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.
Create Slash Commands for AI Workflows
Repeated AI workflows are slow when users rely on long natural language prompts. This skill helps define concise slash commands with routing, validation, chaining, and help text.
Build CloudBase Node Auth Flows
Server-side CloudBase auth work can mix caller identity, user lookup, and custom login details. This skill guides Node.js agents through correct SDK methods and secure backend patterns.
Implement React View Transitions
React view transitions are easy to misplace, causing silent or noisy animations. This skill guides route, Suspense, list, and shared element animation choices.
Build pytm Threat Models as Code
Threat modeling often becomes outdated and disconnected from architecture changes. This skill helps create pytm models, STRIDE analysis, and diagram workflows for security reviews and CI.
Design Better LLM Prompts
Prompt quality often fails because requirements, examples, and evaluation criteria are unclear. This skill helps teams design, test, and review production prompts for Claude, Codex, and Claude Code.
Why this variant is first
alirezarezvani-senior-prompt-engineer
2026-08-21
davila7-senior-prompt-engineer
2026-08-21
Design Reliable Tools for AI Agents
Ambiguous tools cause incorrect calls, wasted context, and poor recovery from errors. This skill provides practical patterns for clear descriptions, schemas, responses, and testing.
Why this variant is first
asmayaseen-tool-design
2026-08-21
muratcankoylan-tool-design
2026-08-21
chakshugautam-tool-design
2026-08-21
sickn33-tool-design
2026-08-21
Create FlowGram Component Docs
FlowGram material components need consistent docs, runnable Story examples, API tables, and bilingual review steps. This skill gives Claude, Codex, and Claude Code a structured workflow for producing those assets.
Diagnose Context Degradation in AI Agents
Long conversations and large prompts can make AI agents lose important information or follow conflicting context. This skill helps Claude, Codex, and Claude Code identify degradation patterns and choose mitigation strategies.
Why this variant is first
chakshugautam-context-degradation
2026-08-21
muratcankoylan-context-degradation
2026-08-21
asmayaseen-context-degradation
2026-08-21
Build Reinforcement Learning Agents with SB3
Reinforcement learning projects require careful algorithm, environment, training, and evaluation choices. This skill provides Stable Baselines3 guidance and reusable templates for each stage.
Why this variant is first
davila7-stable-baselines3
2026-08-21
k-dense-ai-stable-baselines3
2026-08-21
Build Firecrawl Search Workflows
Teams need reliable source discovery before scraping or answering questions. This skill guides Firecrawl search integration, result selection, and follow-up extraction decisions.
Coordinate Paperclip Tasks and Agents
Teams need a consistent way to coordinate agent work, approvals, and task progress. This skill guides Paperclip API workflows for assignments, updates, routines, and deliverables.
Fix Windows AI Agent Encoding
Windows POSIX shells can garble Chinese output from Python, PowerShell, and cmd.exe. This skill gives targeted UTF-8 and GBK fixes for Claude, Codex, and related agents.