@letta-ai/letta-code 0.7.4-next.1 → 0.7.4-next.2

package/skills/memory-init/SKILL.md

@@ -0,0 +1,310 @@
+---
+name: Memory Initialization
+description: Comprehensive guide for initializing or reorganizing agent memory. Load this skill when running /init, when the user asks you to set up your memory, or when you need guidance on creating effective memory blocks.
+---
+
+# Memory Initialization Guide
+
+The user has requested that you initialize or reorganize your memory state. You have access to the `memory` tool which allows you to create, edit, and manage memory blocks.
+
+## Understanding Your Context
+
+**Important**: You are a Letta Code agent, which is fundamentally different from typical AI coding assistants. Letta Code agents are **stateful** - users expect to work with the same agent over extended periods, potentially for the entire lifecycle of a project or even longer. Your memory is not just a convenience; it's how you get better over time and maintain continuity across sessions.
+
+This command may be run in different scenarios:
+- **Fresh agent**: You may have default memory blocks that were created when you were initialized
+- **Existing agent**: You may have been working with the user for a while, and they want you to reorganize or significantly update your memory structure
+- **Shared blocks**: Some memory blocks may be shared across multiple agents - be careful about modifying these
+
+Before making changes, use the `memory` tool to inspect your current memory blocks and understand what already exists.
+
+## What Coding Agents Should Remember
+
+### 1. Procedures (Rules & Workflows)
+Explicit rules and workflows that should always be followed:
+- "Never commit directly to main - always use feature branches"
+- "Always run lint before running tests"
+- "Use conventional commits format for all commit messages"
+- "Always check for existing tests before adding new ones"
+
+### 2. Preferences (Style & Conventions)
+User and project coding style preferences:
+- "Never use try/catch for control flow"
+- "Always add JSDoc comments to exported functions"
+- "Prefer functional components over class components"
+- "Use early returns instead of nested conditionals"
+
+### 3. History & Context
+Important historical context that informs current decisions:
+- "We fixed this exact pagination bug two weeks ago - check PR #234"
+- "This monorepo used to have 3 modules before the consolidation"
+- "The auth system was refactored in v2.0 - old patterns are deprecated"
+- "User prefers verbose explanations when debugging"
+
+Note: For historical recall, you may also have access to `conversation_search` which can search past conversations. Memory blocks are for distilled, important information worth persisting permanently.
+
+## Memory Scope Considerations
+
+Consider whether information is:
+
+**Project-scoped** (store in `project` block):
+- Build commands, test commands, lint configuration
+- Project architecture and key directories
+- Team conventions specific to this codebase
+- Technology stack and framework choices
+
+**User-scoped** (store in `human` block):
+- Personal coding preferences that apply across projects
+- Communication style preferences
+- General workflow habits
+
+**Session/Task-scoped** (consider separate blocks like `ticket` or `context`):
+- Current branch or ticket being worked on
+- Debugging context for an ongoing investigation
+- Temporary notes about a specific task
+
+## Recommended Memory Structure
+
+### Core Blocks (Usually Present)
+
+**`persona`**: Your behavioral guidelines that augment your base system prompt.
+- Your system prompt already contains comprehensive instructions for how to code and behave
+- The persona block is for **learned adaptations** - things you discover about how the user wants you to behave
+- Examples: "User said never use emojis", "User prefers terse responses", "Always explain reasoning before making changes"
+- This block may start empty and grow over time as you learn the user's preferences
+
+**`project`**: Project-specific information, conventions, and commands
+- Build/test/lint commands
+- Key directories and architecture
+- Project-specific conventions from README, AGENTS.md, etc.
+
+**`human`**: User preferences, communication style, general habits
+- Cross-project preferences
+- Working style and communication preferences
+
+### Optional Blocks (Create as Needed)
+
+**`ticket`** or **`task`**: Scratchpad for current work item context.
+- **Important**: This is different from the TODO or Plan tools!
