Claude Skills by fritzprix

Presentation creation, editing, and analysis. When Claude needs to work with presentations (.pptx files) for: (1) Creating new presentations, (2) Modifying or editing content, (3) Working with layouts, (4) Adding comments or speaker notes, or any other presentation tasks

Guide for implementing smooth, native-feeling animations using React's View Transition API (`<ViewTransition>` component, `addTransitionType`, and CSS view transition pseudo-elements). Use this skill whenever the user wants to add page transitions, animate route changes, create shared element animations, animate enter/exit of components, animate list reorder, implement directional (forward/back) navigation animations, or integrate view transitions in Next.js. Also use when the user mentions v...

Guide and principles for refactoring built-in MCP tools in LibrAgent. Use this skill when reviewing, refactoring, or optimizing existing built-in tools to reduce AI cognitive load, eliminate internal callback tool exposure, consolidate redundant tools, and ensure strict state synchronization across the system.

Manage the release process for LibrAgent. Use this skill to analyze changes, update the changelog intelligently, synchronize user documentation (docs/ & website/), and publish new versions.

Resumable execution guide for the "remove builtin_ prefix" refactoring on the refactor/remove-builtin-prefix branch. Use this skill when asked to continue, resume, or execute any phase of this refactoring. The skill contains the current state of every phase, exact files to touch, and precise mechanical changes required so work can be resumed after a context reset.

Evaluate pull requests and PR review comments against the real codebase, current file state, and PR diff. Use when a user wants to review PR feedback, decide which comments are valid, judge overall code quality or risk, determine whether a PR is worth merging, or apply approved review fixes.

Use when the user needs to diagnose and install runtime environment dependencies (Python, Node.js, etc.) for running LibrAgent. LibrAgent 실행에 필요한 Python, Node.js 등의 환경을 자동으로 진단하고 설치하도록 안내하는 마법사입니다.

Analyzes SQLite databases to identify schema issues, data inconsistencies, and relationship problems. Use when investigating database bugs, validating data integrity, debugging ORM mapping issues, or understanding database structure. Particularly useful for diagnosing ID mismatches, foreign key violations, and entity relationship errors.

Code recipes and explanation for synchronizing Rust backend pending tool approvals (YOLO mode/manual approval) to the frontend React UI when a user resumes or opens an existing agent session. Use this skill when modifying the AgentSession state to maintain approval channels or when fixing UI bugs related to missing pending tool executions upon page reload/session switch.

Resumable spec-driven guide for the Team Workspace / org lineage / scheduled task group refactoring in LibrAgent. Use when continuing, implementing, or reviewing this teamwork architecture so changes stay aligned with the agreed contract: workspace-scaffolded SSOT, teamwork as a meta-meta-skill, org as explicit org-created lineage teamwork, scheduled collaboration as separate task groups, and Settings-backed backend-enforced governance.

Guide for creating high-quality tool servers (MCP servers) that enable LLMs to interact with external services through well-designed tools. Use when building tool servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

Analyzes LibrAgent agent session trace files (.trace.json) to understand what an AI agent actually did during a session. Use when a user shares a .trace.json file, asks "what did the agent do?", wants to debug agent behavior, investigate tool call patterns, validate concurrency limits, or review session results. The trace file is the raw conversation record between the agent and its tools.

Parse .trace.json files and correlate with backend events and tool calls. Use when debugging agent behavior, investigating tool call patterns, or validating concurrency limits.

Monitor and enforce the frontend bundle size budget. Use when checking bundle size, preventing regressions, or validating build output against budget constraints.

Audit React Context usage, detect prop drilling, verify compound component patterns. Use when reviewing frontend code for proper Context consumption, checking AgentChatContext/AgentSessionContext usage, or enforcing compound component patterns.

Audit builtin MCP tool implementations against the Tool Design Manifesto. Use when reviewing builtin tools for compliance, checking context_prompt usage, validating text-first MCPResult design, or auditing canonical naming and session isolation correctness.

