libr-agent

Analyze codebase against new feature requirements, map affected modules and dependencies, identify architectural risks, and propose a structured refactoring and implementation plan before writing code. Use when starting a new feature, planning refactoring, analyzing codebase impact, or reviewing feature feasibility.

Create a GitHub pull request with gh, target the correct base branch, push only committed work, and bind related issues via Fixes/Closes keywords. Use when asked to create a PR, open a pull request, push and open PR, link/bind/associate an issue to a PR, add Fixes #N, or close issues on merge.

Comprehensive review and audit of uncommitted local code changes in git working copy (staged, unstaged, untracked). Use when asked to review local changes, audit git diff, check uncommitted work before commit/PR/push, or inspect working copy edits for potential bugs, security issues, formatting, or regression risks.

Analyze Harbor benchmark jobs and ATIF trajectories, identify evidence-backed weaknesses across LibrAgent builtin tools, prompts, agent guidance, execution policy, and benchmark instrumentation, then design controlled improvements and rerun comparisons. Use when analyzing Harbor or Terminal-Bench results, optimizing the harness, investigating tool-call failures or retries, auditing prompt/context efficiency, or running repeated BM → analysis → improvement cycles.

Re-anchor an AI agent to its SOUL.md persona by re-internalizing tone, rules, and identity. Use when the agent drifts into generic/corporate responses, is explicitly asked to reconnect with its soul, or needs to bootstrap a missing SOUL.md. SOUL content is already injected into the system prompt as

Re-anchor an AI agent to its `SOUL.md` persona by locating the active soul file, reading it, and re-internalizing its tone, rules, and identity. Use when the agent is starting fresh, drifting into generic/corporate responses, explicitly asked to read its soul, or needs to resync with the dedicated persona layer loaded from `.github/SOUL.md`, `SOUL.md`, or lowercase variants.

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 agent cron automation (schedule / session-schedule). Triggers on: "일정 보여줘", "캘린더 확인", "미팅 예약", "show my calendar", "schedule a meeting".

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.

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".

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: "메일 보여줘", "이메일 확인", "send email", "받은 편지함", "메일 보내줘", "메일 검색".

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".

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", "merge PR".

Use when the user needs to create, edit, or analyze presentations (.pptx files) with support for layouts, formatting, comments, or speaker notes.

Repository wiki engine: bi-directional linking, catalog.json, frontmatter injection, slug-based link resolution, backlink generation, and structured directory routing (core/reference/drafts/archive). Use when organizing docs into a wiki with [[slug]] links, generating catalog.json, injecting frontmatter, building backlinks, validating broken links, or migrating flat docs into core/reference/drafts/archive. For binary document conversion (PDF/DOCX/PPTX/XLSX) or workspace index.md generation, use the workspace-indexer skill instead. Triggers: "repo wiki", "catalog.json", "bi-directional links", "backlinks", "docs-tool", "문서 위키", "repo-wiki".

Guide for creating and validating agent skills. Use when authoring or updating a SKILL.md, writing frontmatter, structuring scripts/references/assets, or checking a skill before deployment. Triggers on create skill, write skill, skill frontmatter, validate skill, fix skill YAML. For installing a finished skill, use skill-deployer instead.

Deploy a validated user or workspace skill to user_skills/ or .libragent/skills/. Use after skill-creator validation. NOT for system_skills or app-bundled skills. Triggers: deploy skill, install skill, global skill, workspace skill, user_skills.

Build and scaffold a multi-agent collaboration workspace with the right coordination model, shared operating files, and role-specific skills. Use when a user wants to create a team, crew, task force, asynchronous collaboration loop, specialist handoff workflow, or reusable shared workspace for multiple agents, then route execution to the right teamwork skill.

Python CLI wrapper for Telegram interaction using Telethon (MTProto protocol). Use when the user wants to: (1) send messages, (2) read messages from chats/channels/groups, (3) list chats, (4) download files, or (5) search messages. On first use, guide the user through authentication (API ID/Hash → phone → code → 2FA password). Store session and config in ~/.libragent/telegram_config.json. Subsequent requests use the stored session without re-authentication. Triggers on requests like: "텔레그램 메시지 보내줘", "텔레그램 확인", "send telegram", "텔레그램 채널 확인", "텔레그램 파일 다운로드".

Explore a workspace to (1) convert binary documents (PDF, PPTX, DOCX, XLSX) into text/Markdown and (2) build an index.md file with a keyword map and file inventory. Use when the user asks for binary document conversion, document indexing, index.md generation, keyword-map creation, workspace file inventorying, or PDF/PPTX/DOCX/XLSX text extraction.

Python CLI wrapper for X (Twitter) interaction using Twikit. Use when the user wants to: (1) post tweets (with text or media, including thread replies), (2) view home timeline, (3) view a user's tweets, (4) search tweets, (5) like/favorite a tweet, (6) retweet a tweet, or (7) delete a tweet. On first use, guide the user through credential setup (username, email, password, optional TOTP) or browser cookie setup. Store config in ~/.libragent/x_config.json and session cookies in ~/.libragent/x_cookies.json. Subsequent requests use the stored session without re-authentication. Triggers on requests like: "트윗 올려줘", "트위터 피드 보여줘", "post a tweet", "like tweet", "retweet", "delete tweet".

Critically audit refactorings and design decisions against the real codebase, verify claims vs code, score only relevant quality axes, and write evidence-based tech reports. Use after refactors, when reviewing agent-reported work, or when asking for architecture / ISP / DRY / token-cost / reliability feedback. For builtin MCP tool audits, prefer critique-builtin-tool or lean-builtin-tool-auditor instead.

Critically audit refactorings and design decisions against the real codebase, verify claims vs code, score only relevant quality axes, and write evidence-based tech reports. Use after refactors, when reviewing agent-reported work, or when asking for architecture / ISP / DRY / token-cost / reliability feedback. For builtin MCP tool audits, prefer critique-builtin-tool or lean-builtin-tool-auditor instead.

Analyze installed tools and existing assistant configurations to actively propose and create specialized LibrAgent assistants via agent__create. Use when the user wants to recruit, create, or build a domain expert or specialist agent, utilizing a proactive "Architect" workflow that maps available inventory tools to functional gaps. Not for workspace agents.md (agent-init), teamwork/org, or registering MCP servers.

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.

Guide for creating builtin MCP tools in LibrAgent. Use when creating a new builtin MCP server, adding tools to existing builtin servers, refactoring tool implementations to follow best practices, or auditing tool compliance with the Tool Design Manifesto v2.1.

Audit and critique builtin MCP tool implementations in LibrAgent. Use when auditing existing builtin MCP server implementations for compliance, reviewing pull requests that add or modify builtin tools, validating tool implementations against the Tool Design Manifesto v2.1, or identifying potential issues before they reach production.

Audit builtin MCP tool implementations in LibrAgent for schema accuracy, minimal complexity, and non-bloated hints. Use when reviewing builtin tools for compliance, validating tool schemas, checking for over-engineering, or ensuring next-action hints are concise and relevant.

Use when the user needs to diagnose and install runtime environment dependencies (Python, Node.js, uv) for running LibrAgent or MCP servers. Use on new machines, MCP "command not found" errors, or missing Python/Node runtime failures. LibrAgent 실행에 필요한 Python, Node.js 등의 환경을 자동으로 진단하고 설치하도록 안내하는 마법사입니다.

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

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".

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".

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."