@letta-ai/letta-code 0.7.4-next.1 → 0.7.4-next.3

package/letta.js

@@ -3233,7 +3233,7 @@ var package_default;
 var init_package = __esm(() => {
   package_default = {
     name: "@letta-ai/letta-code",
-    version: "0.7.4-next.1",
+    version: "0.7.4-next.3",
     description: "Letta Code is a CLI tool for interacting with stateful Letta agents from the terminal.",
     type: "module",
     bin: {
@@ -3244,6 +3244,7 @@ var init_package = __esm(() => {
       "README.md",
       "letta.js",
       "scripts",
+      "skills",
       "vendor"
     ],
     repository: {
@@ -5904,7 +5905,7 @@ Remember: Your memory blocks persist across sessions. What you store now will in
 var init_remember = () => {};
 
 // src/agent/prompts/skill_creator_mode.md
-var skill_creator_mode_default = '# Skill Creation Mode\n\nThe user has invoked the `/skill` command. Your task is to help them **design and create a new Skill** for this project.\n\nYou are a Letta Code agent with:\n- Access to the current conversation, project files, and memory blocks\n- Access to the `Skill` tool (for loading skills) and `AskUserQuestion` (for asking clarifying questions)\n- Access to file tools (Read, Write, Edit, ApplyPatch, etc.) via the toolset\n\nYour goal is to guide the user through a **focused, collaborative workflow** to create or update a Skill that will be reused in the future.\n\n## 1. Load the skill-creator Skill (if available)\n\n1. Inspect your memory blocks:\n   - `skills` – list of available skills and their descriptions\n   - `loaded_skills` – SKILL.md contents for currently loaded skills\n2. If a `skill-creator` skill is **not already loaded** in `loaded_skills`, you should **attempt to load it** using the `Skill` tool:\n   - Call the `Skill` tool with:\n     - `command: "load", skills: ["skill-creator"]`\n   - The environment may resolve this from either the project’s `.skills` directory or a bundled `skills/skills/skill-creator/SKILL.md` location.\n3. If loading `skill-creator` fails (for example, the tool errors or the file is missing), or if the environment does not provide it, continue using your own judgment based on these instructions.\n\nDo **not** load unrelated skills unless clearly relevant to the user’s request.\n\n## 2. Understand the requested skill\n\nThe `/skill` command may have been invoked in two ways:\n\n1. `/skill` (no description)\n2. `/skill <description>` (with a short description, e.g. `/skill image editor for marketing screenshots`)\n\nYou should always:\n\n1. Consider:\n   - The current conversation and what the user has been working on\n   - Relevant project context from files and memory blocks (especially `project` and `skills`)\n2. If a description was provided:\n   - Treat it as the **initial specification** of the skill.\n   - Restate it briefly in your own words to confirm understanding.\n\n## 3. Ask upfront clarifying questions (using AskUserQuestion)\n\nBefore you start proposing a concrete skill design, you MUST ask a small bundle of **high‑value upfront questions** using the `AskUserQuestion` tool.\n\nKeep the initial question set small (3–6 questions) and focused. Examples:\n\n1. Purpose and scope:\n   - “What is the main purpose of this skill?”\n   - “Is this skill meant for a specific project or to be reused across many projects?”\n2. Implementation details:\n   - “Do you want this skill to be mostly guidance (instructions) or to include reusable scripts/templates?”\n   - “Where should the skill live? (e.g. `.skills/your-skill-id` in this repo)”\n\nBundle these together in a single `AskUserQuestion` call. After you receive answers, you can ask follow‑up questions as needed, but avoid overwhelming the user.\n\n## 4. Propose a concrete skill design\n\nUsing:\n- The user’s description (if provided)\n- Answers to your questions\n- The current project and conversation context\n\nYou should propose a **concrete skill design**, including at minimum:\n\n- A skill ID (directory name), e.g. `image-editor`, `pdf-workflow`, `webapp-testing`\n- A concise human‑readable name\n- A one‑paragraph description focused on:\n  - What the skill does\n  - When it should be used\n  - Who is likely to use it\n- Example triggering queries (how users will invoke it in natural language)\n- The planned structure of the skill:\n  - `SKILL.md` contents (sections, key instructions)\n  - Any `scripts/` you recommend (and what each script does)\n  - Any `references/` files (and when to read them)\n  - Any `assets/` (templates, fonts, icons, starter projects, etc.)\n\nValidate this design with the user before you start writing files. If something is ambiguous or high‑impact, ask a brief follow‑up question using `AskUserQuestion`.