Run and verify SeaORM database migrations against in-memory SQLite. Use when applying migrations, verifying schema changes, or testing migration correctness.

Scaffold integration tests in src-tauri/tests/ following the project's strict rules. Use when creating new Rust tests, ensuring CI compatibility, or preventing false sense of test coverage from unit tests in src/.

Validate that builtin servers and external MCP managers maintain proper session isolation. Use when auditing session isolation, checking for cross-session state leakage, or verifying per-session MCPServiceProxy instantiation.

Manage Windows-specific process isolation, stdio pipe decoding, and ANSI code page handling. Use when debugging Windows-specific MCP server issues, fixing stdio encoding, or handling Windows path discovery.

A sample helper skill for Libr Assistant.

Analyze a workspace and generate or maintain a modular project documentation setup with a lean, concise agents.md entrypoint. Governs user directives, precautions, and desired persona, while providing selective on-demand reading of detailed guide files and immediate on-the-fly updates when code or rules change. Triggers: 'agent init', 'agents.md 생성', '워크스페이스 분석', 'agent guideline 생성', 'agents.md 모듈화', 'agent-init'. Not for LibrAgent runtime/harness facts (use libragent-harness-reference).

Cross-platform live desktop app UI control and window capture skill for LibrAgent. Supports Windows and Linux. Triggers on requests like '앱 화면 캡처', '앱 스크린샷', '앱 클릭 제어', 'capture app window', 'app screenshot', 'capture ui', 'click app button'.

Run benchmark-style evaluations on AI agents or tools using parent-child session delegation. Use when the user wants to test an agent's performance on a set of problems (e.g. SWE-bench style, tool capability benchmark, coding challenge evaluation). The parent session orchestrates: spawns child sessions to solve individual problems, collects answers via checkSession, and generates a consolidated report with pass/fail scores and analysis. Triggers on: "bench 테스트 해줘", "SWE-bench 돌려줘", "agent ben...

Audit and optimize existing LibrAgent assistant configurations by adding role-appropriate tools and pruning unrelated, bloated, or redundant ones. Use when the user wants to boost, audit, tune, clean up, or optimize existing specialists (e.g. removing github from a finance agent, or adding search to a researcher). Not for creating new assistants.

Google Calendar integration for end-user schedule management at runtime. Use when the user wants to view, create, update, or delete calendar events, or get a week summary ("show my schedule", "book a meeting tomorrow at 3pm", "what's on my calendar this week"). MVP supports Google Calendar API (OAuth2). On first use, guide Google Cloud OAuth setup, collect client_secret via hidden shell prompt, run setup.py --oauth, and store tokens in ~/.libragent/calendar_config.json. Not for LibrAgent agen...

Resume this agent session on a completion signal instead of clock polling. Use when wiring external hooks/--exec/webhooks that must POST into this session (wake URL is already in Agent Runtime Identity), or waiting for process exit, ticket/job status, file watchers — "call me back when done", "끝나면 깨워줘", "subscribe --exec", "register hook", "완료되면 콜백", "webhook으로 깨워줘", "run in background with hook". NEVER for pure time reminders or cron ("5분 뒤", "매일 9시") — use loop (session) or schedule (global...

Comprehensive computer diagnosis and troubleshooting. Use this skill when a user reports issues with their computer (e.g., "my computer is slow", "it's freezing", "loud fan noise", "no disk space") to analyze system metrics (CPU, RAM, Disk, Network) across macOS, Windows, and Linux, and generate a detailed report with actionable recommendations.

Use when the user needs to evaluate the same question from different perspectives by orchestrating multiple specialized child sessions, collecting their independent conclusions, and reconciling disagreements through parent-mediated follow-ups. Suitable for code review triangulation, architecture or risk assessment, security vs performance tradeoff analysis, or any bounded decision that benefits from 2-4 distinct expert viewpoints—not for persistent teams (teamwork/org) or single one-off deleg...

