Automated summary
This skill activates Claude Code Guardian MCP tools for persistent memory, code validation, task tracking, and multi-agent coordination.
Strengths
- Persistent memory for recalling decisions, facts, and patterns across sessions
- Security and quality validation through ten rules, including SQL injection, XSS, and hardcoded secrets
- Workflow tracking with task creation, start, and completion
- Coordination of specialized agents for Trading, Laravel, React, and Node.js
Limitations
- Requires the Code Guardian MCP tools to be installed and available in Claude Code
- Validation is limited to the declared rule set and may produce false positives or miss specific cases
- Specialized agents cover only Trading, Laravel, React, and Node.js, not every stack
Use it when starting a multi-file development session that needs memory, task tracking, or validation before committing.
Avoid it when the Code Guardian MCP tools are not configured or for a small one-off change that needs neither memory nor validation.
Security analysis
SafeThe skill only documents usage of the code-guardian MCP tools for memory, validation, workflow, and agent coordination. It does not instruct any destructive, exfiltrating, or obfuscated actions, and its allowed-tools are scoped exclusively to the mcp__code-guardian__* namespace.
No concerns found
How this analysis is madeExamples
Use CCG Guardian to initialize a session, create a workflow task, and refactor the authentication module with guard validation before finishing.Use the Code Guardian memory tools to recall our previous decisions about the payments service, then store the new API error-handling pattern with importance 8.Run CCG guard validation on the files I changed, check for fake tests, and list any security issues before I commit.name: ccg-guardian description: "Use this skill when working on code projects that need memory persistence, code validation, multi-agent coordination, or workflow tracking. Activates Claude Code Guardian MCP tools." allowed-tools:
- mcp__code-guardian__*
CCG Guardian Skill
Enterprise-grade development assistance with persistent memory, code validation, and multi-agent coordination.
When to Use
Activate this skill when:
- Starting a new development session (call
session_init) - Need to remember decisions, patterns, or context across sessions
- Want code validation before commits (security, quality checks)
- Working on multi-file tasks that need progress tracking
- Need specialized agent guidance (Trading, Laravel, React, Node.js)
Core Capabilities
1. Memory System
memory_store - Save decisions, facts, patterns (importance 1-10)
memory_recall - Search memories by query, tags, type
memory_list - List all memories with filters
2. Guard System (10 Security Rules)
guard_validate - Check code for vulnerabilities
guard_check_test - Detect fake tests without assertions
guard_rules - List all validation rules
Rules include: SQL Injection, XSS, Command Injection, Path Traversal, Prompt Injection, Hardcoded Secrets, Empty Catch, Disabled Features, Fake Tests, Emoji in Code
3. Workflow & Tasks
workflow_task_create - Create task with priority/tags
workflow_task_start - Begin working on task
workflow_task_complete - Mark task done
workflow_current - Get current active task
4. Multi-Agent System
agents_list - List specialized agents
agents_select - Auto-select best agent for task
agents_coordinate - Coordinate multiple agents
Available Agents:
- Trading Agent - Quant systems, risk management, backtesting
- Laravel Agent - PHP backend, Eloquent, REST APIs
- React Agent - Components, hooks, state management
- Node Agent - Event-driven, workers, orchestration
5. Resource Management
resource_status - Token usage and checkpoints
resource_checkpoint_create - Save current progress
resource_checkpoint_restore - Restore from checkpoint
Workflow Pattern
1. session_init → Load memory, check status
2. workflow_task_create → Define what you're doing
3. memory_recall → Get relevant context
4. [do work]
5. guard_validate → Check code quality
6. memory_store → Save important decisions
7. workflow_task_complete → Mark done
8. session_end → Save all data
Best Practices
- Always start with
session_init- Loads previous context - Store important decisions - Use importance 8-10 for critical items
- Validate before commit - Run
guard_validateon changed files - Track progress - Use workflow tasks for multi-step work
- End sessions properly - Call
session_endto persist data
Example Usage
"Use CCG to help me refactor the authentication module with proper memory and validation"
Claude will:
- Initialize session and recall relevant memories
- Create a task for tracking
- Select appropriate agent (Node or Laravel)
- Apply changes with guard validation
- Store decisions for future reference
From the file to a first result
The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.
View the source and supporting filesThis download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.
1. Download the file
Download SKILL.mdFrom the root of a test project, save the file as .skill-downloads/ccg-guardian-enterprise-dev-assistance-mmlj2oe1/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.
Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.
mkdir -p '.skill-downloads/ccg-guardian-enterprise-dev-assistance-mmlj2oe1' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/ccg-guardian-enterprise-dev-assistance-mmlj2oe1/download' --output '.skill-downloads/ccg-guardian-enterprise-dev-assistance-mmlj2oe1/SKILL.md.part' && mv '.skill-downloads/ccg-guardian-enterprise-dev-assistance-mmlj2oe1/SKILL.md.part' '.skill-downloads/ccg-guardian-enterprise-dev-assistance-mmlj2oe1/SKILL.md'2. Check prerequisites
Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.
No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.
The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.
3. Load the skill
After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.
Claude Code
test -f '.skill-downloads/ccg-guardian-enterprise-dev-assistance-mmlj2oe1/SKILL.md' && test -s '.skill-downloads/ccg-guardian-enterprise-dev-assistance-mmlj2oe1/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/ccg-guardian' && cp -R '.skill-downloads/ccg-guardian-enterprise-dev-assistance-mmlj2oe1' '.claude/skills/ccg-guardian'OpenSkills
OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.
Official OpenSkills installationopenskills install './.skill-downloads/ccg-guardian-enterprise-dev-assistance-mmlj2oe1'openskills read 'ccg-guardian-enterprise-dev-assistance-mmlj2oe1'Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.
For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.
openskills syncManual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.
4. Try a first task
Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:
Read .skill-downloads/ccg-guardian-enterprise-dev-assistance-mmlj2oe1/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.
React Hook Form Best Practices
Development
Master React Hook Form: avoid anti-patterns, manage subscriptions, and handle reset, dirty state, and controlled inputs correctly.
Emotion to Mantine Migration
Development
Migrate Emotion styled-components to Mantine components with style props and CSS modules. Use when converting .styled.tsx files or removing @emotion imports.
Scope Creep Detector
Development
Analyzes git diffs against a stated intent to detect scope creep, unrelated files, broad PRs, and oversized changes, then suggests keep, split, or justify actions.