forcedotcom/sf-skills / plugins/builder/salesforce-development/skills/platform-flexipage-generate
platform-flexipage-generate
VerifiedUse when users create, generate, modify, or validate Salesforce Lightning pages (FlexiPages). Trigger on RecordPage, AppPage, HomePage, Lightning pages, adding components to a page, page customization (e.g. 'customize the record page'), or .flexipage-meta.xml files (regions, components, deployment errors). DO NOT TRIGGER for Visualforce pages, page layout assignments in the UI, UI Bundle/Experience Cloud site pages, or Aura/Lightning Web Component development without FlexiPage context.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 20.1 KB |
| references/cli_commands.md | markdown | 769 B |
| references/flexipage_fieldSection.md | markdown | 5.8 KB |
| references/flexipage_richText.md | markdown | 3.2 KB |
| references/identifiers_and_regions.md | markdown | 6.0 KB |
| references/mcp_action_examples.md | markdown | 3.8 KB |
| references/record_flexipage_dynamicHighlights.md | markdown | 4.7 KB |
| references/xml_rules.md | markdown | 13.7 KB |
| scripts/resolve-component-instructions.shexecutable | script | 1.2 KB |
| scripts/scan-lwc-components.shexecutable | script | 2.9 KB |
scripts/scan-lwc-components.sh
View on GitHub#!/bin/bash
# scan-lwc-components.sh — Scan local SFDX project for LWC components matching a query.
#
# Usage: scripts/scan-lwc-components.sh <query> [packageDirectory]
#
# Arguments:
# query — User intent keywords (e.g., "expense tracker")
# packageDirectory — SFDX package directory path (default: read from sfdx-project.json)
#
# Output: Ranked JSON array of matches with confidence scores.
# [{"name": "expenseTracker", "score": 75, "confidence": "high"}]
#
# Confidence tiers:
# high (≥70%): auto-select, confirm with user
# medium (40-69%): present ranked list for user selection
# low (<40%): skip, proceed to Tier 2
set -euo pipefail
QUERY="${1:-}"
PKG_DIR="${2:-}"
if [ -z "$QUERY" ]; then
echo "Usage: $0 <query> [packageDirectory]" >&2
exit 1
fi
# Resolve package directory from sfdx-project.json if not provided
if [ -z "$PKG_DIR" ]; then
if [ -f "sfdx-project.json" ]; then
PKG_DIR=$(python3 -c "
import json, sys
with open('sfdx-project.json') as f:
data = json.load(f)
dirs = data.get('packageDirectories', [])
if dirs:
print(dirs[0].get('path', 'force-app'))
else:
print('force-app')
" 2>/dev/null || echo "force-app")
else
PKG_DIR="force-app"
fi
fi
# Check if package directory exists
if [ ! -d "$PKG_DIR" ]; then
echo "[]"
exit 0
fi
# Tokenize query: lowercase, split on spaces
IFS=' ' read -ra QUERY_TOKENS <<< "$(echo "$QUERY" | tr '[:upper:]' '[:lower:]')"
# Find all LWC component directories
RESULTS="["
FIRST=true
while IFS= read -r dir; do
COMP_NAME=$(basename "$dir")
# Tokenize camelCase component name: split on uppercase boundaries → lowercase
COMP_TOKENS=$(echo "$COMP_NAME" | sed 's/\([a-z]\)\([A-Z]\)/\1 \2/g' | tr '[:upper:]' '[:lower:]')
IFS=' ' read -ra TOKENS <<< "$COMP_TOKENS"
TOTAL=${#TOKENS[@]}
if [ "$TOTAL" -eq 0 ]; then
continue
fi
# Count matched tokens
MATCHED=0
for qt in "${QUERY_TOKENS[@]}"; do
for ct in "${TOKENS[@]}"; do
if [ "$qt" = "$ct" ]; then
MATCHED=$((MATCHED + 1))
break
fi
done
done
# Calculate score
SCORE=$(( (MATCHED * 100) / TOTAL ))
# Determine confidence tier
if [ "$SCORE" -ge 70 ]; then
CONFIDENCE="high"
elif [ "$SCORE" -ge 40 ]; then
CONFIDENCE="medium"
else
CONFIDENCE="low"
fi
# Only include medium and high confidence matches
if [ "$SCORE" -ge 40 ]; then
if [ "$FIRST" = true ]; then
FIRST=false
else
RESULTS+=","
fi
RESULTS+="{\"name\":\"$COMP_NAME\",\"score\":$SCORE,\"confidence\":\"$CONFIDENCE\"}"
fi
done < <(find "$PKG_DIR" -path "*/lwc/*" -type d -maxdepth 5 | grep -v "__tests__")
RESULTS+="]"
# Sort by score descending (using python for JSON sorting)
echo "$RESULTS" | python3 -c "
import json, sys
data = json.load(sys.stdin)
data.sort(key=lambda x: x['score'], reverse=True)
print(json.dumps(data, indent=2))
" 2>/dev/null || echo "$RESULTS"
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| writing-skillsobra/superpowersUse when creating new skills, editing existing skills, or verifying skills work before deployment | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| xlsxanthropics/skillsUse this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| shipping-and-launchaddyosmani/agent-skillsPrepares production launches. Use when preparing to deploy to production, or when asking what needs to be in place before shipping. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy. | Stars: 119k | Updated | Claude CodeCodex | Verified | Install |
| childhoodthedotmack/claude-memBabysit a shipped release after merge, publication, or deployment. Verify published packages, production behavior, installed plugins, and late CI or user reports until the observation window is clean; use babysit for PR readiness before release. | Stars: 118k | Updated | Claude CodeCodex | Verified | Install |