Name: upstash-qstash
Rating: 43.2 (1 reviews)
Author: administrakt0r

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.

Quality

44%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/upstash-qstash/SKILL.md

The canonical home for this skill is upstash-qstash in administrakt0r/AI-Agents-Safe-Coding-Skills

Quality

Content

40%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 skill is well-sectioned and concise but severely lacks actionability: no executable code, truncated content, and stub pattern/anti-pattern sections leave Claude without concrete steps. Validation and workflow sequencing are absent despite the skill involving signature verification and retry behavior where they matter.

Suggestions

Add copy-paste-ready code for each Pattern (publish, schedule/cron, signature verification) and complete the truncated 'core philosophy' line ('no c...').

Expand Anti-Patterns and Sharp-Edges 'Solution' cells into actual executable snippets instead of bare comment fragments like '# Always verify signatures with both keys:'.

Provide a sequenced workflow with validation checkpoints for webhook setup (publish -> verify signature in endpoint -> confirm ack/retry behavior) and replace the generic 'When to Use' placeholder with real trigger guidance.

Dimension	Reasoning	Score
Conciseness	The body is short and does not over-explain concepts Claude already knows, but the opening persona paragraphs ('You are an Upstash QStash expert...', 'You've scheduled millions of messages...') are non-actionable padding that could be trimmed, fitting 'mostly efficient but includes some unnecessary explanation'.	3 / 5
Actionability	There is no executable code anywhere: the Patterns sections are one-line descriptions ('Sending messages to be delivered to endpoints'), Anti-Patterns are bare labels, and Sharp-Edges 'Solutions' are truncated code-comment fragments with no code, matching 'minimal concrete guidance; high-level hints but missing specific steps'.	2 / 5
Workflow Clarity	No multi-step workflow is sequenced and validation checkpoints are absent; the 'core philosophy' list is literally incoherent ('HTTP is the universal language - no c'), and the Sharp Edges only flag validation needs (signatures) without steps, fitting 'rough structure, many gaps, validation absent'.	2 / 5
Progressive Disclosure	The body is under 50 lines with no external references needed, and it is organized into clear sections (Capabilities, Patterns, Anti-Patterns, Sharp Edges, Related Skills); the simple-skill exception allows a high score, but stub-like empty sections and the broken philosophy line keep it at 'good structure, minor organization gaps' rather than 5.	4 / 5
	Total	11 / 20 Passed

Description

48%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 names a specific, distinct product and conveys a clear purpose, but it relies on persona framing rather than action enumeration and omits any 'Use when' trigger guidance. Second-person voice and missing trigger terms keep it mid-range across dimensions.

Suggestions

Convert to third person and lead with concrete actions: e.g. 'Schedules and delivers HTTP messages reliably via Upstash QStash, sets up serverless cron jobs, and builds webhook delivery pipelines.'

Add an explicit trigger clause: 'Use when the user needs scheduled/reliable HTTP calls, serverless cron, webhook delivery, or message deduplication with QStash.'

Include natural trigger synonyms users actually say — cron, webhook, scheduled HTTP call, queue, delay — to raise trigger-term coverage.

Dimension	Reasoning	Score
Specificity	It names the domain ('Upstash QStash', 'serverless messaging') and one concrete action ('builds reliable serverless messaging') with a mechanism ('HTTP in, HTTP out'), sitting at the domain+1-2-actions level (anchor 3), but the second-person voice ('You are', 'You understand') triggers the required -1 specificity penalty, dropping it to 2.	2 / 5
Completeness	The 'what' is reasonably clear ('builds reliable serverless messaging'), but there is no 'Use when...' clause or equivalent trigger guidance, so per the guideline completeness is capped at 3 ('clear what, missing when').	3 / 5
Trigger Term Quality	'Upstash QStash' and 'serverless messaging' are relevant natural terms, but common user phrases for this domain — cron, webhook, scheduled calls, queue, delay — are absent from the description, matching the 'some relevant keywords but missing common variations' anchor.	3 / 5
Distinctiveness Conflict Risk	Naming the specific product 'Upstash QStash' gives a clear niche with minimal conflict risk, but the thin trigger guidance leaves minor overlap risk with related messaging/queue/cron skills, fitting 'mostly distinct; minor overlap risk' rather than the fully-distinct anchor 5.	4 / 5
	Total	12 / 20 Passed

Validation

93%

Warnings & errors only

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

Criteria	Description	Result
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/AI-Agents-Safe-Coding-Skills-claude/skills/upstash-qstash/SKILL.md
Commit: 900c504

Reviewed: 6 hours ago

Table of Contents

Discovery Implementation Validation

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.