Use this skill to create and configure Lightning apps in Salesforce Setup, add navigation items and tabs to apps, configure utility bar components, and control app visibility by profile or permission set. Trigger keywords: Lightning app, App Manager, custom tab, navigation bar, utility bar, app visibility. NOT for Experience Cloud site apps (use experience-cloud skills), NOT for configuring page layouts or record pages (use Lightning App Builder), NOT for permission set architecture (use permission-set-architecture).

Use when choosing between Custom Metadata Types and Custom Settings, understanding hierarchical vs list settings, deployment behavior, governor limit implications, or accessing either from Apex and Flow. Trigger keywords: 'custom metadata vs custom settings', 'hierarchical settings per user profile', 'deployable config vs runtime settings', 'getValues getInstance in apex', 'flow get records custom settings'. NOT for custom objects (use object-creation-and-design), NOT for Named Credentials (use named-credentials-setup), NOT for general CMT field design in isolation (use custom-metadata-types).

Guides creation, design, and maintenance of Calculated Insights in Data Cloud: SQL authoring, dimension/measure definition, scheduling, streaming insights, and insight configuration tradeoffs. Trigger keywords: calculated insight, CI SQL, insight measure, insight dimension, streaming insight, insight schedule, Data Cloud metric, insight refresh. NOT for standard formula fields on sObjects, CRM Analytics SAQL metrics, or Data Cloud segment filter conditions that do not persist as insights.

Use this skill when configuring or troubleshooting Data Cloud identity resolution rulesets — matching rules, reconciliation rules, unified profiles, and cross-device identity linking. Trigger keywords: identity resolution ruleset, unified individual, match rule, reconciliation rule, unified profile, cross-device identity, Data Cloud deduplication, cluster creation. NOT for CRM duplicate management (Duplicate Rules / Matching Rules on standard objects), and NOT for Experience Cloud or Salesforce Identity login deduplication.

Use this skill when creating, filtering, refreshing, or activating audience segments in Salesforce Data Cloud. Covers segment types (Standard, Real-Time, Waterfall, Dynamic, Data Kit), segment refresh schedules, activation field mapping, and audience publishing. NOT for Marketing Cloud Contact Builder segments, NPC Actionable Segmentation, or Experience Cloud audience targeting.

Diagnose and mitigate Salesforce data skew — ownership skew (single user owns >10,000 records) and parent-child skew (>10,000 children under one parent) — that cause sharing recalculation slowness, group membership lock errors, and record-level locking failures. NOT for sharing model design decisions (use sharing-and-visibility) or query optimization (use soql-query-optimization).

Use this skill to configure Dynamic Forms (field and section visibility on Lightning record pages) and Dynamic Actions (button/action visibility rules) using Lightning App Builder. Covers enabling Dynamic Forms, converting page layout fields to Dynamic Form components, writing field visibility rules (field value, profile, permission, record type, device), and controlling action bar visibility per record context. NOT for page layout design or record type assignment (use record-types-and-page-layouts). NOT for building custom LWC components.

Use when designing or configuring public pages on an Experience Cloud site — guest user profile setup, page-level access settings in Experience Builder, object/field visibility for unauthenticated visitors, and explicit sharing rules that expose data on public pages. Triggers: 'configure public pages Experience Cloud', 'guest user profile setup', 'unauthenticated site access', 'public community page visibility', 'make page visible without login'. NOT for authenticated user features (use admin/experience-cloud-member-management). NOT for security hardening or remediation of guest user exposure (use security/guest-user-security).

Use this skill when adding external users to an Experience Cloud site, configuring self-registration, managing external user licenses, or customising the login and registration pages. Trigger keywords: add members to community, external user license, self-registration, customer portal login, partner user onboarding, ConfigurableSelfRegHandler. NOT for internal (Employee) user management, internal profile or permission-set assignments, or Experience Cloud page-layout / component design.

Use when setting up or auditing dedicated Salesforce integration users — including the Salesforce Integration user license, API-only profile, permission set layering, MFA waiver configuration, and login monitoring. NOT for standard user management.

Use when a Lightning record page, home page, or app page is slow to load or render — covers Experienced Page Time (EPT) analysis, component count reduction, progressive disclosure via tabs and conditional rendering, Lightning Experience Insights diagnostics, and DOM/XHR minimization strategies. Triggers: 'Lightning page is slow', 'EPT is high', 'record page takes too long to load', 'too many components on page', 'Lightning Experience Insights shows slow page', 'how to optimize Lightning page performance'. NOT for Visualforce page performance (separate concern). NOT for Apex or SOQL query optimization (use apex/apex-cpu-and-heap-optimization or data/soql-query-optimization). NOT for report or dashboard performance (use admin/report-performance-tuning).