\n\n## 5. Create or update the skill files\n\nOnce the design is agreed upon:\n\n1. Determine the target directory for the skill (in this order):\n   - First, check whether the host environment or CLI has configured a default skills directory for this agent (for example via a `--skills` flag or project settings). If such a directory is provided, use it as the base directory for the new skill unless the user explicitly requests a different path.\n   - If no explicit skills directory is configured, check the `skills` memory block for a `Skills Directory: <path>` line and use that as the base directory.\n   - If neither is available, default to a local `.skills/<skill-id>/` directory in the current project root (or another path the user has requested).\n2. Create or update:\n   - `.skills/<skill-id>/SKILL.md` – the main entry point for the skill\n   - Optional: `.skills/<skill-id>/scripts/` – reusable scripts\n   - Optional: `.skills/<skill-id>/references/` – longer documentation, schemas, or examples\n   - Optional: `.skills/<skill-id>/assets/` – templates, fonts, images, or other resources\n3. Use file tools (Write, Edit, ApplyPatch, etc.) to create and refine these files instead of asking the user to do it manually.\n\nWhen writing `SKILL.md`, follow the conventions used by existing skills in this repository:\n\n- YAML frontmatter at the top, including at least:\n  - `name`: human‑readable name\n  - `description`: when and how the skill should be used\n- Clear sections that:\n  - Explain when to use the skill\n  - Describe the recommended workflows\n  - Link to `scripts/`, `references/`, and `assets/` as needed\n  - Emphasize progressive disclosure (only load detailed references as needed)\n\nKeep `SKILL.md` focused and concise; move long reference content into separate files.\n\n## 6. Keep questions focused and iterative\n\nThroughout the process:\n\n- Prefer a small number of **high‑impact questions** over many tiny questions.\n- When you need more detail, group follow‑up questions into a single `AskUserQuestion` call.\n- Use concrete examples from the user’s project or repository when possible.\n\nYour goal is to:\n\n1. Understand the desired skill thoroughly.\n2. Propose a clear, reusable design.\n3. Implement or update the actual skill files in the repository.\n4. After creating or updating the skill files, use the `Skill` tool with `command: "refresh"` to re-scan the skills directory and update the `skills` memory block.\n5. Leave the user with a ready‑to‑use skill that appears in the `skills` memory block and can be loaded with the `Skill` tool.';
+var skill_creator_mode_default = '# Skill Creation Mode\n\nThe user has invoked the `/skill` command. Your task is to help them **design and create a new Skill** for this project.\n\nYou are a Letta Code agent with:\n- Access to the current conversation, project files, and memory blocks\n- Access to the `Skill` tool (for loading skills) and `AskUserQuestion` (for asking clarifying questions)\n- Access to file tools (Read, Write, Edit, ApplyPatch, etc.) via the toolset\n\nYour goal is to guide the user through a **focused, collaborative workflow** to create or update a Skill that will be reused in the future.\n\n## 1. Load the creating-skills Skill (if available)\n\n1. Inspect your memory blocks:\n   - `skills` – list of available skills and their descriptions\n   - `loaded_skills` – SKILL.md contents for currently loaded skills\n2. If a `creating-skills` skill is **not already loaded** in `loaded_skills`, you should **attempt to load it** using the `Skill` tool:\n   - Call the `Skill` tool with:\n     - `command: "load", skills: ["creating-skills"]`\n   - The environment may resolve this from either the project’s `.skills` directory or a bundled `skills/skills/creating-skills/SKILL.md` location.\n3. If loading `creating-skills` fails (for example, the tool errors or the file is missing), or if the environment does not provide it, continue using your own judgment based on these instructions.\n\nDo **not** load unrelated skills unless clearly relevant to the user’s request.\n\n## 2. Understand the requested skill\n\nThe `/skill` command may have been invoked in two ways:\n\n1. `/skill` (no description)\n2. `/skill <description>` (with a short description, e.g. `/skill image editor for marketing screenshots`)\n\nYou should always:\n\n1. Consider:\n   - The current conversation and what the user has been working on\n   - Relevant project context from files and memory blocks (especially `project` and `skills`)\n2. If a description was provided:\n   - Treat it as the **initial specification** of the skill.