find-my-project
Helps beginners find their first AGENTIC project through pain point identification. Guides through questioning, analysis, project suggestion, and folder setup. Use when someone asks 'what project should I build?' or 'help me get started with Claude Code'.
What this skill does
# Find My Project - סקיל למציאת הפרוייקט המושלם
> עזרה למשתמשים למצוא את הפרוייקט **האג'נטי** הראשון שלהם ב-Claude Code דרך זיהוי כאבים יומיומיים
## CRITICAL: Consult claude-code-guide
**Before any significant decision**, use:
```
Task tool with subagent_type=claude-code-guide
```
Example questions:
- "What Claude Code primitives exist for [use case]?"
- "How to structure an agentic project for [specific workflow]?"
- "What's the difference between skills, agents, and hooks?"
## What is an Agentic Project?
**Agentic project ≠ traditional code or classic automation**
An agentic project is built from:
- **CLAUDE.md** - Knowledge about the user and project
- **Skills** - Modular capabilities the agent can invoke
- **Processes** - Stacks of skills
- **Tools** - Connections to external world
**It is NOT:**
- ❌ React/Node.js application
- ❌ Python script
- ❌ Database with API
- ❌ Zapier/Make automation
**It IS:**
- ✅ Documents the agent knows how to read and update
- ✅ Skills the agent knows how to invoke
- ✅ Knowledge the agent uses for decisions
- ✅ Templates the agent fills in
## Goal
Help new Claude Code users:
1. Identify their daily pain points
2. Find a suitable agentic project (not code!)
3. Set up the project structure
4. Start with initial files
## Workflow
### Step 1: Pain Point Discovery
Ask the user about their daily work:
```
🎯 בוא נמצא את הפרוייקט המושלם עבורך!
ענה על כמה שאלות קצרות:
1. **מה התפקיד שלך?** (מנהל, פרילנסר, יזם, עובד...)
2. **מה הדבר שהכי מתיש אותך בעבודה?**
- משהו שחוזר על עצמו כל יום/שבוע
- משהו שלוקח הרבה זמן
- משהו שאתה שוכח לעשות
3. **אילו כלים אתה משתמש הכי הרבה?**
- אימייל, וואטסאפ, אקסל...
- CRM, יומן, מערכות ניהול...
4. **מה היית רוצה שיעשה לבד?**
```
### Step 2: Analysis and Opportunity Identification
**REQUIRED**: Before continuing, consult claude-code-guide:
```
Use Task tool with subagent_type=claude-code-guide to ask:
"I have a user who [describe pain points]. What Claude Code primitives and project structure would be best for an AGENTIC project (not traditional code) to solve this?"
```
Based on responses and consultation, identify:
- Repetitive tasks → Skills
- Multi-step processes → Skill stacks
- Information that needs to be available → CLAUDE.md + data files
- External actions → Tools (MCP/API)
### Step 3: Project Proposal
Present the recommended project to the user:
```
💡 הפרוייקט המומלץ עבורך:
**שם הפרוייקט:** [appropriate name]
**מה הוא יעשה:**
- [capability 1]
- [capability 2]
- [capability 3]
**למה זה מתאים לך:**
- פותר את: [specific pain]
- חוסך: [specific benefit]
**מבנה מומלץ:**
project-name/
├── CLAUDE.md # הידע על הפרוייקט ועליך
├── data/ # קבצי מידע (לקוחות, משימות...)
├── templates/ # תבניות (מסמכים, הודעות...)
└── .claude/skills/ # סקילים ספציפיים לפרוייקט
רוצה שאקים את התיקייה?
```
### Step 4: Project Setup
If user approves:
1. **Create the folder structure:**
```bash
mkdir -p ~/projects/[project-name]/{data,templates,.claude/skills}
```
2. **Create initial CLAUDE.md** with:
- User information (from questioning)
- Project purpose
- Basic rules
3. **Suggest data files to add:**
```
📥 כדי שאוכל לעזור לך טוב יותר, שקול להכניס לתיקייה:
- רשימת לקוחות (אקסל/CSV/טקסט)
- דוגמאות של מסמכים שאתה שולח
- תבניות של הודעות
- כל מידע קבוע שאתה משתמש בו
אחרי שתכניס - אני אוכל לעזור לך לבנות את הסקיל הראשון!
```
### Step 5: First Skill Recommendation
Based on identified pains, suggest a first skill:
```
⚡ הסקיל הראשון המומלץ:
**שם:** [skill name]
**מה יעשה:** [short description]
רוצה שניצור אותו יחד?
```
**Important**: Before creating the skill, consult claude-code-guide:
```
Use Task tool with subagent_type=claude-code-guide to ask:
"How to create a skill for [specific task]? What's the best structure?"
```
## Common Project Examples
### For Freelancers:
- **Client Management** - quotes, contracts, tracking
- **Project Management** - tasks, deadlines, reports
### For Managers:
- **Weekly Reports** - data collection, processing, generation
- **Team Tracking** - tasks, statuses, alerts
### For Entrepreneurs:
- **Lead Management** - tracking, reminders, conversion
- **Content & Marketing** - post creation, scheduling, measurement
## What This Skill Does NOT Do
- Does not build classic applications (React, Node.js...)
- Does not create databases
- Focuses on **Claude Code ecosystem**: documents, skills, agents
## Consultation Tool
Whenever you need information about Claude Code capabilities:
```
Task tool with subagent_type=claude-code-guide
```
Example questions:
- "What primitives exist in Claude Code for managing data?"
- "How to create a skill that calls other skills?"
- "What's the best way to structure CLAUDE.md?"
- "How to create agents for background tasks?"
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.