create-rule
Create a new memory rule following Claude Code best practices for project instructions, coding standards, and workflow guidelines. This skill should be used when users want to create CLAUDE.md rules, .claude/rules/ files, or memory instructions for Claude Code.
What this skill does
# Create Rule
> **Cross-Platform AI Agent Skill**
> This skill works with any AI agent platform that supports the skills.sh standard.
# Create Memory Rule
Generate a new memory rule following Claude Code best practices for project instructions, coding standards, and workflow guidelines.
> **Note**: Claude Code has merged commands into skills (v2.1.3+). This skill creates **memory rules** (CLAUDE.md entries and `.claude/rules/` files), not skills or commands.
>
> For the memory hierarchy and rule file specifications, see [references/memory-hierarchy.md](references/memory-hierarchy.md).
> For glob patterns and rule examples, see [references/rule-examples.md](references/rule-examples.md).
## Reference Documentation
- Claude Code memory documentation: https://code.claude.com/docs/en/memory
## Anti-Hallucination Guidelines
**CRITICAL**: When creating rules:
1. **Verify existing patterns first** - Don't assume conventions, check the actual codebase
2. **Reference real code** - Base rules on actual patterns found in the project
3. **Don't invent standards** - If no convention exists, ask the user before creating one
4. **Check for conflicts** - Ensure new rules don't contradict existing ones
5. **Validate frontmatter** - Only use `paths` frontmatter for `.claude/rules/` files
## Your Task
### Phase 0: Gather Up-to-Date Documentation (Use claude-code-guide Agent)
**CRITICAL**: Before creating any rule, fetch the latest official documentation:
### Phase 1: Understand Context (Explore Codebase)
Understand the codebase context to create relevant rules:
### Phase 2: Parse Arguments
1. **Extract rule name** from `$1` or first word of `command arguments`
2. **Extract description** from remaining arguments or ask user
3. **Determine rule type**:
- **Modular rule**: `.claude/rules/<name>.md` (recommended for focused topics)
- **CLAUDE.md entry**: Add to existing `./CLAUDE.md` or `~/.claude/CLAUDE.md`
4. **Determine scope**:
- **Project rule**: `.claude/rules/` (shared with team)
- **User rule**: `~/.claude/rules/` (personal, all projects)
### Phase 3: Gather Rule Requirements
Ask user or infer from context:
```
Questions to determine:
1. What specific behavior should this rule enforce?
2. Is it path-specific? (applies only to certain file patterns)
3. Should it be project-scoped or user-scoped?
4. What category does it belong to? (code-style, testing, security, workflow, etc.)
5. Are there existing similar rules to reference or extend?
### Phase 4: Analyze Existing Rules (Use Parallel Analysis)
Spawn parallel Explore agents with model: haiku to gather patterns:
```
Agent 1 - Analyze Existing Memory:
- prompt: "Read any existing CLAUDE.md files and .claude/rules/*.md in the project. Extract common patterns: structure, formatting, specificity level. Return best practices observed."
- agent-type: "Explore"
- model: "haiku"
Agent 2 - Identify Rule Category:
- prompt: "Search existing rules in .claude/rules/ directory. Analyze the category structure used (code-style, testing, security, etc.). Based on '[DESCRIPTION]', which existing category best fits? Return recommended category, filename, and examples of similar rules."
- agent-type: "Explore"
- model: "haiku"
Agent 3 - Check for Conflicts:
- prompt: "Search for existing rules that might conflict with or overlap '[DESCRIPTION]'. Check CLAUDE.md files and .claude/rules/. Return any potential conflicts or opportunities to consolidate."
- agent-type: "Explore"
- model: "haiku"
### Phase 5: Generate Rule Structure
Use TodoWrite to track rule creation:
```
TodoWrite:
- [ ] Create rule file with frontmatter (if path-specific)
- [ ] Write clear, specific instructions
- [ ] Add examples where helpful
- [ ] Validate rule syntax
- [ ] Test rule applicability
### Phase 6: Write Rule File
Generate the rule following the templates in [references/rule-examples.md](references/rule-examples.md).