Use this skill when configuring Marketing Cloud Engagement (formerly ExactTarget): business units, user roles, sender profiles, delivery profiles, send classifications, and account-level settings. NOT for MCAE/Pardot or Marketing Cloud Account Engagement configuration.

Use this skill when configuring MCAE (Account Engagement / Pardot) lead scoring models, grading profiles, score decay rules, or automation rules that fire on score/grade thresholds. Covers: scoring point values per activity, score decay for inactivity, Profiles for fit grading, combined MQL definitions (Score + Grade), and automation rules vs completion actions. NOT for Einstein Lead Scoring (Sales Cloud), not for Marketing Cloud Engagement journey scoring, not for Salesforce native lead scoring without Account Engagement.

Use when a report or dashboard is slow, timing out, hitting row limits, or consuming excessive system resources on large-volume objects — covers selective filter strategy, custom report type optimization, async report execution via Analytics API, dashboard refresh scheduling, and grouping/aggregation tuning. Triggers: 'report times out', 'report is slow', 'dashboard not refreshing', 'report row limit hit', 'too many report results'. NOT for CRM Analytics / Tableau CRM performance (separate skill). NOT for sharing-model or visibility issues causing missing rows (use admin/sharing-and-visibility). NOT for building or designing reports from scratch (use admin/reports-and-dashboards-fundamentals).

Distinguish the six real reasons a Salesforce query can 'fail', and the protocol for diagnosing before declaring. Covers: object doesn't exist, not queryable in edition, permission-denied, field-level errors, namespace prefix missing, API version mismatch. NOT for SOQL performance tuning (use soql-optimization-patterns). NOT for Bulk API payload issues (use bulk-api-2-patterns).

Use this skill to create, deactivate, freeze, or manage Salesforce users, assign user licenses and feature licenses, configure profiles and roles, set login hours and IP restrictions, and set up delegated administration. Triggers: adding a new user, deactivating a departing employee, license assignment, freezing a user account, delegated admin setup. NOT for permission sets (use permission-set-architecture) or sharing model design (use sharing-and-visibility).

Use when grounding an Agentforce agent with Data Cloud retrievers, DMO selection, chunking, and freshness windows. Triggers: agent grounding, retriever, DMO, data graph, RAG, vector index, citations. Does NOT cover Data Cloud ingestion pipelines or Data Cloud identity resolution tuning.

Use when configuring Model Builder in Salesforce to register external LLMs or select standard models for Agentforce and Einstein features. Covers model registration, API key configuration, model aliases, and cost/performance tradeoffs. NOT for Trust Layer configuration (use agentforce-trust-layer).

Custom Permissions in Apex: FeatureManagement.checkPermission, $Permission global variable, permission-set gating of feature code, Custom Permission metadata. NOT for CRUD/FLS enforcement (use security-apex-crud-fls). NOT for standard Salesforce permissions (use permission-set-architecture).

Use when reading or writing Hierarchy Custom Settings from Apex to resolve per-user/per-profile/org configuration. Covers `getInstance()` resolution order, DML cost, cache semantics, and when to prefer Custom Metadata Types instead. NOT for List Custom Settings, Custom Metadata Types deployment packaging, or the deprecated Setup UI for editing.

Use this skill when writing Apex that must check governor limits at runtime before executing expensive operations — guard clauses, early-exit patterns, Queueable re-queue on limit approach, and batch scope sizing. Trigger keywords: check governor limits before SOQL apex, defensive coding against limits apex, Limits.getDMLStatements getLimitDMLStatements, Limits class usage, guard clause governor limits, remaining SOQL queries Apex, heap size check before DML, LimitException handling. NOT for limit values themselves — see apex-cpu-and-heap-optimization. NOT for async job design choices — use the async-selection decision tree. NOT for org-level aggregate limit consumption — see architect/org-limits-monitoring.

Database.Savepoint / Database.rollback for partial-transaction undo: placement rules, ID reset, limit counters, nested savepoints, rollback after callout. NOT for Database.allOrNone=false partial success semantics (use apex-partial-dml). NOT for Queueable chained rollback (use apex-queueable-patterns).

Use when Apex needs to check what the running user is, can see, or can do — via UserInfo, FeatureManagement, FeatureManagement.checkPermission, or FeatureManagement.checkPermissionType. Covers custom permissions, permission sets, user licenses, and profile checks. NOT for FLS/CRUD (use Security.stripInaccessible or `with user_mode`), sharing rules, or external user license logic.

