instructions-development
This skill should be used when the user asks to "create CLAUDE.md", "initialize CLAUDE.md", "sync CLAUDE.md with code", "update documentation from codebase", "create .claude/rules/", "manage modular rules", "split large CLAUDE.md", or mentions project documentation setup. Manages complete lifecycle of project instructions including creation, synchronization with code patterns, and modular organization.
What this skill does
# Project Instructions Development
Manages the complete lifecycle of project instructions: creating initial documentation, syncing with codebase patterns, and organizing modular rules.
## When to Use This Skill
Use when:
- "Create CLAUDE.md for this project"
- "Initialize CLAUDE.md" or "generate CLAUDE.md"
- "Sync CLAUDE.md with my code"
- "Update documentation from codebase"
- "Extract patterns from code"
- "Create .claude/rules/ structure"
- "Split large CLAUDE.md"
- "Manage modular documentation"
## What This Skill Does
Provides 4 main operations:
- ✅ **Initialize**: Create new CLAUDE.md with opinionated baseline standards
- ✅ **Sync**: Analyze codebase and update documentation with detected patterns
- ✅ **Organize**: Create or manage .claude/rules/ modular structure
- ✅ **Split**: Break large CLAUDE.md into focused rule files
**Note**: .claude/rules/ only works in project directories, not in global ~/.claude/
## CRITICAL RULES
### Language
- **CLAUDE.md MUST be 100% in English** (industry standard)
- Never mix languages in documentation
- Code, comments, and docs all in English
### No Dynamic Data
- **NEVER include**: line counts, file counts, commit statistics, dates, timestamps
- **NEVER write**: "Analyzed X files", "Y lines of code", "Created on..."
- **Only include**: stable patterns, timeless structures, architectural principles
### User Confirmation
- **ALWAYS ask questions** to understand context and preferences
- **ALWAYS show preview** before writing any files
- **ALWAYS get explicit confirmation** before creating/modifying files
## Instructions
### Step 0: Check Global Configuration (CRITICAL)
**Before creating any project-level documentation, ALWAYS read the user's global CLAUDE.md:**
```bash
# Check if global CLAUDE.md exists
~/.claude/CLAUDE.md
```
**If it exists:**
- Read and analyze what rules are already defined globally
- **DO NOT duplicate** global rules in project CLAUDE.md
- Only add project-specific patterns that differ from or extend global rules
- Mention to user: "I found your global CLAUDE.md - I'll only add project-specific rules"
**If it doesn't exist:**
- Proceed normally with project documentation
### Step 1: Determine Operation and Complexity
Use AskUserQuestion tool with THREE questions:
```json
{
"questions": [
{
"question": "What do you need help with?",
"header": "Operation",
"multiSelect": false,
"options": [
{
"label": "Create new CLAUDE.md",
"description": "Start from scratch with opinionated baseline"
},
{
"label": "Sync CLAUDE.md with existing code",
"description": "Analyze codebase to detect patterns and update docs"
},
{
"label": "Split large CLAUDE.md into rules/",
"description": "Break CLAUDE.md (>500 lines) into focused files"
}
]
},
{
"question": "What complexity level?",
"header": "Structure",
"multiSelect": false,
"options": [
{
"label": "Simple (just CLAUDE.md)",
"description": "Single file, good for small/medium projects"
},
{
"label": "Modular (CLAUDE.md + .claude/rules/)",
"description": "Multiple files with path patterns, for large projects"
}
]
},
{
"question": "Should this be shared with your team or kept local?",
"header": "Sharing",
"multiSelect": false,
"options": [
{
"label": "Shared (CLAUDE.md)",
"description": "Committed to git, shared across team and sessions"
},
{
"label": "Local only (CLAUDE.local.md)",
"description": "Git-ignored, personal workspace rules only"
}
]
}
]
}
```
Route to workflow:
- **Create new + Simple + Shared** → Initialize Workflow (Step 2) - CLAUDE.md
- **Create new + Simple + Local** → Initialize Workflow (Step 2) - CLAUDE.local.md + add to .gitignore
- **Create new + Modular + Shared** → Initialize Workflow (Step 2) + Organize Workflow (Step 4) - CLAUDE.md
- **Create new + Modular + Local** → Initialize Workflow (Step 2) + Organize Workflow (Step 4) - CLAUDE.local.md + add to .gitignore
- **Sync + Simple + Shared** → Sync Workflow (Step 3) - update CLAUDE.md
- **Sync + Simple + Local** → Sync Workflow (Step 3) - update CLAUDE.local.md
- **Sync + Modular** → Sync Workflow (Step 3) + Organize Workflow (Step 4)
- **Split** → Split Workflow (Step 5)
---
### Step 2: Initialize Workflow (Create New CLAUDE.md)
Create opinionated baseline CLAUDE.md for new projects.
**Process**:
1. **Determine filename** (from Step 1 answer):
- Shared → `CLAUDE.md`
- Local only → `CLAUDE.local.md`
2. **Detect project type**
- Check if it's a code project (package.json, requirements.txt, go.mod, etc.)
- Or non-code (docs, notes, research, etc.)
- Ask user if unclear
3. **Think through design**:
- Minimum viable CLAUDE.md?
- Similar projects/patterns?
- Architectural trade-offs?
- Common pitfalls in this stack?
4. **Show preview** with:
- Structure outline
- Key sections
- Estimated line count
- Architecture reasoning
- Filename that will be created
5. **Generate and write** (after confirmation):
- Single file: ~150-250 lines
- Modular: ~100-150 lines with references to rules/
- Use determined filename from step 1
6. **If local only (CLAUDE.local.md):**
- Add `CLAUDE.local.md` to `.gitignore`
- Create .gitignore if it doesn't exist
- Inform user it's git-ignored
7. **Inform user** with next steps
**See `references/initialize-workflow.md` for complete details**
---
### Step 3: Sync Workflow (Analyze Code and Update Docs)
Analyze codebase to extract patterns and update documentation.