+- TODO/Plan tools track active task lists and implementation plans (structured lists of what to do)
+- A ticket/task memory block is a **scratchpad** for pinned context that should stay visible
+- Examples: Linear ticket ID and URL, Jira issue key, branch name, PR number, relevant links
+- Information that's useful to keep in context but doesn't fit in a TODO list
+
+**`context`**: Debugging or investigation scratchpad
+- Current hypotheses being tested
+- Files already examined
+- Clues and observations
+
+**`decisions`**: Architectural decisions and their rationale
+- Why certain approaches were chosen
+- Trade-offs that were considered
+
+## Writing Good Memory Blocks
+
+**This is critical**: In the future, you (or a future version of yourself) will only see three things about each memory block:
+1. The **label** (name)
+2. The **description**
+3. The **value** (content)
+
+The reasoning you have *right now* about why you're creating a block will be lost. Your future self won't easily remember this initialization conversation (it can be searched, but it will no longer be in-context). Therefore:
+
+**Labels should be:**
+- Clear and descriptive (e.g., `project-conventions` not `stuff`)
+- Consistent in style (e.g., all lowercase with hyphens)
+
+**Descriptions are especially important:**
+- Explain *what* this block is for and *when* to use it
+- Explain *how* this block should influence your behavior
+- Write as if explaining to a future version of yourself who has no context
+- Good: "User's coding style preferences that should be applied to all code I write or review. Update when user expresses new preferences."
+- Bad: "Preferences"
+
+**Values should be:**
+- Well-organized and scannable
+- Updated regularly to stay relevant
+- Pruned of outdated information
+
+Think of memory block descriptions as documentation for your future self. The better you write them now, the more effective you'll be in future sessions.
+
+## Research Depth
+
+You can ask the user if they want a standard or deep research initialization:
+
+**Standard initialization** (~5-20 tool calls):
+- Inspect existing memory blocks
+- Scan README, package.json/config files, AGENTS.md, CLAUDE.md
+- Review git status and recent commits (from context below)
+- Explore key directories and understand project structure
+- Create/update your memory block structure to contain the essential information you need to know about the user, your behavior (learned preferences), the project you're working in, and any other information that will help you be an effective collaborator.
+
+**Deep research initialization** (~100+ tool calls):
+- Everything in standard initialization, plus:
+- Use your TODO or Plan tool to create a systematic research plan
+- Deep dive into git history for patterns, conventions, and context
+- Analyze commit message conventions and branching strategy
+- Explore multiple directories and understand architecture thoroughly
+- Search for and read key source files to understand patterns
+- Create multiple specialized memory blocks
+- May involve multiple rounds of exploration
+
+**What deep research can uncover:**
+- **Contributors & team dynamics**: Who works on what areas? Who are the main contributors? (`git shortlog -sn`)
+- **Coding habits**: When do people commit? (time patterns) What's the typical commit size?
+- **Writing & commit style**: How verbose are commit messages? What conventions are followed?
+- **Code evolution**: How has the architecture changed? What major refactors happened?
+- **Review patterns**: Are there PR templates? What gets reviewed carefully vs rubber-stamped?
+- **Pain points**: What areas have lots of bug fixes? What code gets touched frequently?
+- **Related repositories**: Ask the user if there are other repos you should know about (e.g., a backend monorepo, shared libraries, documentation repos). These relationships can be crucial context.
+
+This kind of deep context can make you significantly more effective as a long-term collaborator on the project.
+
+If the user says "take as long as you need" or explicitly wants deep research, use your TODO or Plan tool to orchestrate a thorough, multi-step research process.
