CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

micro

Expert guidance for micro — asynchronous HTTP microservices framework by Vercel. Use when building lightweight HTTP servers, API endpoints, or microservices using the micro library.

59

Quality

74%

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/vercel/skills/micro/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

75%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 lean, code-centric reference that is immediately actionable for micro's small API surface. It covers install, both handler styles, all core helpers, dev tooling, composition, and project wiring without padding. The main residuals are a trimmable intro, a missing 'verify the server responds' checkpoint, and unconfirmed modern-API usage details.

DimensionReasoningScore

Conciseness

The body is code-first and lean — each API gets a short runnable snippet with almost no prose. Minor over-explanation remains: the persona intro 'You are an expert in micro, Vercel's lightweight framework...' and the line 'micro makes it easy to write single-purpose HTTP endpoints with minimal boilerplate' restate what Claude can infer, keeping it just below the 'every token earns its place' anchor.

4 / 5

Actionability

Nearly all guidance is executable: 'npm install micro', 'npx micro', complete handlers for json/text/buffer/send/createError, and a package.json with start/dev scripts. Minor gaps keep it from 5 — the modern 'serve(handler)' example omits port/listen details, and no example shows how a thrown createError is actually rendered to the client.

4 / 5

Workflow Clarity

The sequence install → write handler → run → dev workflow → package.json setup is clear and in order, and the skill is single-purpose with no destructive or batch operations (so no validation cap applies). It sits at 4 rather than 5 because there is no checkpoint confirming the server works (e.g., curl the endpoint) between 'npx micro' and moving on.

4 / 5

Progressive Disclosure

Sections (Installation, Basic Usage, Core API, Development, Composition, package.json, Key Points) are well-organized and the API reference is appropriately inline given micro's tiny surface (five helpers). No bundle files exist, which is reasonable at this size, but the >50-line body with a full inline API reference leaves minor room to split Core API into a references file, so it fits the 'good structure, minor organization gaps' anchor rather than 5.

4 / 5

Total

16

/

20

Passed

Description

65%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 focused, trigger-explicit description that clearly ties the skill to the micro library with a genuine 'Use when...' clause. Its main weakness is specificity — it says 'expert guidance' without naming any concrete capabilities the skill provides. Distinctiveness is good but the generic server-building phrasing invites some overlap with other web-framework skills.

Suggestions

Replace 'Expert guidance for micro' with 2-3 concrete capabilities, e.g. 'Build HTTP endpoints with micro: parse JSON/text/raw request bodies, send JSON responses, throw HTTP errors via createError, and hot-reload with micro-dev.'

Add natural trigger variations such as 'Node.js HTTP server', 'web endpoint', or 'single-endpoint service' to broaden match coverage without losing distinctiveness.

Mention the classic Node-style (req, res) handler pattern in the when-clause so users describing handlers in those terms also trigger the skill.

DimensionReasoningScore

Specificity

'Expert guidance for micro — asynchronous HTTP microservices framework by Vercel' names the domain but lists no concrete actions — capabilities like body parsing (json/text/buffer), response sending, error creation, and hot-reload dev tooling that the body actually covers are absent. This matches the anchor 'Names the domain but actions are minimal or generic'; it is below 3 because not even 1-2 concrete actions are stated.

2 / 5

Completeness

Both parts are present: the what ('asynchronous HTTP microservices framework by Vercel') and an explicit when ('Use when building lightweight HTTP servers, API endpoints, or microservices using the micro library'). It is not a 5 because the what identifies the library rather than stating concrete trigger-worthy capabilities, and the when could mention the classic Node http handler pattern.

4 / 5

Trigger Term Quality

'building lightweight HTTP servers, API endpoints, or microservices using the micro library' includes natural phrases users would say. It falls short of comprehensive coverage — variations like 'web server', 'Node.js endpoint', or 'micro-dev' are missing, though for a named library the core terms are strong.

4 / 5

Distinctiveness Conflict Risk

The trigger is pinned to 'the micro library', giving a clear niche, but the generic phrases 'building lightweight HTTP servers' and 'API endpoints' overlap with skills for Express, Fastify, or plain Node servers. Minor overlap risk with closely related skills — the anchor 4 example, not the minimal-conflict anchor 5.

4 / 5

Total

14

/

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.

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

Total

14

/

16

Passed

Repository

openai/plugins

Path

plugins/vercel/skills/micro/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.