Use when diagnosing SOQL performance problems caused by formula fields, hitting formula compile-size limits, or deciding whether to replace a formula field with a stored field for indexing. Triggers: 'formula field slowing SOQL', 'compile size limit', 'cross-object formula spanning limit', 'formula field not indexable', 'LDV query full table scan', 'SOQL WHERE on formula'. NOT for formula syntax help, building formula expressions, or authoring new formulas from scratch — use admin/formula-fields for that.

Use this skill when implementing custom financial calculation logic in Financial Services Cloud — including portfolio performance metrics (IRR, TWR), wealth rollup recalculation after bulk loads, custom Apex aggregation for objects outside native FSC rollup scope, and Data Processing Engine integration for large-scale writeback. NOT for standard declarative rollup summaries on supported out-of-the-box FSC objects, nor for configuring the FSC Rollup-by-Lookup admin UI itself.

Use when writing Apex that calls Field Service Lightning scheduling APIs — AppointmentBookingService, ScheduleService, GradeSlotsService, or OAAS — to book, schedule, grade, or optimize service appointments programmatically. Trigger keywords: FSL Apex namespace, GetSlots, schedule service appointment via code, appointment booking API, FSL optimization API. NOT for standard Apex patterns unrelated to FSL, admin-level scheduling policy configuration, or declarative FSL scheduling.

Recovering from and preventing Apex governor limit errors: proactive Limits class checkpoints, savepoint-based partial recovery, BatchApexErrorEvent scope recovery, CPU timeout analysis, limit-safe coding patterns. Use when diagnosing LimitException failures or designing limit-safe Apex. NOT for general limits overview (use limits-and-scalability-planning). NOT for bulkification patterns (use governor-limits).

<!-- Managed by agent: keep sections and order; edit content, not structure. Last updated: 2025-09-29 -->

memwal

Karpathy's LLM Wiki pattern, built for Claude Code. Long-term memory for Claude via Obsidian: captures URLs, PDFs, GitHub, YouTube and compiles them into a structured Obsidian vault with citations that grows smarter every session. Second brain, zettelkasten, and autonomous research assistant in one. Keywords: llm-wiki, obsidian-plugin, knowledge-base, compounding-knowledge, claude-code, pkm, llm-memory.

This repository uses a modular, AI-optimized skill layout.

Optimize X/Twitter posts for maximum reach using algorithm insights. Use when writing tweets, improving post engagement, or analyzing why posts underperform.

Lossless LLM-optimized compression of source documents. Use when the user requests to 'distill documents' or 'create a distillate'.

Expert guidance for Tennessee Eastman Process (TEP) simulator - Python/Fortran chemical process simulation, fault injection with 20 IDV disturbances, fault detection with PCA/EWMA/CUSUM detectors, PI control systems, batch simulation CLI (tep-sim), and real-time web dashboard (tep-web). Use when working with TEP simulations, process control, or fault detection.

Context for developing the Emeraude Engine hierarchical scene graph system.

AI กลยุทธ์ Ads — Google Ads, Meta (Facebook/IG), TikTok Ads — campaign structure, audience, creative brief, budget allocation, bid strategy สำหรับตลาดไทย

วางแผน digital marketing campaign ครบ — brief, budget, channel mix, KPI, timeline

สร้าง Dockerfile CI/CD yaml และ monitoring config ที่ production-ready ไม่พัง

พัฒนาเกมด้วย Unity C# หรือ Godot GDScript พร้อม physics save system UI pattern

ผู้จัดการร้านออนไลน์ — Shopee/Lazada/Shopify, conversion funnel, cart abandonment, fulfillment, return policy

Four on-device ML models running on Mac Studio M3 Ultra via `http://127.0.0.1:18321`.

An interactive walkthrough. You (Claude) teach the user the Memory Kit by opening their actual files and showing what each part solves. Read real files, explain what you see, help the user write their

Persistent memory system for Claude Code. Your agent remembers everything across sessions and projects. Two-layer architecture: hot cache (MEMORY.md) + knowledge wiki. Safety hooks prevent context loss. /close-day captures your day in one command. Zero external dependencies, runs on existing subscription.

../../.claude/skills/close-day/SKILL.md

Detect PII, credentials, and corporate sensitive data in API responses, source code, files, headers, and database extracts

AI-powered SEO content creation toolkit. Research keywords, write optimized articles, and publish to WordPress/Ghost.

zero-skills

>

>

a file-based long-term memory using a single JSONL file, with append-only writes and recent-window search via bash + jq.