**For path-specific rules** (with frontmatter):
```markdown
## Claude Code Enhanced Features
This skill includes the following Claude Code-specific enhancements:
## Your Task
### Phase 0: Gather Up-to-Date Documentation (Use claude-code-guide Agent)
**CRITICAL**: Before creating any rule, fetch the latest official documentation:
```
Use Task tool with claude-code-guide agent:
- prompt: "I need to create a new Claude Code memory rule. Please research and provide:
1. **Rules File Specification**:
- Current frontmatter format (paths field syntax)
- Glob pattern support and limitations
- File naming and organization conventions
2. **Memory Hierarchy**:
- Current loading order (enterprise, project, user, etc.)
- Priority rules when conflicts occur
- Path specificity rules
3. **CLAUDE.md Best Practices**:
- Current structure recommendations
- Import syntax (@path/to/file)
- Section organization patterns
4. **Recent Changes**:
- Any new frontmatter fields
- New memory features or capabilities
- Deprecated patterns to avoid
Return specific, actionable information with examples."
- subagent_type: "claude-code-guide"
```
### Phase 1: Understand Context (Use Explore Agent)
Understand the codebase context to create relevant rules:
```
Use Task tool with Explore agent:
- prompt: "The user wants to create a rule called [RULE_NAME] with description: [DESCRIPTION]. Search the codebase to understand: 1) Existing CLAUDE.md files and their structure, 2) Existing .claude/rules/ if any, 3) Relevant code patterns the rule should enforce. Return findings with file paths."
- subagent_type: "Explore"
- model: "haiku"
```
### Phase 2: Parse Arguments
1. **Extract rule name** from `$1` or first word of `$ARGUMENTS`
2. **Extract description** from remaining arguments or ask user
3. **Determine rule type**:
- **Modular rule**: `.claude/rules/<name>.md` (recommended for focused topics)
- **CLAUDE.md entry**: Add to existing `./CLAUDE.md` or `~/.claude/CLAUDE.md`
4. **Determine scope**:
- **Project rule**: `.claude/rules/` (shared with team)
- **User rule**: `~/.claude/rules/` (personal, all projects)
### Phase 3: Gather Rule Requirements
Ask user or infer from context:
```
Questions to determine:
1. What specific behavior should this rule enforce?
2. Is it path-specific? (applies only to certain file patterns)
3. Should it be project-scoped or user-scoped?
4. What category does it belong to? (code-style, testing, security, workflow, etc.)
5. Are there existing similar rules to reference or extend?
```
### Phase 4: Analyze Existing Rules (Use SubAgents)
Spawn parallel Explore agents with model: haiku to gather patterns:
```
Agent 1 - Analyze Existing Memory:
- prompt: "Read any existing CLAUDE.md files and .claude/rules/*.md in the project. Extract common patterns: structure, formatting, specificity level. Return best practices observed."
- subagent_type: "Explore"
- model: "haiku"
Agent 2 - Identify Rule Category:
- prompt: "Search existing rules in .claude/rules/ directory. Analyze the category structure used (code-style, testing, security, etc.). Based on '[DESCRIPTION]', which existing category best fits? Return recommended category, filename, and examples of similar rules."
- subagent_type: "Explore"
- model: "haiku"
Agent 3 - Check for Conflicts:
- prompt: "Search for existing rules that might conflict with or overlap '[DESCRIPTION]'. Check CLAUDE.md files and .claude/rules/. Return any potential conflicts or opportunities to consolidate."
- subagent_type: "Explore"
- model: "haiku"
```
### Phase 5: Generate Rule Structure
Use TodoWrite to track rule creation:
```
TodoWrite:
- [ ] Create rule file with frontmatter (if path-specific)
- [ ] Write clear, specific instructions
- [ ] Add examples where helpful
- [ ] Validate rule syntax
- [ ] Test rule applicability
```
### Phase 6: Write Rule File
Generate the rule following the templates in [references/rule-examples.md](references/rule-examplesRelated 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.