promptqualityscore.com
14 resources8088ms p50
86
promptqualityscore.com
promptqualityscore.com is a prompt engineering utility host serving agents and developers who need to evaluate, improve, or secure prompts before sending them to LLMs. It is distinct in combining a structured multi-dimension scoring rubric with rewrite generation, cross-model response comparison, and injection sanitization under one API surface. It does not execute general LLM tasks or evaluate LLM outputs beyond the cross-model comparison workflow.
Capabilities
Prompt Quality Scoring
Evaluates a prompt against the 8-dimension PQS rubric, returning a numeric score, letter grade, percentile, and the top three actionable fixes. This is the foundational assessment layer the other skills build on.
score-prompt-quality
Prompt Improvement and Rewriting
Generates up to five ranked rewrites of a prompt, each scored on the same 8-dimension rubric, with a baseline comparison and per-variant delta showing improvement over the original.
generate-prompt-variants
Cross-Model Response Comparison
Submits a prompt to both Claude and GPT-4o, scores each response on relevancy, completeness, faithfulness, and reasoning depth, and returns a winner verdict with per-dimension scores.
compare-prompt-across-models
Prompt Security and Injection Detection
Detects and sanitizes prompt injection attempts—including instruction overrides, role hijacks, jailbreaks, delimiter attacks, and encoding evasion—before a prompt reaches an LLM.
fix-prompt-injection
Workflows
Secure-Then-Score Pipeline
Use when an agent needs to process user-supplied or third-party prompt text that may be adversarial before evaluating or improving it.
- 1fix-prompt-injectionSanitize the incoming prompt, removing injection fragments and obtaining a clean version with a confidence score.
- 2score-prompt-qualityScore the sanitized prompt on the 8-dimension rubric to understand its baseline quality before any LLM call.
Secure, Score, and Improve
Use when an agent needs to take untrusted user input, confirm it is safe, assess its quality, and then produce ranked improved rewrites ready for LLM submission.
- 1fix-prompt-injectionSanitize the prompt to remove injection attempts and obtain a clean baseline.
- 2score-prompt-qualityScore the sanitized prompt to identify the weakest dimensions and establish a baseline score.
- 3generate-prompt-variantsGenerate ranked rewrites of the sanitized prompt, using the baseline score as a reference point for measuring improvement.
Optimize Then Compare Models
Use when an agent needs to determine which LLM handles a prompt best, but first wants to ensure the prompt is high quality before running the comparison.
- 1score-prompt-qualityScore the prompt to identify weaknesses and confirm it meets a quality threshold worth comparing.
- 2generate-prompt-variantsGenerate improved rewrites and select the best-scoring variant to use as the comparison prompt.
- 3compare-prompt-across-modelsSubmit the optimized prompt to Claude and GPT-4o and receive a scored verdict on which model responds better.
Use this host in Claude
Copy the skill below, then add it on claude.ai under Skills → Create skill → Upload.
$1.30
across39settlements·$0.03avg
2buyers
1sellers
All-time context: $26.39 across 872 settlements
Facilitators
all-time breakdown
Chains
Last 24h
base
Resources (14)
All-time breakdown
| Resource | Category | Quality | Tier | Txns | Volume |
|---|---|---|---|---|---|
Prompt Quality Grade https://promptqualityscore.com/api/pqs-grade | AI | 86 | host level | 132 | $3.35 |
Prompt Quality Score https://promptqualityscore.com/api/score/sol | AI | — | host level | — | — |
Own promptqualityscore.com? List it with your agent
Paste the prompt below to your coding agent. It runs a real paid test on every route, fixes what scores low, and re-auditions until they pass — the gaps below are already filled in for you.
- 6 of 14 routes have never been scored — the audition tests them for the first time.
- 1 route is scoring below 50 — likely broken, mispriced, or returning the wrong shape.
- 3 routes are in the 50–74 band — working, but with room to climb.
- 6 routes are flagged by the verifier as failing or inconclusive.
Paste this to your agent
Make my x402 API at https://promptqualityscore.com discoverable on x402gle. Read the instructions at https://x402gle.com/agent.md and follow them end to end. Install the OpenDexter CLI, then run `npx @dexterai/opendexter audition https://promptqualityscore.com --json`. Heads up: 6 routes have never been scored and 1 route is scoring below 50 — start there. Read the score and fixInstructions for every route, fix my OpenAPI and endpoints until each route passes, and re-audition until it does. A passing audition lists my API automatically.
New to this? How agent-first onboarding works.
Latest Settlements
Live feed| For | Via | Chain | Amount | Buyer | Tx | Time |
|---|---|---|---|---|---|---|