Retrieve full pre-compaction conversation history from saved transcript files when the compact summary is insufficient or earlier session details are missing. Use when asked about past decisions, tool results, or content that predates the latest compaction; when the agent would say it does not remember; or when the compact summary's Context recovery / fallback note names a transcript path. Triggers: "what did we discuss earlier", "before the context was reset", "older messages", "pre-compacti...

End-user data visualization — turn CSV, Excel, or JSON into standalone HTML charts and small dashboards. Use when the user wants charts, trends, or visual reports from tabular data ("chart this CSV", "show monthly sales trend", "make a dashboard from this spreadsheet"). Not for document editing (docx/pptx) or raw format conversion (to-md). Triggers on: "차트 만들어줘", "데이터 시각화", "plot this data", "dashboard from CSV".

Advanced multi-source research and comprehensive report generation. Use when the user requests in-depth analysis on a specific topic. This skill guides you through (1) adaptive planning, (2) information gathering via tools or delegation, (3) iterative synthesis, and (4) high-quality Markdown report production.

Delegate work between LibrAgent AI agent sessions using sub-agent sessions. Use when an agent needs to spawn, brief, monitor, or troubleshoot a child session with `agent__spawnSession`, `agent__checkSession`, or `agent__messageToSession`, especially when deciding whether the child really needs parent workspace state, workspace instructions, or workspace-scoped skills. For generator-evaluator / strict acceptance criteria / proof before done, load `delegation-eval-loop` after this skill's spawn...

Generator-evaluator loop for delegated sub-agent work: parent evaluates, child generates. Use layered verification (Deterministic, Invariant Gate, Trajectory/reliability, Semantic), sprint contracts with checkbox acceptance criteria, and targeted re-steers via agent__messageToSession. Use when briefing with strict acceptance criteria, evaluating child results from agent__checkSession, preventing premature "done" without proof, or when delegate routes here for high-stakes handoffs. Triggers: g...

Split a large task into independent subtasks, delegate them to child sessions for parallel execution, and merge the results. Use when a task can be broken into non-overlapping pieces that don't depend on each other's output. Not for consensus/review (use consensus-delegation) or benchmarks (use bench). Triggers: "분할 정복", "병렬 처리", "parallel execution", "split and process".

Use when the user needs to create, edit, or analyze professional Word documents (.docx) with support for tracked changes, comments, formatting preservation, and text extraction.

Integrates with any IMAP/SMTP mail server (Gmail, Outlook, Naver, Kakao, custom servers, etc.). Use when the user wants to read, send, search, reply to, or manage emails. On first use, collect the email/server settings, capture the password through a single hidden shell prompt, and run setup_account.py non-interactively to store credentials in a local config file with restricted permissions. Subsequent requests use the stored config without re-asking for credentials. Triggers on requests like...

Train custom LLM models locally using conversations exported from LibrAgent. Use when the user requests to fine-tune a model, train on past chats, export chat datasets, or configure custom agent models. Triggers on: "fine-tune model", "모델 학습시켜줘", "내 대화 데이터로 학습해줘", "export dataset", "대화 데이터셋 추출".

Implement a Creator-Reviewer quality gate loop. The Creator generates an artifact, and the Gatekeeper/Reviewer verifies it against quality criteria. If approved, it passes; if rejected, the Creator must perform rework and resubmit. Useful for strict code reviews, verification checks, or quality assurance. Triggers: "게이트키퍼", "리뷰 루프", "검증 게이트", "품질 검증", "gatekeeper", "reviewer loop", "quality gate".

End-user Git and GitHub workflow orchestration for the user's own repositories. Use when the user wants feature branches, commits, pull requests, PR review, merge, tags, or GitHub releases ("create a PR", "merge PR #42", "ship v1.2.0", "review this pull request"). Uses workspace git + GitHub CLI (gh). Optional GitHub MCP can supplement but is not required. Not for LibrAgent product releases or internal repo maintenance. Triggers on: "PR 만들어줘", "브랜치 파서", "PR 머지", "릴리즈 태그", "create pull request...

