@amrhas82/agentic-kit 1.7.0 → 1.7.6

package/packages/opencode/command/skill-creator.md

@@ -1,18 +1,32 @@
 ---
-description: Guide for creating effective skills that extend Claude's capabilities with specialized knowledge
-argument-hint: <skill-concept>
+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 Claude's capabilities with specialized knowledge, workflows, or tool integrations.
+usage: /skill-creator <skill-type> <skill-description>
+auto_trigger: false
+license: Complete terms in LICENSE.txt
 ---
 
-Create effective skills that extend Claude's capabilities with specialized knowledge, workflows, and tool integrations.
+# Skill Creator
 
-## What Skills Provide
+This skill provides guidance for creating effective skills.
 
-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 tasks
+## About Skills
 
-## Anatomy of a Skill
+Skills are modular, self-contained packages that extend Claude's capabilities by providing
+specialized knowledge, workflows, and tools. Think of them as "onboarding guides" for specific
+domains or tasks—they transform Claude 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
+
+### Anatomy of a Skill
+
+Every skill consists of a required SKILL.md file and optional bundled resources:
 
 ```
 skill-name/
@@ -23,174 +37,175 @@ skill-name/
 │   └── Markdown instructions (required)
 └── Bundled Resources (optional)
     ├── scripts/          - Executable code (Python/Bash/etc.)
-    ├── references/       - Documentation for context loading
-    └── assets/           - Files used in output (templates, icons, fonts)
+    ├── references/       - Documentation intended to be loaded into context as needed
+    └── assets/           - Files used in output (templates, icons, fonts, etc.)
 ```
 
-### SKILL.md Structure
+#### SKILL.md (required)
 
-**YAML Frontmatter:**
-```yaml
----
-name: skill-name
-description: This skill should be used when [specific use case]. [What it does].
-license: License information
----
-```
+**Metadata Quality:** The `name` and `description` in YAML frontmatter determine when Claude will use the skill. Be specific about what the skill does and when to use it. Use the third-person (e.g. "This skill should be used when..." instead of "Use this skill when...").
+
+#### Bundled Resources (optional)
+
+##### Scripts (`scripts/`)
+
+Executable code (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.py` for PDF rotation tasks
+- **Benefits**: Token efficient, deterministic, may be executed without loading into context
+- **Note**: Scripts may still need to be read by Claude for patching or environment-specific adjustments
+
+##### References (`references/`)
+
+Documentation and reference material intended to be loaded as needed into context to inform Claude's process and thinking.
+
+- **When to include**: For documentation that Claude 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 Claude 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 Claude 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 Claude to use files without loading them into context
+
+### 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 Claude (Unlimited*)
 
-**Content Guidelines:**
-- Be specific about what the skill does and when to use it
-- Use third-person perspective ("This skill should be used when...")
-- Keep body under 5k words for context efficiency
-- Include concrete examples and patterns
-- Progressive disclosure: core info in SKILL.md, detailed info in references/
-
-### Bundled Resources
-
-#### Scripts (`scripts/`)
-- **Purpose:** Deterministic, reusable code that gets rewritten repeatedly
-- **When to include:** Same code patterns across projects, need reliability
-- **Examples:** PDF rotation, data transformation, file processing
-- **Benefits:** Token efficient, deterministic, executable without context loading
-
-#### References (`references/`)
-- **Purpose:** Documentation loaded as needed into context
-- **When to include:** Large documentation, schemas, API specs, company policies
-- **Best practices:** 
-  - Keep SKILL.md lean (<5k words)
-  - Move detailed info to references files
-  - Use grep patterns for large files (>10k words)
-- **Examples:** Financial schemas, API documentation, domain knowledge
-
-#### Assets (`assets/`)
-- **Purpose:** Files used in output, not loaded into context
-- **When to include:** Templates, images, boilerplate code, fonts
-- **Examples:** HTML templates, PowerPoint slides, brand assets, sample documents
-- **Benefits:** Separates output resources from documentation
+*Unlimited because scripts can be executed without reading into context window.
 
 ## Skill Creation Process
 
-### Step 1: Understanding with Concrete Examples
+To create a skill, follow the "Skill Creation Process" in order, skipping steps only if there is a clear reason why they are not applicable.
 