+
+## Research Techniques
+
+**File-based research:**
+- README.md, CONTRIBUTING.md, AGENTS.md, CLAUDE.md
+- Package manifests (package.json, Cargo.toml, pyproject.toml, go.mod)
+- Config files (.eslintrc, tsconfig.json, .prettierrc)
+- CI/CD configs (.github/workflows/, .gitlab-ci.yml)
+
+**Git-based research** (if in a git repo):
+- `git log --oneline -20` - Recent commit history and patterns
+- `git branch -a` - Branching strategy
+- `git log --format="%s" -50 | head -20` - Commit message conventions
+- `git shortlog -sn --all | head -10` - Main contributors
+- `git log --format="%an <%ae>" | sort -u` - Contributors with emails (more reliable for deduplication)
+- Recent PRs or merge commits for context on ongoing work
+
+**Important: Deduplicate contributors!** Git groups by exact author string, so the same person may appear multiple times with different names (e.g., "jsmith" and "John Smith" are likely the same person). Use emails to deduplicate, and apply common sense - usernames often match parts of full names.
+
+## How to Do Thorough Research
+
+**Don't just collect data - analyze and cross-reference it.**
+
+Shallow research (bad):
+- Run commands, copy output
+- Take everything at face value
+- List facts without understanding
+
+Thorough research (good):
+- **Cross-reference findings**: If two pieces of data seem inconsistent, dig deeper
+- **Resolve ambiguities**: Don't leave questions unanswered (e.g., "are these two contributors the same person?")
+- **Read actual content**: Don't just list file names - read key files to understand them
+- **Look for patterns**: What do the commit messages tell you about workflow? What do file structures tell you about architecture?
+- **Form hypotheses and verify**: "I think this team uses feature branches" → check git branch patterns to confirm
+- **Think like a new team member**: What would you want to know on your first day?
+
+**Questions to ask yourself during research:**
+- Does this make sense? (e.g., why would there be two contributors with similar names?)
+- What's missing? (e.g., no tests directory - is testing not done, or done differently?)
+- What can I infer? (e.g., lots of "fix:" commits in one area → that area is buggy or complex)
+- Am I just listing facts, or do I understand the project?
+
+The goal isn't to produce a report - it's to genuinely understand the project and how this human(s) works so you can be an effective collaborator.
+
+## On Asking Questions
+
+**Ask important questions upfront, then be autonomous during execution.**
+
+### Recommended Upfront Questions
+
+You should ask these questions at the start (bundle them together in one AskUserQuestion call):
+
+1. **Research depth**: "Standard or deep research (comprehensive, as long as needed)?"
+2. **Identity**: "Which contributor are you?" (You can often infer this from git logs - e.g., if git shows "cpacker" as a top contributor, ask "Are you cpacker?")
+3. **Related repos**: "Are there other repositories I should know about and consider in my research?" (e.g., backend monorepo, shared libraries)
+4. **Workflow style**: "How proactive should I be?" (auto-commit vs ask-first)
+5. **Communication style**: "Terse or detailed responses?"
+6. **Any specific rules**: "Rules I should always follow?"
+
+**Why these matter:**
+- Identity lets you correlate git history to the user (their commits, PRs, coding style)
+- Related repos provide crucial context (many projects span multiple repos)
+- Workflow/communication style should be stored in the `human` block
+- Rules go in `persona` block
+
+### What NOT to ask
+
+- Things you can find by reading files ("What's your test framework?")
+- "What kind of work do you do? Reviewing PRs vs writing code?" - obvious from git log, most devs do everything
+- Permission for obvious actions - just do them
+- Questions one at a time - bundle them (but don't exhaust the user with too many questions at once)
+
+**During execution**, be autonomous. Make reasonable choices and proceed.
+
+## Memory Block Strategy
+
+### Split Large Blocks
+
+**Don't create monolithic blocks.** If a block is getting long (>50-100 lines), split it:
+
+Instead of one huge `project` block, consider:
+- `project-overview`: High-level description, tech stack, repo links
+- `project-commands`: Build, test, lint, dev commands
+- `project-conventions`: Commit style, PR process, code style
+- `project-architecture`: Directory structure, key modules
+- `project-gotchas`: Footguns, things to watch out for
+
+This makes memory more scannable and easier to update and share with other agents.
