bootstrap
High Risk 38Bootstrap Repository Context for Coding Agents
Coding agents lose accuracy when repository guidance is missing or outdated. This skill creates reviewed context files, confidence labels, and risk boundaries with human approval.
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.
Bootstrap Repository Context for Coding Agents
Coding agents lose accuracy when repository guidance is missing or outdated. This skill creates reviewed context files, confidence labels, and risk boundaries with human approval.
Orchestrate Issues Through Review and QA
Multi-agent issue delivery can lose state, mix roles, and skip safeguards. This skill coordinates implementation, review, QA, escalation, and pull request creation through agent-flow.
Search the Web with Exa.ai
AI agents often need current web results with clear search intent. This skill lets Claude, Codex, and Claude Code query Exa.ai through a simple Node.js wrapper.
Improve Skills From Agent Sessions
Skill authors need clear evidence from real agent sessions. This skill extracts transcripts and turns them into prompts for improving or creating skills.
Test Skills With Subagents
Process skills often fail when agents face time pressure, authority pressure, or sunk cost. This skill gives a repeatable subagent test workflow to expose failures and improve instructions.
Troubleshoot LiveKit Letta Voice Agents
Voice agent failures are hard to diagnose when audio, WebRTC, tokens, and process state interact. This skill gives focused checks, workflows, and helper scripts for LiveKit and Letta debugging.
Draft Domain-Specific Requirements
Teams lose time when requirements are vague or forced into one template. This skill guides Claude, Codex, and Claude Code to create clear, testable requirements for each domain.
Validate Failing Tool Output
Developers need predictable failure output when testing agent tool handling. This skill prints stdout, stderr, and a simulated stack trace before exiting with an error.
Find and Install Agent Skills
Finding reusable agent skills across a registry can take time. This skill searches prompts.chat, retrieves selected packages, and installs their files for Claude.
Build Genkit Dart AI Apps
Dart teams need current patterns for adding generative AI to applications. This skill guides Genkit flows, tools, providers, streaming, MCP, and typed schemas.
Set Up Firebase Projects with AI Agents
Firebase setup often requires CLI, authentication, and project context checks. This skill guides Claude, Codex, and Claude Code through Firebase setup workflows.
Search and Extract Web Data with Firecrawl
Web research often needs clean page text, links, and search results from many sources. This skill shows how to use Firecrawl CLI workflows to collect and organize that data.