📦
tool-discovery
Safe 87Choose the Right AI Tool for Every Task
Choosing between many skills and agents can delay technical work. This skill maps each task to focused tools using concise catalogs and selection rules.
Productivity View
Unified search
Search skill packs and skills together
Start with the task. Skillstore will show complete packs first, then individual skills when they are a better match.
Showing results for "agent"
Skill Packs 9
Complete task bundles with multiple skills and one install command.
PackAgent-Code
Build better software with disciplined AI workflows. Agent-Code selects the right skills, delegates tasks to focused subagents, and enforces spec and quality reviews.
2 skills 17 installs
PackAgent Engineering Starter Kit
Build better AI agents with a practical toolkit for prompt structure, context efficiency, and tool design. This plugin helps builders ship more capable agents with clearer architecture and lower token waste.
3 skills 71 installs
PackAgent Swarm Studio
Plan and coordinate multi-agent systems with clear roles, parallel execution, and convergence checks.
3 skills 16 installs
PackBranch Handoff Kit
Guides agents from isolated worktrees to review-ready pull requests. It keeps the branch clean, helps choose the right finish path, and prepares a polished PR handoff.
2 skills 5 installs
PackDiscord Agent Ops Kit
Build and run production-ready Discord assistants with clear architecture, safe automation, and public-server isolation guardrails.
3 skills 4 installs
PackGoogle Calendar Command Center
Plan, check agendas, and create Google Calendar events without leaving the agent flow.
3 skills 4 installs
PackmacOS Productivity Toolkit
CLI control for Apple Notes, Reminders, and Things 3 — the three essential macOS productivity apps, all without touching the GUI. Capture notes, manage reminders that sync to iOS, and run GTD-style project management, all from your AI agent.
0 skills 3 installs
PackPlan to Ship Guard
Helps agents move from plan to execution with checkpoints and mandatory verification before claiming completion. Reduces false completion and keeps handoffs evidence-based.
3 skills 5 installs
Individual Skills 648
Use these when you need one narrow capability instead of a whole pack.
📦
building-agents
Safe 85Build Claude Code Agents
Creating reliable AI agents requires clear schemas, safe tools, and repeatable review steps. This skill guides agent design, validation, migration, and maintenance for Claude Code workflows.
Coding & Development View
📦
agent-development
Safe 85Build Claude Code Agents
Designing reliable Claude Code agents is hard without structure. This skill provides templates, validation rules, and examples for agent prompts, triggers, tools, and metadata.
Coding & Development View
4 installable variants Compare
Why this variant is first
Highest Skillstore Score
dami-randle-agent-development
Skillstore Score 85
Evidence Confidence High
Skillstore usage 25
Updated
2026-08-21
agent-development
Skillstore Score 84
Evidence Confidence High
Skillstore usage 32
Updated
2026-08-21
anthropics-agent-development
Skillstore Score 84
Evidence Confidence High
Skillstore usage 13
Updated
2026-08-21
davila7-agent-development
Skillstore Score 83
Evidence Confidence High
Skillstore usage 11
Updated
2026-08-21
📦
diffdock
Safe 85Run DiffDock Molecular Docking
Molecular docking workflows require careful setup, validated inputs, and cautious result interpretation. This skill guides Claude, Codex, and Claude Code through DiffDock setup, docking runs, batch screening, and confidence-score analysis.
Research & Learning View
📦
nature-paper-to-patent
Safe 85Draft Evidence-Grounded Chinese Patent Packages
Research teams struggle to turn technical papers into traceable Chinese patent drafts. This skill structures evidence, claims, figures, formulas, and DOCX deliverables for expert review.
Legal & Contracts View
📦
product-decision-agent
Safe 84Diagnose Product Decisions in Chinese
Product teams often mistake symptoms for root causes and spread resources across weak priorities. This skill identifies the main blocker and recommends measurable next actions.
Productivity View
📦
skill-creator
Safe 83Create Effective AI Skills
Building reusable AI skills is hard when structure, resources, and validation rules are unclear. This skill provides a practical workflow for designing, writing, validating, and packaging skills.
Documentation View
5 installable variants Compare
Why this variant is first
Highest Skillstore Score
89jobrien-skill-creator
Skillstore Score 83
Evidence Confidence High
Skillstore usage 52
Updated
2026-08-21
7spade-skill-creator
Skillstore Score 80
Evidence Confidence High
Skillstore usage 41
Updated
2026-08-21
cesaraugustusgrob-skill-creator
Skillstore Score 78
Evidence Confidence High
Skillstore usage 7
Updated
2026-08-21
langchain-ai-skill-creator
Skillstore Score 67
Evidence Confidence High
Skillstore usage 18
Updated
2026-08-21
sickn33-skill-creator
Skillstore Score 38
Evidence Confidence Medium
Skillstore usage 45
Updated
2026-08-21
📦
building-plugins
Safe 83Build Claude Code Plugins
Creating Claude Code plugins requires correct structure, validation, documentation, and safe packaging. This skill guides users through plugin architecture, templates, validation, and publishing workflows.
DevOps & Infrastructure View
📦
planning-with-files
Safe 83Organize Long AI Tasks with Planning Files
Long AI sessions can lose goals, decisions, and progress. This skill guides Claude, Codex, and Claude Code to store plans, findings, and logs in project files.
Productivity View
3 installable variants Compare
Why this variant is first
Highest Skillstore Score
zhanlincui-planning-with-files
Skillstore Score 83
Evidence Confidence High
Skillstore usage 263
Updated
2026-08-21
othmanadi-planning-with-files
Skillstore Score 78
Evidence Confidence High
Skillstore usage 35
Updated
2026-08-21
sickn33-planning-with-files
Skillstore Score 73
Evidence Confidence High
Skillstore usage 17
Updated
2026-08-21
📦
prompt-optimization
Safe 82Optimize LLM Prompts and Agent Instructions
Weak prompts create inconsistent model outputs and slow AI feature development. This skill helps structure prompts, examples, constraints, and output formats for Claude, Codex, and Claude Code.
Productivity View
📦
analyzing-component-quality
Safe 82Evaluate Claude Code Component Quality
Claude Code components can be technically valid yet unclear, over-permissioned, or difficult to invoke. This skill scores five quality dimensions and recommends specific improvements.
Coding & Development View
📦
extension-oql
Safe 82Expose Canister Data Through OQL
Structured canister data is difficult for intelligence agents to query safely. This skill adds OQL entities, schema discovery, query execution, relationships, and per-entity authorization.
Coding & Development View