+
+### Update Memory Incrementally
+
+**For deep research: Update memory as you go, not all at once at the end.**
+
+Why this matters:
+- Deep research can take many turns and millions of tokens
+- Context windows overflow and trigger rolling summaries
+- If you wait until the end to write memory, you may lose important details
+- Write findings to memory blocks as you discover them
+
+Good pattern:
+1. Create block structure early (even with placeholder content)
+2. Update blocks after each research phase
+3. Refine and consolidate at the end
+
+Remember, your memory tool allows you to easily add, edit, and remove blocks. There's no reason to wait until you "know everything" to write memory. Treat your memory blocks as a living scratchpad.
+
+### Initialize ALL Relevant Blocks
+
+Don't just update a single memory block. Based on your upfront questions, also update:
+
+- **`human`**: Store the user's identity, workflow preferences, communication style
+- **`persona`**: Store rules the user wants you to follow, behavioral adaptations
+- **`project-*`**: Split project info across multiple focused blocks
+
+And add memory blocks that you think make sense to add (e.g., `project-architecture`, `project-conventions`, `project-gotchas`, etc, or even splitting the `human` block into more focused blocks, or even multiple blocks for multiple users).
+
+## Your Task
+
+1. **Ask upfront questions**: Use AskUserQuestion with the recommended questions above (bundled together). This is critical - don't skip it.
+2. **Inspect existing memory**: You may already have some memory blocks initialized. See what already exists, and analyze how it is or is not insufficient or incomplete.
+3. **Identify the user**: From git logs and their answer, figure out who they are and store in `human` block. If relevant, ask questions to gather information about their preferences that will help you be a useful assistant to them.
+4. **Update human/persona early**: Based on answers, update your memory blocks eagerly before diving into project research. You can always change them as you go, you're not locked into any memory configuration.
+5. **Research the project**: Explore based on chosen depth. Use your TODO or plan tool to create a systematic research plan.
+6. **Create/update project blocks incrementally**: Don't wait until the end - write findings as you go.
+7. **Reflect and review**: See "Reflection Phase" below - this is critical for deep research.
+8. **Ask user if done**: Check if they're satisfied or want you to continue refining.
+
+## Reflection Phase (Critical for Deep Research)
+
+Before finishing, you MUST do a reflection step. **Your memory blocks are visible to you in your system prompt right now.** Look at them carefully and ask yourself:
+
+1. **Redundancy check**: Are there blocks with overlapping content? Either literally overlapping (due to errors while making memory edits), or semantically/conceptually overlapping?
+
+2. **Completeness check**: Did you actually update ALL relevant blocks? For example:
+   - Did you update `human` with the user's identity and preferences?
+   - Did you update `persona` with behavioral rules they expressed?
+   - Or did you only update project blocks and forget the rest?
+
+3. **Quality check**: Are there typos, formatting issues, or unclear descriptions in your blocks?
+
+4. **Structure check**: Would this make sense to your future self? Is anything missing? Is anything redundant?
+
+**After reflection**, fix any issues you found. Then ask the user:
+> "I've completed the initialization. Here's a brief summary of what I set up: [summary]. Should I continue refining, or is this good to proceed?"
+
+This gives the user a chance to provide feedback or ask for adjustments before you finish.
+
+Remember: Good memory management is an investment. The effort you put into organizing your memory now will pay dividends as you work with this user over time.

package/skills/skill-creator/SKILL.md

@@ -0,0 +1,355 @@
+---
+name: skill-creator
+description: Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Letta Code's capabilities with specialized knowledge, workflows, or tool integrations.
+---
+
+# Skill Creator
+
+This skill provides guidance for creating effective skills in Letta Code.
+
+## About Skills
+
+Skills are modular, self-contained packages that extend Letta Code's capabilities by providing
+specialized knowledge, workflows, and tools. Think of them as "onboarding guides" for specific
+domains or tasks—they transform a Letta Code agent from a general-purpose agent into a specialized agent
+equipped with procedural knowledge that no model can fully possess.