-Understand concrete usage patterns before building:
+### Step 1: Understanding the Skill with Concrete Examples
 
-**Questions to ask:**
-- What functionality should this skill support?
-- Can you give examples of how this skill would be used?
-- What are the most common workflows?
-- What knowledge gaps exist that this skill should fill?
+Skip this step only when the skill's usage patterns are already clearly understood. It remains valuable even when working with an existing skill.
 
-**Validation:** Generate examples and validate with user feedback
+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.
 
-### Step 2: Define Scope and Boundaries
+For example, when building an image-editor skill, relevant questions include:
 
-**Scope definition:**
-- What is IN the skill's domain?
-- What is OUT of scope?
-- When should this skill trigger vs. other skills?
+- "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?"
 
-**Naming guidelines:**
-- Use descriptive, domain-specific names
-- Avoid generic names ("file-handler" vs. "document-processor")
-- Consider workflow names users would recognize
+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.
 
-### Step 3: Structure the Knowledge
+Conclude this step when there is a clear sense of the functionality the skill should support.
 
-**Progressive disclosure:**
-1. **Metadata** (100 words) - Always loaded
-2. **SKILL.md body** (<5k words) - When skill triggers  
-3. **Bundled resources** (unlimited) - As needed
+### Step 2: Planning the Reusable Skill Contents
 
-**Content organization:**
-- Core procedural knowledge in SKILL.md
-- Detailed reference material in references/
-- Reusable code patterns in scripts/
-- Output templates in assets/
+To turn concrete examples into an effective skill, analyze each example by:
 
-### Step 4: Write Effective Instructions
+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
 
-**Instruction quality:**
-- Clear, actionable steps
-- Concrete examples with actual code
-- Common patterns and anti-patterns
-- Edge cases and error handling
-- Integration points with other tools
+Example: When building a `pdf-editor` skill to handle queries like "Help me rotate this PDF," the analysis shows:
 
-**Examples structure:**
-```markdown
-## Usage Examples
+1. Rotating a PDF requires re-writing the same code each time
+2. A `scripts/rotate_pdf.py` script would be helpful to store in the skill
 
-**Basic usage:**
-`/skill-name input-file`
+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:
 
-**Advanced workflow:**
-`/skill-name complex-input --option value`
+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
 
