CtrlK
BlogDocsLog inGet started
Tessl Logo

upstash-qstash

You are an Upstash QStash expert who builds reliable serverless messaging without infrastructure management. You understand that QStash's simplicity is its power - HTTP in, HTTP out, with reliability in between.

32

Quality

27%

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 ./skills/upstash-qstash/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

18%Scale 1-5

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 skeleton or outline with no actionable content. It names relevant QStash concepts and lists sharp edges in a table format, but provides zero executable code, no concrete API examples, no workflow steps, and no actual solutions in the sharp edges table. The core philosophy section appears truncated. As-is, this skill would not help Claude perform any QStash-related task.

Suggestions

Add concrete, executable code examples for each pattern (Basic Message Publishing, Scheduled Cron Jobs, Signature Verification) — at minimum show the HTTP request or SDK call with actual parameters.

Complete the sharp edges table by providing actual code solutions instead of truncated comments (e.g., show the signature verification code, the fast-acknowledgment pattern, the deduplication header usage).

Define a clear workflow for the most common use case (e.g., publish message → verify signature at endpoint → handle callback) with explicit validation steps.

Either flesh out the anti-patterns with concrete 'do this instead' examples, or remove them to save tokens and focus on making the patterns section actionable.

DimensionReasoningScore

Conciseness

The skill includes some unnecessary filler (e.g., 'You've scheduled millions of messages,' 'Your core philosophy' section that gets cut off), and the capabilities list is somewhat redundant with the content. However, the sharp edges table is reasonably compact. There's moderate verbosity without much payoff.

3 / 5

Actionability

The skill contains zero executable code, no concrete commands, no API calls, no copy-paste examples. The patterns section names concepts ('Basic Message Publishing', 'Scheduled Cron Jobs', 'Signature Verification') but provides no actual implementation. The sharp edges table references code comments but includes no actual code. This is entirely vague direction.

1 / 5

Workflow Clarity

There are no defined steps, no sequences, no validation checkpoints. The patterns section lists topic headers with one-line descriptions but no workflow. The sharp edges table mentions solutions but doesn't actually provide them — just truncated comments. No feedback loops or error recovery guidance exists.

1 / 5

Progressive Disclosure

The content has some section structure (Capabilities, Patterns, Anti-Patterns, Sharp Edges, Related Skills), but there are no bundle files and no references to external documents. The patterns and anti-patterns sections are stubs with headers only and no content beneath them. Content that should exist somewhere simply doesn't exist at all.

2 / 5

Total

7

/

20

Passed

Description

36%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 uses first/second person voice ('You are...', 'You understand...'), which violates the third-person requirement. It names the specific technology (Upstash QStash) but fails to list concrete actions the skill performs and entirely omits trigger guidance for when Claude should select it. The philosophical statement about QStash's simplicity is fluff that doesn't aid skill selection.

Suggestions

Replace the vague capability statement with specific actions like 'Publishes messages to HTTP endpoints, schedules delayed deliveries, configures retry policies, manages topics and subscriptions using Upstash QStash.'

Add an explicit 'Use when...' clause with trigger terms such as 'Use when the user asks about QStash, message queues, background jobs, scheduled HTTP requests, or serverless messaging with Upstash.'

Rewrite in third person voice (e.g., 'Builds and configures Upstash QStash serverless messaging...') instead of the current second person 'You are...' framing.

DimensionReasoningScore

Specificity

Names the domain (Upstash QStash, serverless messaging) but provides no concrete actions. 'Builds reliable serverless messaging' is vague and doesn't describe what the skill actually does (e.g., create queues, schedule messages, configure retries).

2 / 5

Completeness

Has a vague 'what' (builds serverless messaging) but completely lacks a 'when' clause. There is no explicit guidance on when Claude should select this skill. The rubric caps completeness at 3 for missing 'Use when...' and this also has a weak 'what', so 2 is appropriate.

2 / 5

Trigger Term Quality

Includes 'QStash', 'Upstash', 'serverless messaging', and 'HTTP' which are relevant keywords. However, it misses natural user phrases like 'message queue', 'background jobs', 'scheduled tasks', 'webhooks', 'retry', or 'pub/sub'.

3 / 5

Distinctiveness Conflict Risk

Mentioning 'Upstash QStash' specifically provides some distinctiveness, but 'serverless messaging' and 'HTTP' are broad enough to overlap with other messaging, API, or serverless skills.

3 / 5

Total

10

/

20

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
administrakt0r/AI-Agents-Safe-Coding-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.