+
+### What Skills Provide
+
+1. Specialized workflows - Multi-step procedures for specific domains
+2. Tool integrations - Instructions for working with specific file formats or APIs
+3. Domain expertise - Company-specific knowledge, schemas, business logic
+4. Bundled resources - Scripts, references, and assets for complex and repetitive tasks
+
+## Core Principles
+
+### Concise is Key
+
+The context window is a public good. Skills share the context window with everything else the Letta Code agent needs: system prompt, conversation history, other Skills' metadata, and the actual user request.
+
+**Default assumption: the Letta Code agent is already very capable.** Only add context the Letta Code agent doesn't already have. Challenge each piece of information: "Does the Letta Code agent really need this explanation?" and "Does this paragraph justify its token cost?"
+
+Prefer concise examples over verbose explanations.
+
+### Set Appropriate Degrees of Freedom
+
+Match the level of specificity to the task's fragility and variability:
+
+**High freedom (text-based instructions)**: Use when multiple approaches are valid, decisions depend on context, or heuristics guide the approach.
+
+**Medium freedom (pseudocode or scripts with parameters)**: Use when a preferred pattern exists, some variation is acceptable, or configuration affects behavior.
+
+**Low freedom (specific scripts, few parameters)**: Use when operations are fragile and error-prone, consistency is critical, or a specific sequence must be followed.
+
+Think of the Letta Code agent as exploring a path: a narrow bridge with cliffs needs specific guardrails (low freedom), while an open field allows many routes (high freedom).
+
+### Anatomy of a Skill
+
+Every skill consists of a required SKILL.md file and optional bundled resources:
+
+```
+skill-name/
+├── SKILL.md (required)
+│   ├── YAML frontmatter metadata (required)
+│   │   ├── name: (required)
+│   │   └── description: (required)
+│   └── Markdown instructions (required)
+└── Bundled Resources (optional)
+    ├── scripts/          - Executable code (TypeScript/Python/Bash/etc.)
+    ├── references/       - Documentation intended to be loaded into context as needed
+    └── assets/           - Files used in output (templates, icons, fonts, etc.)
+```
+
+#### SKILL.md (required)
+
+Every SKILL.md in Letta Code consists of:
+
+- **Frontmatter** (YAML): Contains `name` and `description` fields. These are the only fields that the Letta Code agent reads to determine when the skill gets used, thus it is very important to be clear and comprehensive in describing what the skill is, and when it should be used.
+- **Body** (Markdown): Instructions and guidance for using the skill. Only loaded AFTER the skill triggers (if at all).
+
+#### Bundled Resources (optional)
+
+##### Scripts (`scripts/`)
+
+Executable code (TypeScript/Python/Bash/etc.) for tasks that require deterministic reliability or are repeatedly rewritten.
+
+- **When to include**: When the same code is being rewritten repeatedly or deterministic reliability is needed
+- **Example**: `scripts/rotate-pdf.ts` for PDF rotation tasks
+- **Benefits**: Token efficient, deterministic, may be executed without loading into context
+- **Note**: Scripts may still need to be read by the Letta Code agent for patching or environment-specific adjustments
+
+##### References (`references/`)
+
+Documentation and reference material intended to be loaded as needed into context to inform the Letta Code agent's process and thinking.
+
+- **When to include**: For documentation that the Letta Code agent should reference while working
+- **Examples**: `references/finance.md` for financial schemas, `references/mnda.md` for company NDA template, `references/policies.md` for company policies, `references/api_docs.md` for API specifications
+- **Use cases**: Database schemas, API documentation, domain knowledge, company policies, detailed workflow guides
+- **Benefits**: Keeps SKILL.md lean, loaded only when the Letta Code agent determines it's needed
+- **Best practice**: If files are large (>10k words), include grep search patterns in SKILL.md
+- **Avoid duplication**: Information should live in either SKILL.md or references files, not both. Prefer references files for detailed information unless it's truly core to the skill—this keeps SKILL.md lean while making information discoverable without hogging the context window. Keep only essential procedural instructions and workflow guidance in SKILL.md; move detailed reference material, schemas, and examples to references files.
