{"ok":true,"host":"promptqualityscore.com","skill_count":14,"skills":[{"skill_name":"score-prompt-quality","display_name":"Prompt Quality Score","one_liner":"Scores a prompt across 8 dimensions (clarity, specificity, context, constraints, output_format, role_definition, examples, cot_structure) and returns a grade, total out of 80, percentile, and top 3 actionable fixes.","when_to_use":"Use when an agent or user wants to evaluate the quality of a prompt before sending it to an LLM, or to iteratively improve a prompt by understanding which dimensions are weakest and what specific changes would raise the score.","not_for":"Do not use for evaluating LLM responses or outputs — this scores only the prompt itself. Not suitable for real-time or streaming prompt feedback loops due to per-call cost.","confidence":"high","price":"0.03 USD Coin","network":"eip155:8453","method":"POST","resource_url":"https://promptqualityscore.com/api/score","version":1,"merchant_approved":false,"verification_status":"pass","quality_score":66,"last_verified_at":"2026-05-20T06:38:11.598Z","skill_url":"https://x402gle.com/servers/promptqualityscore.com/score-prompt-quality/json"},{"skill_name":"score-prompt-quality-preflight","display_name":"Prompt Quality Score Preflight (Solana)","one_liner":"Scores a prompt across 8 dimensions (clarity, specificity, context, examples, constraints, cot_structure, output_format, role_definition) out of 80 and returns a clearance verdict (CLEAR, CAUTION, or BLOCK) via Solana x402 payment.","when_to_use":"Use when an agent needs to evaluate prompt quality before sending it to a downstream LLM or paid API endpoint, or when checking whether a prompt meets a quality threshold and optionally verifying on-chain trust signals for a target endpoint URL.","not_for":"Do not use for real-time streaming prompt evaluation or for scoring prompts longer than 10,000 characters. Not a content moderation or safety classifier — clearance reflects prompt quality, not harmful content detection.","confidence":"medium","price":"0.05 USDC","network":"solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp","method":"POST","resource_url":"https://promptqualityscore.com/api/preflight/sol","version":1,"merchant_approved":false,"verification_status":"fail","quality_score":61,"last_verified_at":"2026-05-20T11:29:13.067Z","skill_url":"https://x402gle.com/servers/promptqualityscore.com/score-prompt-quality-preflight/json"},{"skill_name":"score-and-complete-prompt-via-venice","display_name":"Prompt Quality Score + Venice.ai Chat Completion","one_liner":"Scores a prompt across 8 quality dimensions (total 8–80, grade A–F) and forwards it to a Venice.ai LLM, returning both the PQS breakdown and the model's response in one call for $0.05 USDC.","when_to_use":"Use when an agent needs to evaluate prompt quality before or alongside LLM inference — specifically to get a structured 8-dimension PQS score (clarity, specificity, context, constraints, output_format, role_definition, examples, cot_structure) plus the Venice.ai chat completion result in a single paid request.","not_for":"Do not use for streaming LLM responses, image generation, or embedding tasks. Do not use if only a quality score is needed without an LLM completion — the $0.05 fee covers both. Note: the Venice.ai backend may return errors (e.g. HTTP 404); the PQS score is still returned but the venice.content field will be absent.","confidence":"high","price":"0.05 USD Coin","network":"eip155:8453","method":"POST","resource_url":"https://promptqualityscore.com/api/proxy/venice","version":1,"merchant_approved":false,"verification_status":"fail","quality_score":18,"last_verified_at":"2026-05-20T10:54:10.505Z","skill_url":"https://x402gle.com/servers/promptqualityscore.com/score-and-complete-prompt-via-venice/json"},{"skill_name":"fix-prompt-injection","display_name":"Prompt Injection Fixer","one_liner":"Detects prompt injection attempts in a given prompt and returns a sanitized version with injection-like fragments removed, along with a confidence score and pattern classification.","when_to_use":"Use