\n   - Restate it briefly in your own words to confirm understanding.\n\n## 3. Ask upfront clarifying questions (using AskUserQuestion)\n\nBefore you start proposing a concrete skill design, you MUST ask a small bundle of **high‑value upfront questions** using the `AskUserQuestion` tool.\n\nKeep the initial question set small (3–6 questions) and focused. Examples:\n\n1. Purpose and scope:\n   - “What is the main purpose of this skill?”\n   - “Is this skill meant for a specific project or to be reused across many projects?”\n2. Implementation details:\n   - “Do you want this skill to be mostly guidance (instructions) or to include reusable scripts/templates?”\n   - “Where should the skill live? (e.g. `.skills/your-skill-id` in this repo)”\n\nBundle these together in a single `AskUserQuestion` call. After you receive answers, you can ask follow‑up questions as needed, but avoid overwhelming the user.\n\n## 4. Propose a concrete skill design\n\nUsing:\n- The user’s description (if provided)\n- Answers to your questions\n- The current project and conversation context\n\nYou should propose a **concrete skill design**, including at minimum:\n\n- A skill ID (directory name), e.g. `image-editor`, `pdf-workflow`, `webapp-testing`\n- A concise human‑readable name\n- A one‑paragraph description focused on:\n  - What the skill does\n  - When it should be used\n  - Who is likely to use it\n- Example triggering queries (how users will invoke it in natural language)\n- The planned structure of the skill:\n  - `SKILL.md` contents (sections, key instructions)\n  - Any `scripts/` you recommend (and what each script does)\n  - Any `references/` files (and when to read them)\n  - Any `assets/` (templates, fonts, icons, starter projects, etc.)\n\nValidate this design with the user before you start writing files. If something is ambiguous or high‑impact, ask a brief follow‑up question using `AskUserQuestion`.\n\n## 5. Create or update the skill files\n\nOnce the design is agreed upon:\n\n1. Determine the target directory for the skill (in this order):\n   - First, check whether the host environment or CLI has configured a default skills directory for this agent (for example via a `--skills` flag or project settings). If such a directory is provided, use it as the base directory for the new skill unless the user explicitly requests a different path.\n   - If no explicit skills directory is configured, check the `skills` memory block for a `Skills Directory: <path>` line and use that as the base directory.\n   - If neither is available, default to a local `.skills/<skill-id>/` directory in the current project root (or another path the user has requested).\n2. Create or update:\n   - `.skills/<skill-id>/SKILL.md` – the main entry point for the skill\n   - Optional: `.skills/<skill-id>/scripts/` – reusable scripts\n   - Optional: `.skills/<skill-id>/references/` – longer documentation, schemas, or examples\n   - Optional: `.skills/<skill-id>/assets/` – templates, fonts, images, or other resources\n3. Use file tools (Write, Edit, ApplyPatch, etc.) to create and refine these files instead of asking the user to do it manually.\n\nWhen writing `SKILL.md`, follow the conventions used by existing skills in this repository:\n\n- YAML frontmatter at the top, including at least:\n  - `name`: human‑readable name\n  - `description`: when and how the skill should be used\n- Clear sections that:\n  - Explain when to use the skill\n  - Describe the recommended workflows\n  - Link to `scripts/`, `references/`, and `assets/` as needed\n  - Emphasize progressive disclosure (only load detailed references as needed)\n\nKeep `SKILL.md` focused and concise; move long reference content into separate files.\n\n## 6. Keep questions focused and iterative\n\nThroughout the process:\n\n- Prefer a small number of **high‑impact questions** over many tiny questions.\n- When you need more detail, group follow‑up questions into a single `AskUserQuestion` call.\n- Use concrete examples from the user’s project or repository when possible.\n\nYour goal is to:\n\n1. Understand the desired skill thoroughly.\n2. Propose a clear, reusable design.\n3. Implement or update the actual skill files in the repository.\n4. After creating or updating the skill files, use the `Skill` tool with `command: "refresh"` to re-scan the skills directory and update the `skills` memory block.\n5. Leave the user with a ready‑to‑use skill that appears in the `skills` memory block and can be loaded with the `Skill` tool.';
 var init_skill_creator_mode = () => {};
 