**Process**:
1. **Detect current setup**:
- Check if CLAUDE.md exists
- Check if .claude/rules/ exists
- Determine mode: CREATE, UPDATE Single, UPDATE Modular
2. **Analyze codebase** (use Task tool with Explore agent):
- Main source directory
- Tech stack
- Folder organization
- Test patterns
3. **Extract patterns**:
- Naming conventions (files, functions, variables)
- Architectural pattern (FSD, Feature-First, etc.)
- Import patterns
- Testing conventions
- Component/API patterns
4. **Think through findings**:
- Stable (>80%) vs emerging patterns
- What to document vs leave implicit
- Single file or modular approach
5. **Show findings** to user:
- Detected patterns
- Mismatches with documented patterns
- Recommendations
6. **Ask approach** (AskUserQuestion):
- Update CLAUDE.md (single file)
- Create .claude/rules/ (modular)
- Show both options
7. **Generate updates** and write (after confirmation)
8. **Inform user** with summary of changes
**See `references/sync-workflow.md` for complete details**
---
### Step 4: Organize Workflow (Create .claude/rules/ Structure)
Set up modular documentation with focused rule files.
**Process**:
1. **Detect stack** (same as initialize)
2. **Ask which rules to create** (AskUserQuestion):
- coding-standards.md (recommended)
- architecture.md (recommended)
- testing.md
- api.md
3. **Think through design**:
- What in each file vs CLAUDE.md
- Path patterns for each file
- Keep each file <200 lines
4. **Show preview**:
- File structure
- Estimated line counts
- Path patterns
- CLAUDE.md updates
5. **Create files** (after confirmation):
- Create .claude/rules/ directory
- Create each rule file with YAML frontmatter
- Update CLAUDE.md to reference rules
6. **Inform user** with structure overview
**See `references/organize-and-split-workflows.md` for templates and details**
---
### Step 5: Split Workflow (Break Large CLAUDE.md)
Break CLAUDE.md (>500 lines) into focused modular files.
**Process**:
1. **Read and analyze CLAUDE.md**:
- Identify sections
- Core vs detailed content
- Line countRelated in General
modeling-omnistudio-epc-catalog
IncludedSalesforce Industries CME EPC product-modeling skill for Product2-based catalog creation. Use when creating EPC products, configuring product attributes, building offer bundles with Product Child Items, or reviewing EPC DataPack JSON metadata for product catalog changes. TRIGGER when: user creates or updates Product2 EPC records, AttributeAssignment payloads, AttributeMetadata/AttributeDefaultValues, Offer bundles, or ProductChildItem relationships. DO NOT TRIGGER when: designing OmniScripts/FlexCards/Integration Procedures (use building-omnistudio-omniscript, building-omnistudio-flexcard, or building-omnistudio-integration-procedure), implementing Apex business logic (use generating-apex), or troubleshooting deployment pipelines (use deploying-metadata).
relationship-science-coach
IncludedUse this skill for direct, practical adult relationship coaching: couples conflict, repair, trust, marriage, dating, flirting, attachment patterns, emotional connection, sex, desire differences, eroticism, kink negotiation, affection, love languages, breakups, and long-term passion. Draw on Gottman, EFT and Hold Me Tight, attachment science, modern sex research, Perel, Nagoski, Kerner, Schnarch, Love and Stosny, and flexible love-language tools. Be concrete and low-hedge. Redirect only for imminent danger, abuse, coercive control, minors, non-consent, self-harm, stalking, or medical/legal/psychiatric decisions.
building-sf-integrations
IncludedSalesforce integration architecture and runtime plumbing with 120-point scoring. Use this skill to set up Named Credentials, External Credentials, External Services, REST/SOAP callout patterns, Platform Events, and Change Data Capture. TRIGGER when: user sets up Named Credentials, External Services, REST/SOAP callouts, Platform Events, CDC, or touches .namedCredential-meta.xml files. DO NOT TRIGGER when: Connected App/OAuth config (use configuring-connected-apps), Apex-only logic (use generating-apex), or data import/export (use handling-sf-data).
venue-templates
IncludedAccess comprehensive LaTeX templates, formatting requirements, and submission guidelines for major scientific publication venues (Nature, Science, PLOS, IEEE, ACM), academic conferences (NeurIPS, ICML, CVPR, CHI), research posters, and grant proposals (NSF, NIH, DOE, DARPA). This skill should be used when preparing manuscripts for journal submission, conference papers, research posters, or grant proposals and need venue-specific formatting requirements and templates.
let-fate-decide
IncludedDraws the 12 Houses of the Zodiac Tarot spread to inject entropy into planning when prompts are vague, ambiguous, or casually delegated. Interprets the spread to guide next steps. Use when the user says 'let fate decide', 'YOLO', 'whatever', 'idk', or other nonchalant phrases, makes Yu-Gi-Oh references, or when you are about to arbitrarily pick between multiple reasonable approaches. Prefer over ask-questions-if-underspecified when the user's tone is casual or playful rather than precision-seeking.
net-ops
IncludedCross-platform network troubleshooting (Windows, macOS, Linux) via local or remote shell. Use for: DNS broken, can't resolve hostnames, nslookup/dig works but apps fail, NRPT, WFP, scutil, /etc/resolver, systemd-resolved, /etc/resolv.conf, NetworkManager, VPN DNS leak residue (ProtonVPN/Mullvad/WireGuard/AnyConnect), AV/firewall blocking DNS or DoH, Tailscale DNS interaction, intermittent connectivity, remote diagnostics over SSH.