when an agent or application needs to validate user-supplied or third-party prompt text for injection attacks (instruction overrides, role hijacks, jailbreaks, delimiter attacks, data exfiltration, encoding evasion) before passing it to an LLM.","not_for":"Do not use for general prompt quality scoring or grammar checking; this endpoint is specifically for injection detection and sanitization only.","confidence":"high","price":"0.03 USD Coin","network":"eip155:8453","method":"POST","resource_url":"https://promptqualityscore.com/api/fix-injection","version":1,"merchant_approved":false,"verification_status":"pass","quality_score":92,"last_verified_at":"2026-05-19T18:53:29.885Z","skill_url":"https://x402gle.com/servers/promptqualityscore.com/fix-prompt-injection/json"},{"skill_name":"generate-prompt-variants","display_name":"PQS Prompt Variants","one_liner":"Generates 1–5 ranked rewrites of a given prompt, each scored on the 8-dimension PQS rubric (clarity, specificity, context, constraints, output_format, role_definition, examples, cot_structure) and returned best-first.","when_to_use":"Use when an agent or user wants to improve a prompt by receiving multiple scored rewrite alternatives with per-dimension breakdowns, a baseline comparison, and a delta showing improvement over the original.","not_for":"Do not use for evaluating a single prompt without generating rewrites; use a dedicated scoring endpoint instead. Not suitable for batch evaluation of many prompts in one call.","confidence":"high","price":"0.10 USD Coin","network":"eip155:8453","method":"POST","resource_url":"https://promptqualityscore.com/api/variants","version":1,"merchant_approved":false,"verification_status":"pass","quality_score":88,"last_verified_at":"2026-05-19T18:53:32.992Z","skill_url":"https://x402gle.com/servers/promptqualityscore.com/generate-prompt-variants/json"},{"skill_name":"score-prompts-batch","display_name":"Batch Prompt Quality Scorer","one_liner":"Scores 1–10 prompts against 8 quality dimensions (clarity, specificity, context, constraints, output_format, role_definition, examples, cot_structure) and returns per-prompt grades, scores out of 80, top fixes, and a batch summary.","when_to_use":"Use when an agent or user wants to evaluate the quality of one or more LLM prompts before deployment, during prompt engineering iteration, or to compare prompt variants across verticals such as software, crypto, content, or research.","not_for":"Do not use for single real-time prompt scoring in a streaming or latency-sensitive pipeline; this is a batch endpoint accepting up to 10 prompts per call. Not suitable for evaluating model outputs — it scores prompts only.","confidence":"high","price":"0.25 USDC","network":"solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp","method":"POST","resource_url":"https://promptqualityscore.com/api/score/batch/sol","version":1,"merchant_approved":false,"verification_status":"unverified","quality_score":null,"last_verified_at":"2026-05-19T19:22:03.526Z","skill_url":"https://x402gle.com/servers/promptqualityscore.com/score-prompts-batch/json"},{"skill_name":"score-prompt-quality","display_name":"Prompt Quality Score (Solana)","one_liner":"Scores a text prompt across 8 dimensions (clarity, specificity, context, constraints, output_format, role_definition, examples, cot_structure) and returns a total score out of 80, letter grade, percentile, and top 3 fix suggestions.","when_to_use":"Use when an agent or user wants to evaluate the quality of a prompt before sending it to an LLM, or to diagnose why a prompt is underperforming and get actionable improvement suggestions.","not_for":"Do not use for optimized/rewritten prompt output; use the /api/score/full/sol endpoint instead. Not suitable for scoring non-prompt text such as documents or code.","confidence":"high","price":"0.03 USDC","network":"solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp","method":"POST","resource_url":"https://promptqualityscore.com/api/score/sol","version":1,"merchant_approved":false,"verification_status":"unverified","quality_score":null,"last_verified_at":"2026-05-19T19:21:07.033Z","skill_url":"https://x402gle.com/servers/promptqualityscore.com/score-prompt-quality/json"},{"skill_name":"compare-prompt-across-models","display_name":"Cross-Model