 // src/agent/prompts/skill_unload_reminder.txt
@@ -16592,320 +16593,6 @@ var init_context = __esm(() => {
   context2 = getContext2();
 });
 
-// src/skills/builtin/memory-init/SKILL.md
-var SKILL_default = `---
-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.
-`;
-var init_SKILL = () => {};
-
 // src/agent/skills.ts
 var exports_skills = {};
 __export(exports_skills, {
@@ -16917,40 +16604,19 @@ __export(exports_skills, {
 });
 import { existsSync as existsSync3 } from "node:fs";
 import { readdir as readdir4, readFile as readFile3 } from "node:fs/promises";
-import { join as join7 } from "node:path";
-function parseBundledSkill(id, content) {
-  const { frontmatter, body } = parseFrontmatter(content);
-  const name = (typeof frontmatter.name === "string" ? frontmatter.name : null) || id.split("/").pop()?.replace(/-/g, " ").replace(/\b\w/g, (l) => l.toUpperCase()) || id;
-  let description = typeof frontmatter.description === "string" ? frontmatter.description : null;
-  if (!description) {
-    const firstParagraph = body.trim().split(`
-
-`)[0];
-    description = firstParagraph || "No description available";
-  }
-  description = description.trim();
-  if (description.startsWith('"') && description.endsWith('"') || description.startsWith("'") && description.endsWith("'")) {
-    description = description.slice(1, -1);
-  }
-  let tags;
-  if (Array.isArray(frontmatter.tags)) {
-    tags = frontmatter.tags;
-  } else if (typeof frontmatter.tags === "string") {
-    tags = [frontmatter.tags];
+import { dirname as dirname4, join as join7 } from "node:path";
+import { fileURLToPath as fileURLToPath5 } from "node:url";
+function getBundledSkillsPath() {
+  const thisDir = dirname4(fileURLToPath5(import.meta.url));
+  if (thisDir.includes("src/agent") || thisDir.includes("src\\agent")) {
+    return join7(thisDir, "../skills/builtin");
   }
-  return {
-    id,
-    name,
-    description,
-    category: typeof frontmatter.category === "string" ? frontmatter.category : undefined,
-    tags,
-    path: "",
-    source: "bundled",
-    content
-  };
+  return join7(thisDir, "skills");
 }
-function getBundledSkills() {
-  return BUNDLED_SKILL_SOURCES.map(({ id, content }) => parseBundledSkill(id, content));
+async function getBundledSkills() {
+  const bundledPath = getBundledSkillsPath();
+  const result = await discoverSkillsFromDir(bundledPath, "bundled");
+  return result.skills;
 }
 async function discoverSkillsFromDir(skillsPath, source) {
   const errors = [];
@@ -16971,7 +16637,8 @@ async function discoverSkillsFromDir(skillsPath, source) {
 async function discoverSkills(projectSkillsPath = join7(process.cwd(), SKILLS_DIR)) {
   const allErrors = [];
   const skillsById = new Map;
-  for (const skill of getBundledSkills()) {
+  const bundledSkills = await getBundledSkills();
+  for (const skill of bundledSkills) {
     skillsById.set(skill.id, skill);
   }
   const globalResult = await discoverSkillsFromDir(GLOBAL_SKILLS_DIR, "global");
@@ -17177,12 +16844,8 @@ function formatSkillsForMemory(skills, skillsDirectory) {
   }
   return formatSkillsAsTree(skills, skillsDirectory);
 }
-var BUNDLED_SKILL_SOURCES, SKILLS_DIR = ".skills", GLOBAL_SKILLS_DIR, SKILLS_BLOCK_CHAR_LIMIT = 20000;
+var SKILLS_DIR = ".skills", GLOBAL_SKILLS_DIR, SKILLS_BLOCK_CHAR_LIMIT = 20000;
 var init_skills2 = __esm(() => {
-  init_SKILL();
-  BUNDLED_SKILL_SOURCES = [
-    { id: "memory-init", content: SKILL_default }
-  ];
   GLOBAL_SKILLS_DIR = join7(process.env.HOME || process.env.USERPROFILE || "~", ".letta/skills");
 });
 