+
+##### Assets (`assets/`)
+
+Files not intended to be loaded into context, but rather used within the output the Letta Code agent produces.
+
+- **When to include**: When the skill needs files that will be used in the final output
+- **Examples**: `assets/logo.png` for brand assets, `assets/slides.pptx` for PowerPoint templates, `assets/frontend-template/` for HTML/React boilerplate, `assets/font.ttf` for typography
+- **Use cases**: Templates, images, icons, boilerplate code, fonts, sample documents that get copied or modified
+- **Benefits**: Separates output resources from documentation, enables the Letta Code agent to use files without loading them into context
+
+#### What to Not Include in a Skill
+
+A skill should only contain essential files that directly support its functionality. Do NOT create extraneous documentation or auxiliary files, including:
+
+- README.md
+- INSTALLATION_GUIDE.md
+- QUICK_REFERENCE.md
+- CHANGELOG.md
+- etc.
+
+The skill should only contain the information needed for an AI agent to do the job at hand. It should not contain auxilary context about the process that went into creating it, setup and testing procedures, user-facing documentation, etc. Creating additional documentation files just adds clutter and confusion.
+
+### Progressive Disclosure Design Principle
+
+Skills use a three-level loading system to manage context efficiently:
+
+1. **Metadata (name + description)** - Always in context (~100 words)
+2. **SKILL.md body** - When skill triggers (<5k words)
+3. **Bundled resources** - As needed by the Letta Code agent (Unlimited because scripts can be executed without reading into context window)
+
+#### Progressive Disclosure Patterns
+
+Keep SKILL.md body to the essentials and under 500 lines to minimize context bloat. Split content into separate files when approaching this limit. When splitting out content into other files, it is very important to reference them from SKILL.md and describe clearly when to read them, to ensure the reader of the skill knows they exist and when to use them.
+
+**Key principle:** When a skill supports multiple variations, frameworks, or options, keep only the core workflow and selection guidance in SKILL.md. Move variant-specific details (patterns, examples, configuration) into separate reference files.
+
+**Pattern 1: High-level guide with references**
+
+```markdown
+# PDF Processing
+
+## Quick start
+
+Extract text with pdfplumber:
+[code example]
+
+## Advanced features
+
+- **Form filling**: See [FORMS.md](FORMS.md) for complete guide
+- **API reference**: See [REFERENCE.md](REFERENCE.md) for all methods
+- **Examples**: See [EXAMPLES.md](EXAMPLES.md) for common patterns
+```
+
+The Letta Code agent loads FORMS.md, REFERENCE.md, or EXAMPLES.md only when needed.
+
+**Pattern 2: Domain-specific organization**
+
+For Skills with multiple domains, organize content by domain to avoid loading irrelevant context:
+
+```
+bigquery-skill/
+├── SKILL.md (overview and navigation)
+└── reference/
+    ├── finance.md (revenue, billing metrics)
+    ├── sales.md (opportunities, pipeline)
+    ├── product.md (API usage, features)
+    └── marketing.md (campaigns, attribution)
+```
+
+When a user asks about sales metrics, the Letta Code agent only reads sales.md.
+
+Similarly, for skills supporting multiple frameworks or variants, organize by variant:
+
+```
+cloud-deploy/
+├── SKILL.md (workflow + provider selection)
+└── references/
+    ├── aws.md (AWS deployment patterns)
+    ├── gcp.md (GCP deployment patterns)
+    └── azure.md (Azure deployment patterns)
+```
+
+When the user chooses AWS, the Letta Code agent only reads aws.md.
+
+**Pattern 3: Conditional details**
+
+Show basic content, link to advanced content:
+
+```markdown
+# DOCX Processing
+
+## Creating documents
+
+Use docx-js for new documents. See [DOCX-JS.md](DOCX-JS.md).