Prompt Quality Comparison","one_liner":"Submits a prompt to both Claude and GPT-4o, scores each response on relevancy, completeness, faithfulness, and reasoning depth (1–10), and returns a winner verdict.","when_to_use":"Use when an agent or user needs to evaluate which LLM (Claude vs GPT-4o) produces a higher-quality response to a given prompt, with per-dimension scores and a natural-language verdict explaining the winner.","not_for":"Do not use for single-model scoring or prompt optimization without comparison; use a single-model scoring endpoint instead. Not suitable for real-time or streaming inference.","confidence":"medium","price":"1.25 USDC","network":"solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp","method":"POST","resource_url":"https://promptqualityscore.com/api/score/compare/sol","version":1,"merchant_approved":false,"verification_status":"unverified","quality_score":null,"last_verified_at":"2026-05-19T20:39:47.246Z","skill_url":"https://x402gle.com/servers/promptqualityscore.com/compare-prompt-across-models/json"},{"skill_name":"score-and-optimize-prompt-full","display_name":"PQS Full Prompt Score","one_liner":"Scores a prompt across 8 quality dimensions (clarity, specificity, context, constraints, examples, output_format, role_definition, cot_structure) out of 80, then returns an optimized version with before/after comparison.","when_to_use":"Use when an agent or user wants to evaluate and improve a prompt before sending it to an LLM, needing both a numeric quality score with dimensional breakdown and a rewritten optimized version of the prompt.","not_for":"Do not use for real-time or streaming prompt evaluation; this is a single-shot analysis. Not suitable for scoring model outputs — only prompt inputs are evaluated.","confidence":"medium","price":"0.13 USDC","network":"solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp","method":"POST","resource_url":"https://promptqualityscore.com/api/score/full/sol","version":1,"merchant_approved":false,"verification_status":"fail","quality_score":null,"last_verified_at":"2026-05-20T04:38:39.007Z","skill_url":"https://x402gle.com/servers/promptqualityscore.com/score-and-optimize-prompt-full/json"},{"skill_name":"score-prompt-quality-preflight","display_name":"Prompt Quality Preflight Check","one_liner":"Scores a prompt across 8 quality dimensions (0–80) and returns a clearance verdict plus optional endpoint trust label before sending to inference.","when_to_use":"Use when an agent needs to evaluate whether a prompt meets quality thresholds before dispatching it to an LLM endpoint, or when the agent wants to check the trust status of a target API endpoint alongside prompt quality.","not_for":"Do not use as a real-time streaming quality filter or for bulk batch scoring; this is a single-shot preflight check per prompt. Not a substitute for output evaluation after inference.","confidence":"high","price":"0.05 USD Coin","network":"eip155:8453","method":"POST","resource_url":"https://promptqualityscore.com/api/preflight","version":1,"merchant_approved":false,"verification_status":"unverified","quality_score":null,"last_verified_at":"2026-05-19T19:21:07.061Z","skill_url":"https://x402gle.com/servers/promptqualityscore.com/score-prompt-quality-preflight/json"},{"skill_name":"grade-prompt-quality","display_name":"Prompt Quality Grade","one_liner":"Scores a prompt 0-100 with a letter grade (A-F), PEEM/RAGAS/G-Eval sub-scores (0-10 each), and a one-sentence verdict identifying the weakest dimension.","when_to_use":"Use when an agent needs to evaluate prompt quality before sending it to a costly inference call, or when a user wants to diagnose why a prompt is underperforming across structure, grounding, and faithfulness dimensions.","not_for":"Do not use for evaluating model outputs or generated text quality; this endpoint scores the