@@ -17246,10 +16909,12 @@ function extractSkillsDir(skillsBlockValue) {
   return match2 ? match2[1]?.trim() || null : null;
 }
 async function readSkillContent(skillId, skillsDir) {
-  const bundledSkills = getBundledSkills();
+  const bundledSkills = await getBundledSkills();
   const bundledSkill = bundledSkills.find((s) => s.id === skillId);
-  if (bundledSkill?.content) {
-    return bundledSkill.content;
+  if (bundledSkill?.path) {
+    try {
+      return await readFile4(bundledSkill.path, "utf-8");
+    } catch {}
   }
   const globalSkillPath = join8(GLOBAL_SKILLS_DIR, skillId, "SKILL.md");
   try {
@@ -21381,7 +21046,7 @@ var exports_analyzer = {};
 __export(exports_analyzer, {
   analyzeApprovalContext: () => analyzeApprovalContext
 });
-import { dirname as dirname5, resolve as resolve13 } from "node:path";
+import { dirname as dirname6, resolve as resolve13 } from "node:path";
 function analyzeApprovalContext(toolName, toolArgs, workingDirectory) {
   const resolveFilePath = () => {
     const candidate = toolArgs.file_path ?? toolArgs.path ?? toolArgs.notebook_path ?? "";
@@ -21413,7 +21078,7 @@ function analyzeApprovalContext(toolName, toolArgs, workingDirectory) {
 function analyzeReadApproval(filePath, workingDir) {
   const absolutePath = resolve13(workingDir, filePath);
   if (!absolutePath.startsWith(workingDir)) {
-    const dirPath = dirname5(absolutePath);
+    const dirPath = dirname6(absolutePath);
     const displayPath = dirPath.replace(__require("node:os").homedir(), "~");
     return {
       recommendedRule: `Read(/${dirPath}/**)`,
@@ -21425,7 +21090,7 @@ function analyzeReadApproval(filePath, workingDir) {
     };
   }
   const relativePath = absolutePath.slice(workingDir.length + 1);
-  const relativeDir = dirname5(relativePath);
+  const relativeDir = dirname6(relativePath);
   const pattern = relativeDir === "." ? "**" : `${relativeDir}/**`;
   return {
     recommendedRule: `Read(${pattern})`,
@@ -21448,7 +21113,7 @@ function analyzeWriteApproval(_filePath, _workingDir) {
 }
 function analyzeEditApproval(filePath, workingDir) {
   const absolutePath = resolve13(workingDir, filePath);
-  const dirPath = dirname5(absolutePath);
+  const dirPath = dirname6(absolutePath);
   if (!dirPath.startsWith(workingDir)) {
     const displayPath = dirPath.replace(__require("node:os").homedir(), "~");
     return {
@@ -22404,40 +22069,19 @@ __export(exports_skills2, {
 });
 import { existsSync as existsSync4 } from "node:fs";
 import { readdir as readdir5, readFile as readFile5 } from "node:fs/promises";
-import { join as join10 } from "node:path";
-function parseBundledSkill2(id, content) {
-  const { frontmatter, body } = parseFrontmatter(content);
-  const name = (typeof frontmatter.name === "string" ? frontmatter.name : null) || id.split("/").pop()?.replace(/-/g, " ").replace(/\b\w/g, (l) => l.toUpperCase()) || id;
-  let description = typeof frontmatter.description === "string" ? frontmatter.description : null;
-  if (!description) {
-    const firstParagraph = body.trim().split(`
-
-`)[0];
-    description = firstParagraph || "No description available";
-  }
-  description = description.trim();
-  if (description.startsWith('"') && description.endsWith('"') || description.startsWith("'") && description.endsWith("'")) {
-    description = description.slice(1, -1);
-  }
-  let tags;
-  if (Array.isArray(frontmatter.tags)) {
-    tags = frontmatter.tags;
-  } else if (typeof frontmatter.tags === "string") {
-    tags = [frontmatter.tags];
+import { dirname as dirname7, join as join10 } from "node:path";
+import { fileURLToPath as fileURLToPath6 } from "node:url";
+function getBundledSkillsPath2() {
+  const thisDir = dirname7(fileURLToPath6(import.meta.url));
+  if (thisDir.includes("src/agent") || thisDir.includes("src\\agent")) {
+    return join10(thisDir, "../skills/builtin");
   }
-  return {
-    id,
-    name,
-    description,
-    category: typeof frontmatter.category === "string" ? frontmatter.category : undefined,
-    tags,
-    path: "",
-    source: "bundled",
-    content
-  };
+  return join10(thisDir, "skills");
 }
-function getBundledSkills2() {
-  return BUNDLED_SKILL_SOURCES2.map(({ id, content }) => parseBundledSkill2(id, content));
+async function getBundledSkills2() {
+  const bundledPath = getBundledSkillsPath2();
+  const result = await discoverSkillsFromDir2(bundledPath, "bundled");
+  return result.skills;
 }
 async function discoverSkillsFromDir2(skillsPath, source) {
   const errors = [];
@@ -22458,7 +22102,8 @@ async function discoverSkillsFromDir2(skillsPath, source) {
 async function discoverSkills2(projectSkillsPath = join10(process.cwd(), SKILLS_DIR2)) {
   const allErrors = [];
   const skillsById = new Map;
-  for (const skill2 of getBundledSkills2()) {
+  const bundledSkills = await getBundledSkills2();
+  for (const skill2 of bundledSkills) {
     skillsById.set(skill2.id, skill2);
   }
   const globalResult = await discoverSkillsFromDir2(GLOBAL_SKILLS_DIR2, "global");
@@ -22664,12 +22309,8 @@ function formatSkillsForMemory2(skills, skillsDirectory) {
   }
   return formatSkillsAsTree2(skills, skillsDirectory);
 }
-var BUNDLED_SKILL_SOURCES2, SKILLS_DIR2 = ".skills", GLOBAL_SKILLS_DIR2, SKILLS_BLOCK_CHAR_LIMIT2 = 20000;
+var SKILLS_DIR2 = ".skills", GLOBAL_SKILLS_DIR2, SKILLS_BLOCK_CHAR_LIMIT2 = 20000;
 var init_skills3 = __esm(() => {
-  init_SKILL();
-  BUNDLED_SKILL_SOURCES2 = [
-    { id: "memory-init", content: SKILL_default }
-  ];
   GLOBAL_SKILLS_DIR2 = join10(process.env.HOME || process.env.USERPROFILE || "~", ".letta/skills");
 });
 
