agent-generation
Medium Risk 70Generate Project-Specific Claude Code Agents
Generic assistants miss project conventions. This skill helps create specialized Claude Code agents using real architecture, domain, and tech stack details.
Unified search
Start with the task. Skillstore will show complete packs first, then individual skills when they are a better match.
Showing results for "agent"
Use these when you need one narrow capability instead of a whole pack.
Generate Project-Specific Claude Code Agents
Generic assistants miss project conventions. This skill helps create specialized Claude Code agents using real architecture, domain, and tech stack details.
Coordinate Multi-Agent Coding Swarms
Parallel AI coding can become hard to coordinate across tasks, files, and reviews. This skill provides prompts and tool steps for NTM, Agent Mail, Beads, and BV.
Build Consistent TypeScript Backends
Backend services often drift into mixed patterns and hard-to-test code. This skill gives Claude, Codex, and Claude Code structured guidance for Express, Prisma, validation, monitoring, and tests.
Create Isolated Git Worktrees
Parallel Git work can mix branches and uncommitted changes. This skill guides safe worktree setup, checks, cleanup, and review workflows.
Why this variant is first
doyajin174-using-git-worktrees
2026-09-09
obra-using-git-worktrees
2026-09-09
sickn33-using-git-worktrees
2026-09-09
Deploy Google ADK Agents
Deploying ADK agents across Google Cloud targets requires many infrastructure choices. This skill guides target selection, deployment commands, secrets, CI/CD, testing, and recovery.
Audit UI and Prepare Evidence-Based Design Plans
Interface reviews can mistake intentional differences for defects and recommend changes without evidence. This skill verifies design findings and prepares selected implementation plans while preserving product identity.
Manage IdeaVim YouTrack Issues
Teams working on IdeaVim need consistent YouTrack workflows instead of GitHub Issues. This skill gives agents the ticket conventions, commands, tags, and release steps for VIM issues.
Check Website and Agent Ratings
Assessing a known website or agent requires relevant feedback and clear evidence limits. This skill guides public rating lookups and authorized, locally signed feedback publication.
Assign Models Across Chats and Scheduled Tasks
Using one expensive model across every chat can exhaust limits, while careless downgrades can reduce quality. This skill guides model assignments using task importance, frequency, current plan rules, and quality checks.
Organize Open Work and Forgotten Commitments
Tasks and promises become scattered across conversations, notes, and project records. This skill consolidates accessible context into a prioritized list with owners, blockers, and next actions.
Build Persistent Azure AI Agents with .NET
Persistent agent workflows require coordinated threads, messages, runs, tools, and cleanup. This skill provides focused .NET patterns for implementing those workflows with Azure AI Agents.
Automate Browser Testing and Scraping
Browser scripts often fail because selectors, waits, and browser state are fragile. This skill guides reliable Playwright and Puppeteer automation for tests, scraping, and agent workflows.