prompt itself, not the response it produces.","confidence":"high","price":"0.0010 USD Coin","network":"eip155:8453","method":"POST","resource_url":"https://promptqualityscore.com/api/pqs-grade","version":1,"merchant_approved":false,"verification_status":"pass","quality_score":84,"last_verified_at":"2026-05-20T14:35:18.846Z","skill_url":"https://x402gle.com/servers/promptqualityscore.com/grade-prompt-quality/json"},{"skill_name":"compare-prompt-claude-vs-gpt4o","display_name":"Claude vs GPT-4o Prompt Quality Comparison","one_liner":"Runs a prompt through both Claude Sonnet 4 and GPT-4o, scores each on relevancy, completeness, faithfulness, and reasoning depth (1–10), and returns a winner verdict judged by a third model.","when_to_use":"Use when an agent or user needs to know which model (Claude or GPT-4o) produces a higher-quality response to a given prompt, including per-dimension scores and a natural-language verdict explaining the winner.","not_for":"Do not use for single-model scoring or prompt optimization without comparison; use a single-model scoring endpoint instead. Not suitable for real-time or streaming inference — this is a one-shot scored comparison.","confidence":"medium","price":"1.25 USD Coin","network":"eip155:8453","method":"POST","resource_url":"https://promptqualityscore.com/api/score/compare","version":1,"merchant_approved":false,"verification_status":"unverified","quality_score":null,"last_verified_at":"2026-05-19T20:39:47.901Z","skill_url":"https://x402gle.com/servers/promptqualityscore.com/compare-prompt-claude-vs-gpt4o/json"},{"skill_name":"score-prompts-batch","display_name":"Batch Prompt Quality Scorer","one_liner":"Scores 1–10 prompts against 8 quality dimensions (clarity, specificity, context, constraints, output_format, role_definition, examples, cot_structure) and returns per-prompt grades and batch summary statistics.","when_to_use":"Use when an agent needs to evaluate or compare the quality of one or more LLM prompts before deployment, during prompt engineering iteration, or to surface actionable improvement suggestions across a batch of up to 10 prompts at once.","not_for":"Do not use for scoring more than 10 prompts in a single call; split into multiple batch requests instead. Not suitable for real-time streaming evaluation or non-text prompt modalities.","confidence":"high","price":"0.25 USD Coin","network":"eip155:8453","method":"POST","resource_url":"https://promptqualityscore.com/api/score/batch","version":1,"merchant_approved":false,"verification_status":"unverified","quality_score":null,"last_verified_at":"2026-05-19T19:21:07.681Z","skill_url":"https://x402gle.com/servers/promptqualityscore.com/score-prompts-batch/json"},{"skill_name":"score-and-optimize-prompt-full","display_name":"Prompt Quality Score — Full Analysis","one_liner":"Scores an input prompt across 8 dimensions (clarity, specificity, context, constraints, output_format, role_definition, examples, cot_structure), returns an optimized rewrite, before/after scores, and an improvement percentage.","when_to_use":"Use when an agent or user wants to evaluate prompt quality and receive an improved version with dimensional scores, letter grades, percentile rankings, and a sample output for both the original and optimized prompts.","not_for":"Do not use for simple prompt execution or inference tasks where no quality evaluation or rewrite is needed; use a standard LLM completion endpoint instead.","confidence":"high","price":"0.13 USD Coin","network":"eip155:8453","method":"POST","resource_url":"https://promptqualityscore.com/api/score/full","version":1,"merchant_approved":false,"verification_status":"unverified","quality_score":null,"last_verified_at":"2026-05-19T19:22:05.055Z","skill_url":"https://x402gle.com/servers/promptqualityscore.com/score-and-optimize-prompt-full/json"}],"manifest_url":"https://x402gle.com/servers/promptqualityscore.com/manifest.json","skill_md_url":"https://x402gle.com/servers/promptqualityscore.com/SKILL.md","agent_card_url":"https://x402gle.com/servers/promptqualityscore.com/.well-known/agent.json"}