@@ -22689,12 +22330,12 @@ import {
   writeFileSync as fsWriteFileSync2,
   mkdirSync as mkdirSync2
 } from "node:fs";
-import { dirname as dirname6 } from "node:path";
+import { dirname as dirname8 } from "node:path";
 async function readFile6(path15) {
   return fsReadFileSync2(path15, { encoding: "utf-8" });
 }
 async function writeFile2(path15, content) {
-  const dir = dirname6(path15);
+  const dir = dirname8(path15);
   if (!existsSync5(dir)) {
     mkdirSync2(dir, { recursive: true });
   }
@@ -47843,7 +47484,7 @@ __export(exports_open, {
 import process18 from "node:process";
 import { Buffer as Buffer3 } from "node:buffer";
 import path15 from "node:path";
-import { fileURLToPath as fileURLToPath5 } from "node:url";
+import { fileURLToPath as fileURLToPath7 } from "node:url";
 import { promisify as promisify8 } from "node:util";
 import childProcess from "node:child_process";
 import fs14, { constants as fsConstants2 } from "node:fs/promises";
@@ -48067,7 +47708,7 @@ var init_open = __esm(() => {
   init_default_browser();
   init_is_inside_container();
   execFile6 = promisify8(childProcess.execFile);
-  __dirname2 = path15.dirname(fileURLToPath5(import.meta.url));
+  __dirname2 = path15.dirname(fileURLToPath7(import.meta.url));
   localXdgOpenPath = path15.join(__dirname2, "xdg-open");
   ({ platform: platform2, arch } = process18);
   apps = {};
@@ -68050,7 +67691,7 @@ Press Enter to continue, or type anything to cancel.`, false, "running");
         const cmdId2 = uid4("cmd");
         const [, ...rest] = trimmed.split(/\s+/);
         const description = rest.join(" ").trim();
-        const initialOutput = description ? `Starting skill creation for: ${description}` : "Starting skill creation. I’ll load the skill-creator skill and ask a few questions about the skill you want to build...";
+        const initialOutput = description ? `Starting skill creation for: ${description}` : "Starting skill creation. I’ll load the creating-skills skill and ask a few questions about the skill you want to build...";
         buffersRef.current.byId.set(cmdId2, {
           kind: "command",
           id: cmdId2,
@@ -68227,10 +67868,10 @@ ${recentCommits}
           const initMessage = `<system-reminder>
 The user has requested memory initialization via /init.
 