-**Common patterns:**
-```typescript
-// Example code showing the pattern
-```
+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.py` 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
+scripts/init_skill.py <skill-name> --path <output-directory>
 ```
 
-### Step 5: Add Bundled Resources
+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
 
-**Scripts inclusion criteria:**
-- Code rewritten repeatedly across projects
-- Deterministic operations requiring reliability
-- Complex multi-step workflows
+After initialization, customize or remove the generated SKILL.md and example files as needed.
 
-**References inclusion criteria:**
-- Documentation >10k words
-- Technical specifications and schemas
-- Company policies and procedures
-- API documentation and examples
+### Step 4: Edit the Skill
 
-**Assets inclusion criteria:**
-- Templates used in output
-- Brand materials and styling
-- Boilerplate code structures
-- Sample documents for modification
+When editing the (newly-generated or existing) skill, remember that the skill is being created for another instance of Claude to use. Focus on including information that would be beneficial and non-obvious to Claude. Consider what procedural knowledge, domain-specific details, or reusable assets would help another Claude instance execute these tasks more effectively.
 
-### Step 6: Test and Refine
+#### Start with Reusable Skill Contents
 
-**Testing approach:**
-- Create example use cases
-- Validate with real scenarios
-- Check instruction clarity
-- Verify bundled resource integration
+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/`.
 
-**Quality checklist:**
-- [ ] Name and description are specific and accurate
-- [ ] Instructions are actionable and clear
-- [ ] Examples demonstrate real usage
-- [ ] Bundled resources are properly organized
-- [ ] Progressive disclosure works effectively
+Also, delete any example files and directories not needed for the skill. The initialization script creates example files in `scripts/`, `references/`, and `assets/` to demonstrate structure, but most skills won't need all of them.
 
-## Best Practices
+#### Update SKILL.md
+
+**Writing Style:** Write the entire skill using **imperative/infinitive form** (verb-first instructions), not second person. Use objective, instructional language (e.g., "To accomplish X, do Y" rather than "You should do X" or "If you need to do X"). This maintains consistency and clarity for AI consumption.
+
+To complete SKILL.md, answer the following questions:
+
+1. What is the purpose of the skill, in a few sentences?
+2. When should the skill be used?
+3. In practice, how should Claude use the skill? All reusable skill contents developed above should be referenced so that Claude knows how to use them.
+
+### Step 5: Packaging a Skill
+
+Once the skill is ready, it should be packaged into a distributable zip file that gets shared with the user. The packaging process automatically validates the skill first to ensure it meets all requirements:
+
+```bash
+scripts/package_skill.py <path/to/skill-folder>
+```
+
+Optional output directory specification:
+
+```bash
+scripts/package_skill.py <path/to/skill-folder> ./dist
+```
 
-**Do:**
-- Be specific about use cases and boundaries
-- Include concrete examples and patterns
-- Use progressive disclosure for complex topics
-- Bundle resources when reused across projects
-- Test with real scenarios
+The packaging script will:
 
-**Don't:**
-- Make instructions too generic
-- Include everything in SKILL.md
-- Create skills for single-use cases
-- Over-bundle resources unnecessarily
-- Skip validation with actual examples
+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
 
-## Usage Examples
+2. **Package** the skill if validation passes, creating a zip file named after the skill (e.g., `my-skill.zip`) that includes all files and maintains the proper directory structure for distribution.
 
-**Create new skill:**
-`/skill-creator "document processing skill for PDF forms"`
+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.
 
-**Improve existing skill:**
-`/skill-creator "enhance PDF processing with better error handling"`
+### Step 6: Iterate
 
-**Bundle resources:**
-`/skill-creator "create skill with scripts and reference docs"`
+After testing the skill, users may request improvements. Often this happens right after using the skill, with fresh context of how the skill performed.
 
-Remember: Skills are "onboarding guides" for specialized domains—they should transform Claude from general-purpose to specialized expert.
+**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

package/packages/opencode/command/subagent-spawning.md

@@ -0,0 +1,81 @@
+---
+name: subagent-spawning
+description: Use when spawning fresh subagents for isolated task execution. Provides TDD-aware templates for 3-process-task-list and other agents.
+usage: Used by 3-process-task-list and other agents for clean subagent execution
+auto_trigger: true
+---
+
+## Auto-Trigger
+
+**APPLIES WHEN:**
+- 3-process-task-list spawning implementer for a task
+- Any agent delegating work to fresh subagent
+- Task isolation needed (prevent context pollution)
+
+**APPLIES TO:**
+- Task list processing
+- Parallel task execution
+- Complex multi-step implementations
+
+## Template A: With TDD (when tdd: yes)
+
+```
+You are implementing Task: {task_description}
+
+CONTEXT:
+{relevant_file_contents}
+
+ACCEPTANCE CRITERIA:
+{task_specific_criteria}
+
+TDD REQUIRED:
+Write test FIRST. Watch it FAIL. Then implement. Then watch it PASS.
+{tdd_note}
+
+VERIFY WITH: {verify_command}
+
+WORKFLOW:
+1. Write test for expected behavior
+2. Run test - MUST see it FAIL (red)
+3. Implement minimal code to pass
+4. Run test - verify it PASSES (green)
+5. Refactor if needed
+6. Report: test output (fail→pass) + changes + concerns
+
+CONSTRAINTS:
+- Do NOT implement before writing test
+- Do NOT skip red-green verification
+- Do NOT reference other tasks
+- Do NOT assume context not provided
+```
+
+## Template B: Without TDD (when tdd: no)
+
+```
+You are implementing Task: {task_description}
+
+CONTEXT:
+{relevant_file_contents}
+
+ACCEPTANCE CRITERIA:
+{task_specific_criteria}
+
+VERIFY WITH: {verify_command}
+
+WORKFLOW:
+1. Implement the task completely
+2. Run verify command BEFORE claiming done
+3. Report: changes + verify output + concerns
+
+CONSTRAINTS:
+- Do NOT reference other tasks
+- Do NOT assume context not provided
+- Do NOT claim done without verify output
+```
+
+## Why Fresh Subagents?
+
+- Task 1 confusion doesn't pollute task 5
+- Each task gets clean reasoning slate
+- Prevents "I already tried that" false memories
+- Forces explicit context = fewer assumptions