From contextstellar
Score a prompt for context engineering quality. Use when the user asks to score, analyze, or optimize a prompt, or when reviewing prompt quality before sending to an LLM.
npx claudepluginhub sunnypatneedi/claude-code-contextstellarThis skill uses the workspace's default tool permissions.
Score the provided prompt text for context engineering quality using the ContextStellar scoring API.
Evaluates prompt quality, optimizes using 58 techniques like CoT, few-shot learning, role-play. Useful for improving clarity, specificity, structure, or generating variations.
Scores prompts across 7 dimensions and restructures using 8 Anthropic techniques like XML tags and chain-of-thought. Auto-triggers on PreToolUse for unstructured subagent prompts; manual via /reprompt-orator.
Analyze and improve existing prompts for better performance
Share bugs, ideas, or general feedback.
Score the provided prompt text for context engineering quality using the ContextStellar scoring API.
Take the prompt text from $ARGUMENTS. If no arguments provided, ask the user to paste or describe the prompt they want scored.
Call the ContextStellar hooks endpoint to score the prompt:
curl -s -X POST "${CONTEXTSTELLAR_BASE_URL:-https://contextstellar.com}/api/v1/hooks/claude-code" \
-H "Authorization: ${CONTEXTSTELLAR_API_KEY}" \
-H "Content-Type: application/json" \
-d "{
\"sessionId\": \"manual-score-$(date +%s)\",
\"type\": \"PreToolUse\",
\"toolName\": \"ManualScore\",
\"toolInput\": { \"content\": $(echo "$PROMPT_TEXT" | jq -Rs .) }
}"
Present the results clearly:
If the score is below B (< 70), proactively suggest specific improvements the user can make.
| Dimension | What It Measures |
|---|---|
| Token Utilization (25%) | Waste: politeness, filler, intensifiers, redundancy |
| Structural Clarity (23%) | XML tags, lists, headers, code blocks, imperative keywords |
| Specificity (20%) | Numbers, format keywords, role assignment, examples, constraints |
| Content Density (17%) | Lexical diversity, n-gram repetition |
| Cache-Friendliness (15%) | Timestamps, UUIDs, date refs, volatile data positioning |