Implement a central Coordinator (Hub) that manages, distributes, and merges tasks performed by specialized worker sessions (Spokes). Spokes communicate only with the Hub and not with each other. Useful for ad-hoc project management and complex workflow distribution. Triggers: "허브 스포크", "중앙 통제", "작업 배분", "hub and spoke", "coordinator pattern", "centralized workflow".

Python CLI wrapper for Instagram interaction using instagrapi. Use when the user wants to: (1) post photos/reels with captions, (2) reply to comments, (3) view feed/posts, (4) like/unlike posts, (5) follow/unfollow users, (6) view profile info. On first use, guide the user through credential setup (username + password via hidden prompt). Store config in ~/.libragent/ig_config.json and session settings in ~/.libragent/ig_session.json. Subsequent requests use the stored session without re-authe...

Analyzes conversation sessions to extract key insights, decisions, and technical details, then saves them to the knowledge base. Use this skill when asked to "summarize what I learned today," "record key points from recent sessions," or "sync current project context to long-term memory."

On-demand LibrAgent runtime facts: system-prompt layers, tool naming (server__tool), session/workspace isolation, skills progressive disclosure, when to call agent-init, and verification habits. Use when unsure how LibrAgent injects context, how sub-agents inherit (or do not inherit) workspace/instructions/skills, which instruction files load, or what belongs in assistant systemPrompt vs workspace agents.md vs skills. Triggers: harness, system prompt layers, agents.md vs SOUL, session workspa...

Implement, verify, and deploy a host MediaAssist plugin that converts audio/image/video into text when the LLM rejects multimodal input (HTTP 400). Use when media-assist placeholders appear, assistPluginStatus reports missing, listenContent/seeContent succeed but the next completion fails, or the user asks to install an ASR/OCR assist plugin. Triggers: media-assist, MediaAssist, multimodal 400, deployAssistPlugin, harness-plugins, libragent-plugin.

PRIMARY skill for clock-based session wakes via scheduleCallback. Use when the user asks for reminders, delays, or recurring checks inside the active conversation — "remind me in 5 minutes", "tomorrow at 9", "매일 아침 확인해줘", timers, and wall-clock recurrence bound to this chat. NEVER for process exit, build/test completion, kanban/ticket done, webhooks, or file-watcher completion — use call-me-back. Prefer this over global schedule for in-session time requests; escalate to schedule only for perm...

Restructure a living explicit org in LibrAgent without dissolving it. Use when an org already exists and you need to add/remove/merge roles in ROLES.md, update the org constitution (agents.md, MISSION.md), remove or retire org child sessions, reassign KANBAN owners, or record structural changes in coordination files. Not for initial org creation (use org), initial scaffolding (use teamwork), org dissolution, or archive.

Run explicit org-based teamwork in LibrAgent. Use when collaboration needs durable org identity, org-visible child sessions, org-root resume behavior, or clear parent/sibling org context while preserving normal parent workspace inheritance.

Implement a turn-based Driver-Navigator pair programming workflow. One agent (Driver) focuses on implementation and writes code, while the other (Navigator) reviews, validates, and suggests improvements in real time. Roles can swap dynamically based on tasks. Triggers: "페어 프로그래밍", "공동 작업", "드라이버 네비게이터", "pair programming", "driver navigator", "collaborative coding".

Execute sequential, stage-based assembly line tasks where the output of one stage becomes the input of the next stage. Useful for progressive refinement workflows like Research -> Draft -> Review -> Format. Not for parallel execution (use divide-conquer) or consensus (use consensus-delegation). Triggers: "파이프라인", "순차 처리", "단계별 처리", "pipeline", "sequential processing".