ai-usage-coach
Help users get more value from AI assistants by suggesting better prompting techniques, surfacing underused features, and identifying workflow improvements. Use when users ask things like "how can I use Claude better?", "what features am I missing?", "give me tips for prompting", "what can you do?", "I feel like I'm not getting the most out of this", or when they explicitly ask for help improving their AI usage. Also use when users seem frustrated with results or are clearly using suboptimal patterns.
Best use case
ai-usage-coach is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Help users get more value from AI assistants by suggesting better prompting techniques, surfacing underused features, and identifying workflow improvements. Use when users ask things like "how can I use Claude better?", "what features am I missing?", "give me tips for prompting", "what can you do?", "I feel like I'm not getting the most out of this", or when they explicitly ask for help improving their AI usage. Also use when users seem frustrated with results or are clearly using suboptimal patterns.
Teams using ai-usage-coach should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/ai-usage-coach/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How ai-usage-coach Compares
| Feature / Agent | ai-usage-coach | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Help users get more value from AI assistants by suggesting better prompting techniques, surfacing underused features, and identifying workflow improvements. Use when users ask things like "how can I use Claude better?", "what features am I missing?", "give me tips for prompting", "what can you do?", "I feel like I'm not getting the most out of this", or when they explicitly ask for help improving their AI usage. Also use when users seem frustrated with results or are clearly using suboptimal patterns.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
SKILL.md Source
# AI Usage Coach
Provide actionable, personalized suggestions to help users become more effective with AI assistants.
## Core Principles
1. **Be helpful, not preachy** - Frame suggestions as opportunities, not criticisms
2. **Be specific** - Generic advice is forgettable; concrete examples stick
3. **Be contextual** - Tailor suggestions to what the user is actually doing
4. **Be concise** - One or two high-value suggestions beat a wall of tips
## How to Use This Skill
When triggered, assess what would be most valuable for this user:
**For explicit "help me improve" requests:**
1. Ask 1-2 clarifying questions about their typical use cases
2. Consult the relevant reference files based on their needs
3. Provide 2-3 targeted suggestions with concrete examples
**For feature discovery requests ("what can you do?"):**
1. Read `references/features.md`
2. Highlight capabilities most relevant to their apparent context
3. Offer to dive deeper into any area
**For users showing suboptimal patterns:**
1. Read `references/anti-patterns.md` to identify the issue
2. Gently suggest an alternative approach
3. Show a before/after example if helpful
## Reference Files
Load these based on user needs:
- **[references/prompting-patterns.md](references/prompting-patterns.md)** - Core techniques for writing effective prompts. Use when users struggle to get good outputs or ask about prompting.
- **[references/features.md](references/features.md)** - Claude's capabilities and when to use them. Use for feature discovery or when users could benefit from a feature they're not using.
- **[references/workflows.md](references/workflows.md)** - Common workflow patterns and how to structure complex tasks. Use when users tackle multi-step problems inefficiently.
- **[references/anti-patterns.md](references/anti-patterns.md)** - Common mistakes and how to fix them. Use when you notice suboptimal usage patterns.
## Response Guidelines
When giving suggestions:
1. **Lead with value** - Start with the most impactful suggestion
2. **Show, don't tell** - Include a concrete example whenever possible
3. **Keep it brief** - 2-3 suggestions max per response
4. **Invite follow-up** - Offer to elaborate on any point
Avoid:
- Listing every possible tip
- Being condescending about current habits
- Overwhelming with information
- Generic advice that applies to everyone equallyRelated Skills
mailcoach-automation
Automate Mailcoach tasks via Rube MCP (Composio). Always search tools first for current schemas.
ffmpeg-usage
ffmpeg recipes and best practices: convert, concatenate, merge, resize, compress, GIF creation, audio extraction, subtitles, optimize for social platforms.
mongodb_usage
This skill should be used when user asks to "query MongoDB", "show database collections", "get collection schema", "list MongoDB databases", "search records in MongoDB", or "check database indexes".
adherence-coach
Identifies missed sessions or inconsistency and proposes plan reshuffles with motivational nudges.
openai-usage
Report current OpenAI usage/rate-limit health from Codex ChatGPT limits.
ai-usage
Check AI CLI usage/quota for Claude Code, OpenAI Codex, Google Gemini CLI, and Z.AI. Use when user asks about remaining quota, usage limits, rate limits, or wants to check how much capacity is left.
agentic-coach
Interactive prompt engineering coach that elevates vague prompts through Socratic dialogue, multiple transformation styles, and guided learning. Use when improving prompts, learning agentic engineering, or wanting coached guidance rather than automated transformation. NEVER auto-executes - always displays and asks first.
bgo
Automates the complete Blender build-go workflow, from building and packaging your extension/add-on to removing old versions, installing, enabling, and launching Blender for quick testing and iteration.
moai-lang-r
R 4.4+ best practices with testthat 3.2, lintr 3.2, and data analysis patterns.
moai-lang-python
Python 3.13+ development specialist covering FastAPI, Django, async patterns, data science, testing with pytest, and modern Python features. Use when developing Python APIs, web applications, data pipelines, or writing tests.
moai-icons-vector
Vector icon libraries ecosystem guide covering 10+ major libraries with 200K+ icons, including React Icons (35K+), Lucide (1000+), Tabler Icons (5900+), Iconify (200K+), Heroicons, Phosphor, and Radix Icons with implementation patterns, decision trees, and best practices.
moai-foundation-trust
Complete TRUST 4 principles guide covering Test First, Readable, Unified, Secured. Validation methods, enterprise quality gates, metrics, and November 2025 standards. Enterprise v4.0 with 50+ software quality standards references.