-## 1. Load the memory-init skill
+## 1. Load the initializing-memory skill
 
-First, check your \`loaded_skills\` memory block. If the \`memory-init\` skill is not already loaded:
-1. Use the \`Skill\` tool with \`command: "load", skills: ["memory-init"]\`
+First, check your \`loaded_skills\` memory block. If the \`initializing-memory\` skill is not already loaded:
+1. Use the \`Skill\` tool with \`command: "load", skills: ["initializing-memory"]\`
 2. The skill contains comprehensive instructions for memory initialization
 
 If the skill fails to load, proceed with your best judgment based on these guidelines:
@@ -68241,7 +67882,7 @@ If the skill fails to load, proceed with your best judgment based on these guide
 
 ## 2. Follow the loaded skill instructions
 
-Once loaded, follow the instructions in the \`memory-init\` skill to complete the initialization.
+Once loaded, follow the instructions in the \`initializing-memory\` skill to complete the initialization.
 ${gitContext}
 </system-reminder>`;
           await processConversation([
@@ -71958,4 +71599,4 @@ Error during initialization: ${message}`);
 }
 main();
 
-//# debugId=AB315140F646E6AE64756E2164756E21
+//# debugId=CAAC5BC4B213F90764756E2164756E21

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@letta-ai/letta-code",
-  "version": "0.7.4-next.1",
+  "version": "0.7.4-next.3",
   "description": "Letta Code is a CLI tool for interacting with stateful Letta agents from the terminal.",
   "type": "module",
   "bin": {
@@ -11,6 +11,7 @@
     "README.md",
     "letta.js",
     "scripts",
+    "skills",
     "vendor"
   ],
   "repository": {