Get highest-rated ACE patterns by helpful score
Retrieve the highest-rated ACE patterns by helpful score - get battle-tested patterns that have proven successful in your project. Use this when you want quality-first best practices instead of searching for specific solutions.
/plugin marketplace add ce-dot-net/ce-claude-marketplace/plugin install ace@ce-dot-net-marketplaceRetrieve proven patterns with the highest helpful scores - battle-tested patterns that have proven successful.
Returns patterns sorted by helpful score (upvotes from successful usage), giving you quality-first retrieval instead of quantity.
When the user runs /ace-top [section] [limit], use ace-cli:
#!/usr/bin/env bash
set -euo pipefail
if ! command -v ace-cli >/dev/null 2>&1; then
echo "ā ace-cli not found - Install: npm install -g @ace-sdk/cli"
exit 1
fi
# Read context
ORG_ID=$(jq -r '.orgId // .env.ACE_ORG_ID // empty' .claude/settings.json 2>/dev/null || echo "")
PROJECT_ID=$(jq -r '.projectId // .env.ACE_PROJECT_ID // empty' .claude/settings.json 2>/dev/null || echo "")
# Try env wrapper format
if [ -z "$ORG_ID" ] || [ -z "$PROJECT_ID" ]; then
ORG_ID=$(jq -r '.env.ACE_ORG_ID // empty' .claude/settings.json 2>/dev/null || echo "")
PROJECT_ID=$(jq -r '.env.ACE_PROJECT_ID // empty' .claude/settings.json 2>/dev/null || echo "")
fi
if [ -z "$PROJECT_ID" ]; then
echo "ā Run /ace:configure first"
exit 1
fi
# Parse arguments
SECTION="${1:-}"
LIMIT="${2:-10}"
MIN_HELPFUL="${3:-0}"
# Build command
CMD_ARGS=""
if [ -n "$SECTION" ]; then
CMD_ARGS="$CMD_ARGS --section $SECTION"
fi
CMD_ARGS="$CMD_ARGS --limit $LIMIT --min-helpful $MIN_HELPFUL"
echo "š Fetching top-rated patterns..."
# Execute command
if [ -n "$ORG_ID" ]; then
ace-cli --org "$ORG_ID" --project "$PROJECT_ID" top $CMD_ARGS
else
ace-cli --project "$PROJECT_ID" top $CMD_ARGS
fi
if [ $? -eq 0 ]; then
echo "ā
Retrieved top patterns"
else
echo "ā Failed to retrieve patterns"
exit 1
fi
strategies_and_hard_rules, useful_code_snippets, troubleshooting_and_pitfalls, apis_to_use5 for only highly-rated patterns/ace-top
ā Returns top 10 patterns across all sections
/ace-top strategies_and_hard_rules
ā Returns top 10 architectural patterns/principles
/ace-top troubleshooting_and_pitfalls 5
ā Returns top 5 troubleshooting patterns
/ace-top apis_to_use 20 3
ā Returns top 20 API recommendations with helpful >= 3
ā
Use /ace-top when:
ā Don't use when:
/ace-search instead)/ace-patterns instead)The tool returns JSON with top-rated patterns:
{
"patterns": [
{
"content": "Always use refresh token rotation to prevent theft attacks",
"helpful": 12,
"harmful": 0,
"confidence": 0.95,
"section": "strategies_and_hard_rules",
"observations": 15,
"evidence": [
"Prevented auth bypass in 3 projects",
"Industry standard per OWASP recommendations"
]
}
],
"section": "strategies_and_hard_rules",
"count": 10,
"min_helpful": 5
}
Patterns are sorted by helpful score (descending).
Patterns with harmful > 0 indicate they've had negative feedback and should be used cautiously.
Similar to semantic search - retrieves only top patterns instead of full playbook:
Architecture questions:
/ace-top strategies_and_hard_rules 10
ā "What are the best architectural patterns we've learned?"
Debugging help:
/ace-top troubleshooting_and_pitfalls 5
ā "What are the most common issues we've encountered?"
Library selection:
/ace-top apis_to_use 10 5
ā "What libraries have we had success with?"
/ace-search - Semantic search for specific queries/ace-patterns - View full playbook/ace-status - Check playbook statistics