ('any external infrastructure') rather than concrete trigger phrases, and missing natural technology-specific keywords users would say.

Suggestions

Sharpen the 'when' clause with concrete trigger situations, e.g. 'Use when direct SDK calls (Redis, S3, queues, databases) spread across business logic, or when switching infrastructure providers'.

Add natural trigger keywords and synonyms users would actually say, such as technology names (Redis, S3, Postgres, SQS) and phrases like 'wrap', 'abstract', or 'adapter', to improve trigger term quality and distinctiveness.

List one or two more concrete actions (e.g. 'expose domain-named operations and replace SDK types with domain types') to raise specificity beyond a single encapsulation verb.

DimensionReasoningScore

Specificity

The description names its domain clearly ('infrastructure SDKs') and one concrete action ('Encapsulates ... behind minimal domain-aligned interfaces'), but the remaining clauses ('keep SDK usage contained, testing simple, and changes easy') state benefits rather than additional concrete actions, so it does not reach the 'several specific actions' level.

3 / 5

Completeness

Both parts are explicitly present: a clear 'what' ('Encapsulates infrastructure SDKs behind minimal domain-aligned interfaces') and an explicit 'Use when' clause, but the trigger ('accessing any external infrastructure') is broad rather than a set of concrete trigger phrases, so it falls short of the top anchor.

4 / 5

Trigger Term Quality

Relevant keywords like 'SDK', 'infrastructure', and 'interfaces' are present, but the natural phrases a user would actually say (e.g. 'wrap the Redis client', 'abstract away the AWS SDK', or technology names like Redis, S3, queue, database) are missing, matching 'some relevant keywords but missing common variations or synonyms'.

3 / 5

Distinctiveness Conflict Risk

The thin-wrapper design niche itself is distinctive, but the trigger 'any external infrastructure' would fire on nearly every database, cache, queue, or cloud task, creating real overlap risk with other infrastructure-related skills; this sits between 'mostly distinct' and 'very broad'.

3 / 5

Total

13

/

20

Passed

Validation

100%

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

saski/arnesto

Path

.agents/skills/thin-wrappers/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.