개발 스킬

Design autonomous coding agents using implementation patterns for tool calls, permission checks, browser interaction, and saved task state. Code examples and checklists help structure agent behavior and workflows that include human approval.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Designing a coding agent's execution loop
• Defining tool interfaces for files and commands
• Adding permissions and human approval steps

Split independent debugging or repair tasks among multiple AI agents. Define a focused scope, constraints, and expected report for each agent, then review their changes, check for conflicts, and test the combined result.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigating unrelated failures across test files
• Assigning separate subsystems to different agents
• Writing focused tasks with clear constraints

Set up users, organizations, roles, and dataset sharing in cognee. The skill explains SDK and HTTP authentication, helps investigate permission errors or missing datasets, and clarifies how access settings separate each user’s stored data.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Share datasets with specific users or roles
• Organize data access across teams and organizations
• Configure SDK identities and HTTP authentication

Manage cognee database migrations, from checking migration status and recovering blocked writes to creating schema or data updates. It also guides dataset backups, restores, and transfers using cognee’s portable COGX archive format.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Recover writes blocked by a failed migration
• Create migrations for database structure or stored data
• Back up and restore datasets with COGX

Generate page and component folder structures with a command, keeping related files together by feature. Create tabbed page shells, starter tests, and README files, and register page routes within the supplied frontend structure.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Starting a page with a consistent folder structure
• Creating a page shell with multiple tabs
• Adding components within a feature

Refactor state held in Redux or React Context by separating API data, URL settings, shared interface state, and local component state. Move each part to React Query, nuqs, Zustand, or React’s local state hooks.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Migrating away from Redux or React Context
• Removing duplicate storage of API responses
• Sharing filters and pagination through URLs

Review code changes using a knowledge graph, a map of code relationships, to assess risk and affected behavior. Organize findings by severity, identify missing tests, suggest fixes, and provide a merge recommendation.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Prioritizing review findings by risk
• Checking how changed functions affect other code
• Identifying missing tests and proposing test cases

Build or refresh a knowledge graph, a map of code relationships used for code review. Choose a full rebuild or an incremental update, then report the operation's status and summary.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Setting up the graph for a repository's first review
• Refreshing the graph after switching branches
• Updating review data after a large refactor

Explore an unfamiliar codebase using a graph of code relationships. Inspect its structure, find functions and classes, trace calls and imports, follow execution paths, and locate large functions for closer investigation.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Understanding the structure of an unfamiliar codebase
• Finding functions and classes by name or keyword
• Tracing calls, imports, and execution paths

Plan refactoring with dependency analysis, which shows how code parts rely on each other. Find candidates and unreferenced code, preview and apply renames, and compare the resulting impact with the original plan.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Finding refactoring candidates and unreferenced code
• Previewing edits before applying a rename
• Checking affected dependencies and execution paths

Review all changes in a pull request or branch against its base branch. Use a knowledge graph, a map of code relationships, to report affected files and functions, test coverage, API compatibility issues, and recommended actions.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing all commits in a pull request
• Checking a branch's changes against its base
• Finding callers missed by public API changes

Review code changes against the previous commit and identify affected files and functions. Use dependency relationships to assess risk, check missing tests, and produce a focused report with issues and recommendations.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reviewing changes against the previous commit
• Checking how a change affects other functions
• Finding missing tests for high-risk changes

Investigate bugs using a graph of code relationships. Find relevant functions, trace calls and execution paths, check recent changes, and assess what a proposed fix could affect before reading and changing the implementation.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Narrowing down code related to a bug
• Tracing the execution path that triggers an issue
• Checking whether recent changes caused a bug

Analyze large logs, test results, API responses, and files outside the conversation, then return focused findings. It guides agents to save, process, index, and search outputs while limiting how much raw data enters their working context.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Extracting errors from large logs
• Summarizing test failures and build warnings
• Inspecting JSON and CSV data

Route codebase exploration, file analysis, and web research through context-mode tools in Antigravity CLI. Process large outputs outside the conversation and return focused findings, with indexed content available for later searches.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Explore a codebase and summarize key findings
• Extract and count information in a file
• Index web content for follow-up searches

Coordinate multiple agents to maintain context-mode, from sorting GitHub issues and reviewing pull requests to preparing releases and announcements. Workflows require reproduced bugs, source evidence, test-first changes, and checks across supported platforms.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigating reported bugs and their history
• Reviewing contributor pull requests
• Preparing releases and compatibility checks

Upload local script files to a Google Apps Script project by specifying its project ID and an optional source folder. The command supports script, HTML, and manifest files, and replaces all files in the destination project.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Uploading local scripts to an Apps Script project
• Using a specific folder as the upload source
• Replacing project contents with a local set of files

Manage Google Apps Script projects from the command line. Create projects, retrieve or update source files, inspect execution status, and fetch metrics such as execution counts and active users to review script activity.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Creating a new Apps Script project
• Retrieving and updating script source files
• Checking execution status

Guide an RxJS 7 project to RxJS Next by testing existing behavior, reviewing how subscriptions start and end, and validating small batches of changes. Record approved behavior choices, verification results, and unresolved blockers in migration reports.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Assess RxJS usage and test coverage before migration
• Plan how subscriptions and cleanup should behave
• Migrate code and TestScheduler tests in small batches

Learn how to author a third-party gbrain skillpack through a reference example. It explains required files, ten validation criteria, tests, and evaluation coverage, helping authors understand what to check before packaging and publishing.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Learning the structure of a gbrain skillpack
• Checking requirements before publication
• Understanding test and evaluation files

Prepare a proven local skill for reuse in gbrain’s bundled collection. Guide removal of private details, generalize instructions and triggers, preview copied files, and verify the result before the user reviews and approves a commit.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Prepare a proven local skill for wider reuse
• Remove private details from skill examples
• Copy a skill and its declared source files into gbrain

Turn incoming SMS, meeting events, and social mentions into cited pages in GBrain, a knowledge store. The workflow extracts people and other entities, updates timelines, sanitizes content, and preserves failed payloads for retry.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Save SMS events to a sender’s timeline
• Route completed meetings to meeting ingestion
• Record social mentions with source links

Turn a feature into an agent skill or improve an existing one. Define purpose-specific quality criteria, review outputs with models from three providers, then add tests and check that user requests reach the intended skill.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Turn a reusable feature into an agent skill
• Audit an existing skill for missing parts
• Check quality after fixing or extending a skill

Create skills that follow GBrain’s required structure, including workflow steps, expected output, and failure handling. Check for overlapping triggers, update the skill registry and routing guide, and verify the result with conformance tests.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Create a skill for an uncovered user request
• Check for overlap with existing skill triggers
• Update skill registration and routing