+
+## Editing documents
+
+For simple edits, modify the XML directly.
+
+**For tracked changes**: See [REDLINING.md](REDLINING.md)
+**For OOXML details**: See [OOXML.md](OOXML.md)
+```
+
+The Letta Code agent reads REDLINING.md or OOXML.md only when the user needs those features.
+
+**Important guidelines:**
+
+- **Avoid deeply nested references** - Keep references one level deep from SKILL.md. All reference files should link directly from SKILL.md.
+- **Structure longer reference files** - For files longer than 100 lines, include a table of contents at the top so the Letta Code agent can see the full scope when previewing.
+
+## Skill Creation Process
+
+Skill creation involves these steps:
+
+1. Understand the skill with concrete examples
+2. Plan reusable skill contents (scripts, references, assets)
+3. Initialize the skill (run init-skill.ts)
+4. Edit the skill (implement resources and write SKILL.md)
+5. Package the skill (run package-skill.ts)
+6. Iterate based on real usage
+
+Follow these steps in order, skipping only if there is a clear reason why they are not applicable.
+
+### Step 1: Understanding the Skill with Concrete Examples
+
+Skip this step only when the skill's usage patterns are already clearly understood. It remains valuable even when working with an existing skill.
+
+To create an effective skill, clearly understand concrete examples of how the skill will be used. This understanding can come from either direct user examples or generated examples that are validated with user feedback.
+
+For example, when building an image-editor skill, relevant questions include:
+
+- "What functionality should the image-editor skill support? Editing, rotating, anything else?"
+- "Can you give some examples of how this skill would be used?"
+- "I can imagine users asking for things like 'Remove the red-eye from this image' or 'Rotate this image'. Are there other ways you imagine this skill being used?"
+- "What would a user say that should trigger this skill?"
+
+To avoid overwhelming users, avoid asking too many questions in a single message. Start with the most important questions and follow up as needed for better effectiveness.
+
+Conclude this step when there is a clear sense of the functionality the skill should support.
+
+### Step 2: Planning the Reusable Skill Contents
+
+To turn concrete examples into an effective skill, analyze each example by:
+
+1. Considering how to execute on the example from scratch
+2. Identifying what scripts, references, and assets would be helpful when executing these workflows repeatedly
+
+Example: When building a `pdf-editor` skill to handle queries like "Help me rotate this PDF," the analysis shows:
+
+1. Rotating a PDF requires re-writing the same code each time
+2. A `scripts/rotate-pdf.ts` script would be helpful to store in the skill
+
+Example: When designing a `frontend-webapp-builder` skill for queries like "Build me a todo app" or "Build me a dashboard to track my steps," the analysis shows:
+
+1. Writing a frontend webapp requires the same boilerplate HTML/React each time
+2. An `assets/hello-world/` template containing the boilerplate HTML/React project files would be helpful to store in the skill
+
+Example: When building a `big-query` skill to handle queries like "How many users have logged in today?" the analysis shows:
+
+1. Querying BigQuery requires re-discovering the table schemas and relationships each time
+2. A `references/schema.md` file documenting the table schemas would be helpful to store in the skill
+
+To establish the skill's contents, analyze each concrete example to create a list of the reusable resources to include: scripts, references, and assets.
+
+### Step 3: Initializing the Skill
+
+At this point, it is time to actually create the skill.
+
+Skip this step only if the skill being developed already exists, and iteration or packaging is needed. In this case, continue to the next step.
+
+When creating a new skill from scratch, always run the `init-skill.ts` script. The script conveniently generates a new template skill directory that automatically includes everything a skill requires, making the skill creation process much more efficient and reliable.
