lark-agent

Latest Astro features from versions 4.x through 5.x (mid 2024 to 2025)

Latest React and Next.js features for past 1.5 years (mid-2024 to 2026)

Latest React features from React 19 and React Compiler (past 1.5 years - mid 2024 to 2026)

Search and navigate The Fold's skill lattice using meta-tooling. Use for finding functions, exploring dependencies, type-aware queries, and cross-reference analysis. Invoke when searching for capabilities, exploring the codebase structure, or finding how functions relate.

Use when creating or modifying code in nomarr/components/. Components contain heavy domain logic (ML, analytics, tagging). Only ml/backend_essentia.py may import Essentia.

Use when creating or modifying code in nomarr/persistence/. Persistence handles database and queue access. Never stores business logic.

layer-testing

Master responsive layout design using modern CSS (Flexbox, Grid), mobile-first approach, and breakpoint strategies. Create layouts that adapt beautifully across all devices while maintaining accessibility and performance. Includes container queries, aspect ratios, and advanced responsive patterns.

Configure lazygit TUI including config.yml setup, custom pagers (especially delta integration), themes, keybindings, and custom commands. Use when setting up lazygit, configuring git diff viewers, integrating delta, or customizing lazygit behavior. Keywords: lazygit, delta, git diff, pager, lazygit config, config.yml, git TUI, diff viewer

LCOV tooling - finding gaps, parsing coverage files, marker syntax

Develop the go-lcpd daemon/tools (Go). Follow repo principles (robustness, TDD, lint) and validate with make test/lint/gen.

Identify and exploit LDAP injection vulnerabilities in web applications that interact with LDAP directory services. LDAP injection attacks manipulate queries sent to LDAP servers, enabling authenticat

THE MOST CRITICAL FEATURE FOR HODGES & FOOSHEE REALTY. Ultimate distressed property intelligence system tracking 22 distress signals across financial, life event, property, legal, and market categories. Self-improving AI that monitors performance, spawns specialized skills to fix bottlenecks, runs A/B tests, and continuously optimizes lead conversion. This is the game-changer that finds homeowners in crisis BEFORE anyone else does. Use for ALL lead generation tasks, pipeline optimization, multi-source data ingestion, and automated lead intelligence.

Create CRPO-compliant lead magnets for therapy practices that build email lists without crossing ethical boundaries. Use when planning top-of-funnel content to capture leads. Creates concepts for guides, frameworks, and educational resources. CRITICAL: NO diagnostic assessments, NO outcome promises, NO psychological tests. Triggers on: create lead magnet, build email list, free resource ideas, content upgrade concepts. Outputs educational lead magnet concepts that provide genuine value while staying compliant.

Qualify and score sales leads using proven frameworks and data-driven criteria

Build, test, and debug Lean 4 projects using Lake. Use when building the ComputationalPaths project, checking for errors, running tests, cleaning artifacts, or debugging Lean 4 compilation issues.

**Build incrementally, structure before solving, trust the type checker.** Lean's type checker is your test suite.

Extract learnings from the current conversation and persist them to CLAUDE.md, skills, or repo-specific documentation.

This skill should be used when a user asks to learn a specific skill or knowledge area using the pattern '帮我学习一下xx技能/知识'. The skill provides a comprehensive 9-step learning journey including concept discovery, practical applications, code examples, resource recommendations, community tracking, and related topic suggestions. It covers the complete learning cycle from foundational understanding to advanced community engagement.

learning-objectives

Generate measurable learning outcomes aligned with Bloom's taxonomy and CEFR proficiency levels for educational content. Use when educators need to define what students will achieve, create learning objectives for curriculum planning, or ensure objectives are specific and testable rather than vague.

Expert in lease abstraction and critical terms extraction. Use when abstracting lease agreements, extracting key dates, identifying critical provisions, or creating lease summaries. Key terms include lease abstraction, critical dates, rent schedule, operating costs, renewal options, termination rights, default provisions, use clause, assignment clause, Schedule G special provisions

Generate comprehensive undergraduate lecture notes for social sciences (especially economics) with mathematical foundations, daily-life examples, and practice questions. Use when user asks to create, generate, or write lecture notes, lecture materials, or teaching content. Supports Turkish and English output, Obsidian-compatible markdown with LaTeX/TikZ, and optional syllabus integration.

Use when modifying, removing, or refactoring code that lacks test coverage. Emphasizes the danger of untested changes and the RGR workflow to add characterization tests before modifications.

Extrai texto de documentos jurídicos escaneados em PDF usando OCR otimizado para linguagem jurídica brasileira. Use quando precisar converter PDFs escaneados (sentenças, petições, acórdãos) em texto editável com alta precisão. Suporta documentos de baixa qualidade, multi-colunas, tabelas e termos jurídicos específicos.

Scan code for client project names, proprietary tool references, and legally sensitive content

Framework for demonstrating AI capabilities in legal contexts. Provides detailed personas across tenant law, business contracts, startup disputes, employment claims, and consumer protection with progressive complexity scenarios. Use when: (1) Demonstrating AI-powered legal triage or intake systems, (2) Showcasing responsible AI-assisted client interactions, (3) Training staff on appropriate AI use in legal contexts, (4) Creating realistic scenarios for legal tech presentations, (5) Developing educational materials about AI in legal services, or (6) Testing AI-powered legal information systems in controlled environments.

AI-powered insurance for renters, homeowners, pet, and life coverage.

Converts a Refound/Lenny Skill into a high-density, agent-executable Skill Pack (Agent Skills standard). Output must be in English.

Generate lesson content following 4-Layer Teaching Framework with standardized metadata and Docusaurus conventions

Run Python code in lesson context with proper uv and venv handling for agent-spike project. Activate when user wants to run tests, demos, or CLI commands for lessons in lessons/ directories. Project-specific for agent-spike multi-agent learning.

Creates ALL task types (implementation, refactoring, test). Generates task documents from templates, validates type rules, creates in Linear, updates kanban. Invoked by orchestrators.

Updates ALL task types (implementation/refactoring/test). Compares IDEAL plan vs existing tasks, categorizes KEEP/UPDATE/OBSOLETE/CREATE, applies changes in Linear and kanban.

Worker that runs existing tests to catch regressions. Auto-detects framework, reports pass/fail. No status changes or task creation.

Security audit worker (L3). Scans codebase for hardcoded secrets, SQL injection, XSS, insecure dependencies, missing input validation. Returns findings with severity (Critical/High/Medium/Low), location, effort, and recommendations.

Dead code & legacy audit worker (L3). Checks unreachable code, unused imports/variables/functions, commented-out code, backward compatibility shims, deprecated patterns. Returns findings.

Concurrency audit worker (L3). Checks race conditions, missing async/await, resource contention, thread safety, deadlock potential. Returns findings with severity, location, effort, recommendations.

Application lifecycle audit worker (L3). Checks bootstrap initialization order, graceful shutdown, resource cleanup, signal handling, liveness/readiness probes. Returns findings with severity, location, effort, recommendations.

Orchestrates full project bootstrap from Replit export to production-ready structure

Upgrades npm/yarn/pnpm dependencies with breaking change handling

Upgrades .NET NuGet packages with breaking change handling

Upgrades Python pip/poetry/pipenv dependencies with breaking change handling

Restructures React frontend from monolith to component-based architecture

Generates .NET Clean Architecture backend structure from entity definitions

Migrates mock data from Drizzle ORM schemas to C# MockData classes

Removes all Replit artifacts from exported projects (configs, packages, code comments)

Generates GitHub Actions CI workflow configuration

Generates project-specific .claude/commands for Claude Code

Generates individual .claude/commands files from templates