Stats
Actions
Tags
From prompsit
Evaluate translation quality with metrics (BLEU, chrF, MetricX) using the Prompsit Translation API. Use when the user needs quality evaluation, QE scores, or translation metric comparisons.
How this skill is triggered — by the user, by Claude, or both
Slash command
/prompsit:prompsit-evaluateThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Evaluate translation quality. Alias: `eval`.
Evaluate translation quality. Alias: eval.
prompsit evaluate -s "Hello" -h "Hola" -r "Hola" -m "bleu,chrf"
prompsit evaluate -s "Hello" -h "Hola" -r "Hola" -m "bleu,chrf,metricx"
TSV format: source\thypothesis\treference (tab-separated).
prompsit evaluate @"scores.tsv" -m "bleu,chrf,metricx"
prompsit evaluate @"file.xlsx" -m "bleu" --out ./scored
prompsit evaluate --formats # supported file formats
| Flag | Description |
|---|---|
-s, --source <text> | Source text |
-h, --hypothesis <text> | Translation hypothesis |
-r, --reference <text> | Reference translation |
-m, --metrics <list> | Comma-separated metric names |
--out <dir> | Output directory |
--output-format <fmt> | Output format |
--formats | List supported file formats |
Version: 1.0.0 Last Updated: 2026-03-13
npx claudepluginhub prompsit/prompsit-cli --plugin prompsitSearches MemPalace before answering questions about past work, people, projects, or prior decisions. Returns verbatim stored content instead of guessing from model memory.
Guides Payload CMS config (payload.config.ts), collections, fields, hooks, access control, APIs. Debugs validation errors, security, relationships, queries, transactions, hook behavior.
Implements vector databases with Pinecone, Weaviate, Qdrant, Milvus, pgvector for semantic search, RAG, recommendations, and similarity systems. Optimizes embeddings, indexing, and hybrid search.