+
+Usage:
+
+```bash
+npx ts-node scripts/init-skill.ts <skill-name> --path <output-directory>
+```
+
+The script:
+
+- Creates the skill directory at the specified path
+- Generates a SKILL.md template with proper frontmatter and TODO placeholders
+- Creates example resource directories: `scripts/`, `references/`, and `assets/`
+- Adds example files in each directory that can be customized or deleted
+
+After initialization, customize or remove the generated SKILL.md and example files as needed.
+
+### Step 4: Edit the Skill
+
+When editing the (newly-generated or existing) skill, remember that the skill is being created for another Letta Code agent instance to use. Include information that would be beneficial and non-obvious to the Letta Code agent. Consider what procedural knowledge, domain-specific details, or reusable assets would help another Letta Code agent instance execute these tasks more effectively.
+
+#### Learn Proven Design Patterns
+
+Consult these helpful guides based on your skill's needs:
+
+- **Multi-step processes**: See references/workflows.md for sequential workflows and conditional logic
+- **Specific output formats or quality standards**: See references/output-patterns.md for template and example patterns
+
+These files contain established best practices for effective skill design.
+
+#### Start with Reusable Skill Contents
+
+To begin implementation, start with the reusable resources identified above: `scripts/`, `references/`, and `assets/` files. Note that this step may require user input. For example, when implementing a `brand-guidelines` skill, the user may need to provide brand assets or templates to store in `assets/`, or documentation to store in `references/`.
+
+Added scripts must be tested by actually running them to ensure there are no bugs and that the output matches what is expected. If there are many similar scripts, only a representative sample needs to be tested to ensure confidence that they all work while balancing time to completion.
+
+Any example files and directories not needed for the skill should be deleted. The initialization script creates example files in `scripts/`, `references/`, and `assets/` to demonstrate structure, but most skills won't need all of them.
+
+#### Update SKILL.md
+
+**Writing Guidelines:** Always use imperative/infinitive form.
+
+##### Frontmatter
+
+Write the YAML frontmatter with `name` and `description`:
+
+- `name`: The skill name
+- `description`: This is the primary triggering mechanism for your skill, and helps the Letta Code agent understand when to use the skill.
+  - Include both what the Skill does and specific triggers/contexts for when to use it.
+  - Include all "when to use" information here - Not in the body. The body is only loaded after triggering, so "When to Use This Skill" sections in the body are not helpful to the Letta Code agent.
+  - Example description for a `docx` skill: "Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. Use when the Letta Code agent needs to work with professional documents (.docx files) for: (1) Creating new documents, (2) Modifying or editing content, (3) Working with tracked changes, (4) Adding comments, or any other document tasks"
+
+Do not include any other fields in YAML frontmatter.
+
+##### Body
+
+Write instructions for using the skill and its bundled resources.
+
+### Step 5: Packaging a Skill
+
+Once development of the skill is complete, it must be packaged into a distributable .skill file that gets shared with the user. The packaging process automatically validates the skill first to ensure it meets all requirements:
+
+```bash
+npx ts-node scripts/package-skill.ts <path/to/skill-folder>
+```
+
+Optional output directory specification:
+
+```bash
+npx ts-node scripts/package-skill.ts <path/to/skill-folder> ./dist
+```
+
+The packaging script will:
+
+1. **Validate** the skill automatically, checking:
+
+   - YAML frontmatter format and required fields
+   - Skill naming conventions and directory structure
+   - Description completeness and quality
+   - File organization and resource references
+
+2. **Package** the skill if validation passes, creating a .skill file named after the skill (e.g., `my-skill.skill`) that includes all files and maintains the proper directory structure for distribution. The .skill file is a zip file with a .skill extension.
+
+If validation fails, the script will report the errors and exit without creating a package. Fix any validation errors and run the packaging command again.
+
+### Step 6: Iterate
+
+After testing the skill, users may request improvements. Often this happens right after using the skill, with fresh context of how the skill performed.
+
+**Iteration workflow:**
+
+1. Use the skill on real tasks
+2. Notice struggles or inefficiencies
+3. Identify how SKILL.md or bundled resources should be updated
+4. Implement changes and test again