mirror of
https://github.com/K-Dense-AI/claude-scientific-skills.git
synced 2026-01-26 16:58:56 +08:00
Fix context initialization by using AGENTS.md instead of AGENT.md
This commit is contained in:
Timothy Kassis
@@ -7,7 +7,7 @@
|
||||
},
|
||||
"metadata": {
|
||||
"description": "Claude scientific skills from K-Dense Inc",
|
||||
"version": "1.61.0"
|
||||
"version": "1.62.0"
|
||||
},
|
||||
"plugins": [
|
||||
{
|
||||
|
||||
@@ -86,7 +86,7 @@ Then, to install a specific set of skills:
|
||||
|
||||
After installation, simply mention the skill or describe your task - Claude Code will automatically use the appropriate skills!
|
||||
|
||||
> 💡 **Tip**: If you find that Claude isn't utilizing the installed skills as much as you'd like, install the `scientific-context-initialization` skill. It automatically creates/updates an `AGENT.md` file in your workspace that instructs Claude to always search for and use existing skills before attempting any scientific task. This ensures Claude leverages documented patterns, authentication methods, working examples, and best practices from the repository.
|
||||
> 💡 **Tip**: If you find that Claude isn't utilizing the installed skills as much as you'd like, install the `scientific-context-initialization` skill. It automatically creates/updates an `AGENTS.md` file in your workspace that instructs Claude to always search for and use existing skills before attempting any scientific task. This ensures Claude leverages documented patterns, authentication methods, working examples, and best practices from the repository.
|
||||
|
||||
### Any MCP Client (including ChatGPT, Cursor, Google ADK, OpenAI Agent SDK, etc.)
|
||||
Use our newly released MCP server that allows you to use any Claude Skill in any client!
|
||||
@@ -382,7 +382,7 @@ results, conclusions and providing recommendations."
|
||||
### 🛠️ Scientific Helpers
|
||||
**2 helper utilities** for enhanced scientific computing capabilities.
|
||||
|
||||
- **scientific-context-initialization** - Auto-invoked skill that creates/updates workspace AGENT.md to instruct Claude to search for and use existing skills before attempting any scientific task
|
||||
- **scientific-context-initialization** - Auto-invoked skill that creates/updates workspace AGENTS.md to instruct Claude to search for and use existing skills before attempting any scientific task
|
||||
- **get-available-resources** - Detects available system resources (CPU cores, GPUs, memory, disk space) and generates strategic recommendations for computational approaches (parallel processing, out-of-core computing, GPU acceleration)
|
||||
|
||||
---
|
||||
@@ -447,7 +447,7 @@ Your contributions help make scientific computing more accessible and enable res
|
||||
|
||||
**Problem: Claude not using installed skills**
|
||||
- Solution: Install the `scientific-context-initialization` skill
|
||||
- This creates an `AGENT.md` file that instructs Claude to search for and use existing skills before attempting tasks
|
||||
- This creates an `AGENTS.md` file that instructs Claude to search for and use existing skills before attempting tasks
|
||||
- After installation, Claude will automatically leverage documented patterns, examples, and best practices
|
||||
|
||||
**Problem: Skills not loading in Claude Code**
|
||||
|
||||
@@ -1,13 +1,13 @@
|
||||
---
|
||||
name: context-initialization
|
||||
description: "Always Auto-invoked skill that creates/updates workspace AGENT.md to instruct the agent to always search for existing skills before attempting any scientific task."
|
||||
description: "Always Auto-invoked skill that creates/updates workspace AGENTS.md to instruct the agent to always search for existing skills before attempting any scientific task."
|
||||
---
|
||||
|
||||
# Context Initialization
|
||||
|
||||
## Overview
|
||||
|
||||
This skill automatically creates or updates an `AGENT.md` file in the workspace root that instructs the agent to use existing skills before attempting to solve scientific tasks. This ensures the agent uses documented patterns, authentication methods, working examples, and best practices from the repository's skills rather than inventing solutions from scratch.
|
||||
This skill automatically creates or updates an `AGENTS.md` file in the workspace root that instructs the agent to use existing skills before attempting to solve scientific tasks. This ensures the agent uses documented patterns, authentication methods, working examples, and best practices from the repository's skills rather than inventing solutions from scratch.
|
||||
|
||||
## When to Use This Skill
|
||||
|
||||
@@ -21,14 +21,14 @@ This skill is automatically invoked when:
|
||||
|
||||
## What This Skill Does
|
||||
|
||||
Creates or updates `AGENT.md` in the workspace root with instructions for the agent to:
|
||||
Creates or updates `AGENTS.md` in the workspace root with instructions for the agent to:
|
||||
|
||||
1. **Search first**: Look for relevant skills across all skill categories before writing code
|
||||
2. **Use existing patterns**: Apply documented API access patterns, workflows, and examples
|
||||
3. **Follow best practices**: Use rate limits, authentication, configurations, and established methodologies
|
||||
4. **Adapt examples**: Leverage working code examples from `scripts/` folders and reference documentation
|
||||
|
||||
**Important**: If `AGENT.md` already exists in the workspace, this skill will update it intelligently rather than overwriting it. This preserves any custom instructions or modifications while ensuring the essential skill-search directives are present.
|
||||
**Important**: If `AGENTS.md` already exists in the workspace, this skill will update it intelligently rather than overwriting it. This preserves any custom instructions or modifications while ensuring the essential skill-search directives are present.
|
||||
|
||||
## Skill Categories
|
||||
|
||||
@@ -61,14 +61,14 @@ This unified context initialization covers four major skill categories:
|
||||
|
||||
## Implementation
|
||||
|
||||
When invoked, this skill manages the workspace `AGENT.md` file as follows:
|
||||
When invoked, this skill manages the workspace `AGENTS.md` file as follows:
|
||||
|
||||
- **If `AGENT.md` does not exist**: Creates a new file using the complete template from `references/AGENT.md`
|
||||
- **If `AGENT.md` already exists**: Updates the file to ensure the essential skill-search directives are present, while preserving any existing custom content or modifications
|
||||
- **If `AGENTS.md` does not exist**: Creates a new file using the complete template from `references/AGENTS.md`
|
||||
- **If `AGENTS.md` already exists**: Updates the file to ensure the essential skill-search directives are present, while preserving any existing custom content or modifications
|
||||
|
||||
The file includes sections instructing the agent to search for and use existing skills across all scientific task categories.
|
||||
|
||||
The complete reference template is available in `references/AGENT.md`.
|
||||
The complete reference template is available in `references/AGENTS.md`.
|
||||
|
||||
## Benefits
|
||||
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
# Reference: Complete Context Initialization Template
|
||||
|
||||
This is the complete reference template for what gets added to the workspace root `AGENT.md` file.
|
||||
This is the complete reference template for what gets added to the workspace root `AGENTS.md` file.
|
||||
|
||||
---
|
||||
|
||||
@@ -70,3 +70,4 @@ Always use available methodology skills before attempting scientific analysis or
|
||||
|
||||
*This file is auto-generated by context-initialization skills. It ensures the agent uses available skills before attempting to solve scientific tasks from scratch.*
|
||||
|
||||
|
||||
Reference in New Issue
Block a user