Requirements
- Target platform
- OpenClaw
- Install method
- Manual import
- Extraction
- Extract archive
- Prerequisites
- OpenClaw
- Primary doc
- SKILL.md
Tencent SkillHub Β· AI
Task Panner Validator for Agents
Provides secure task planning, validation, approval, and execution for AI agents with safety checks, rollback, dry runs, and error handling using pure Python.
skill openclawclawhub Free
Provides secure task planning, validation, approval, and execution for AI agents with safety checks, rollback, dry runs, and error handling using pure Python.
β¬ 0 downloads β
0 stars Unverified but indexed
Install for OpenClaw
Quick setup
- Download the package from Yavira.
- Extract the archive and review SKILL.md first.
- Import or place the package into your OpenClaw setup.
Package facts
- Download mode
- Yavira redirect
- Package format
- ZIP package
- Source platform
- Tencent SkillHub
- What's included
- API.md, CHANGELOG.md, CONTRIBUTING.md, GITHUB_SETUP.md, QUICKSTART.md, README.md
Validation
- Use the Yavira download entry.
- Review SKILL.md after the package is downloaded.
- Confirm the extracted package contains the expected setup assets.
Install with your agent
Agent handoff
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
- Download the package from Yavira.
- Extract it into a folder your agent can access.
- Paste one of the prompts below and point your agent at the extracted folder.
New install
I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Then review README.md for any prerequisites, environment setup, or post-install checks. Tell me what you changed and call out any manual steps you could not complete.
Upgrade existing
I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run.
Trust & source
Release facts
- Source
- Tencent SkillHub
- Verification
- Indexed source record
- Version
- 0.1.0
Provenance
- Publisher
- cerbug45
- Source page
- View original listing
- Canonical URL
- Open canonical page
Documentation
Task Planner and Validator - Skill Guide
This skill provides a secure, step-by-step task management system for AI Agents.
Quick Installation
# Clone the repository git clone https://github.com/cerbug45/task-planner-validator.git cd task-planner-validator # That's it! No dependencies needed - pure Python standard library
Verify Installation
# Run tests python test_basic.py # Run examples python examples.py
1. Import and Initialize
from task_planner import TaskPlanner # Create planner planner = TaskPlanner(auto_approve=False)
2. Define Your Executor
def my_executor(action: str, parameters: dict): """Your custom execution logic""" if action == "fetch_data": # Fetch data from API, database, etc. return {"data": [1, 2, 3]} elif action == "process_data": # Process the data return {"processed": True} else: return {"status": "completed"}
3. Create a Plan
steps = [ { "description": "Fetch user data", "action": "fetch_data", "parameters": {"source": "database"}, "expected_output": "List of users" }, { "description": "Process users", "action": "process_data", "parameters": {"validation": True}, "expected_output": "Processed data" } ] plan = planner.create_plan( title="Data Processing Pipeline", description="Fetch and process user data", steps=steps )
4. Validate and Execute
# Validate is_valid, warnings = planner.validate_plan(plan) if warnings: print("Warnings:", warnings) # Approve planner.approve_plan(plan, approved_by="admin") # Execute success, results = planner.execute_plan(plan, my_executor) # Get summary summary = planner.get_execution_summary(plan) print(f"Progress: {summary['progress_percentage']}%")
Safety Validation
Automatically detects dangerous operations: steps = [ { "description": "Delete old files", "action": "delete_files", # β οΈ Dangerous! "parameters": {"path": "/data/old"}, "safety_check": True, # System will warn "rollback_possible": False # Cannot undo } ]
Dry Run Mode
Test without executing: success, results = planner.execute_plan( plan, my_executor, dry_run=True # Simulate only )
Save and Load Plans
Persist plans for reuse: # Save planner.save_plan(plan, "my_plan.json") # Load later loaded_plan = planner.load_plan("my_plan.json") # Verify integrity if loaded_plan.verify_integrity(): planner.execute_plan(loaded_plan, my_executor)
Error Handling
Control error behavior: success, results = planner.execute_plan( plan, my_executor, stop_on_error=False # Continue on failures ) # Check results for result in results: if not result['success']: print(f"Step {result['order']} failed: {result['error']}")
Step Configuration
Each step supports these parameters: { "description": str, # Required: Human-readable description "action": str, # Required: Action identifier "parameters": dict, # Required: Action parameters "expected_output": str, # Required: Expected result "safety_check": bool, # Optional: Enable validation (default: True) "rollback_possible": bool, # Optional: Can be rolled back (default: True) "max_retries": int # Optional: Retry attempts (default: 3) }
API Orchestration
steps = [ { "description": "Authenticate", "action": "api_auth", "parameters": {"service": "github"}, "expected_output": "Auth token" }, { "description": "Fetch data", "action": "api_fetch", "parameters": {"endpoint": "/repos"}, "expected_output": "Repository list" } ]
Data Pipeline
steps = [ { "description": "Extract data", "action": "extract", "parameters": {"source": "database"}, "expected_output": "Raw data" }, { "description": "Transform data", "action": "transform", "parameters": {"rules": ["normalize", "validate"]}, "expected_output": "Clean data" }, { "description": "Load data", "action": "load", "parameters": {"destination": "warehouse"}, "expected_output": "Success confirmation" } ]
System Automation
steps = [ { "description": "Backup database", "action": "backup", "parameters": {"target": "postgres"}, "expected_output": "Backup file path", "rollback_possible": True }, { "description": "Update schema", "action": "migrate", "parameters": {"version": "2.0"}, "expected_output": "Migration complete", "rollback_possible": True }, { "description": "Verify integrity", "action": "verify", "parameters": {"checks": ["all"]}, "expected_output": "All checks passed" } ]
1. Always Validate First
is_valid, warnings = planner.validate_plan(plan) if not is_valid: print("Plan validation failed!") for warning in warnings: print(f" - {warning}") exit(1)
2. Use Descriptive Names
# Good β { "description": "Fetch active users from PostgreSQL production database", "action": "fetch_active_users_postgres_prod", ... } # Bad β { "description": "Get data", "action": "get", ... }
3. Mark Dangerous Operations
{ "description": "Delete temporary files older than 30 days", "action": "cleanup_temp_files", "parameters": {"age_days": 30, "path": "/tmp"}, "safety_check": True, # β οΈ Will trigger warnings "rollback_possible": False # β οΈ Cannot undo! }
4. Test with Dry Run
# Always test first success, results = planner.execute_plan(plan, my_executor, dry_run=True) if success: # Now run for real success, results = planner.execute_plan(plan, my_executor, dry_run=False)
5. Handle Errors Gracefully
def safe_executor(action: str, parameters: dict): try: result = execute_action(action, parameters) return result except Exception as e: logging.error(f"Failed to execute {action}: {e}") raise # Re-raise to let planner handle it
Auto-Approve for Automation
# Skip manual approval for automated workflows planner = TaskPlanner(auto_approve=True)
Checkpoint System
# Checkpoints are automatically created for rollback-capable steps # Access checkpoint history checkpoints = planner.executor.checkpoint_stack
Execution History
# View execution history history = planner.executor.execution_history for entry in history: print(f"{entry['timestamp']}: {entry['step_id']} - {entry['status']}")
Custom Validation Rules
# Add custom validation to SafetyValidator planner.safety_validator.dangerous_operations.append('my_dangerous_op') planner.safety_validator.sensitive_paths.append('/my/sensitive/path')
"Plan must be approved before execution"
# Solution: Approve the plan first planner.approve_plan(plan, approved_by="admin") # Or use auto-approve mode planner = TaskPlanner(auto_approve=True)
Safety validation warnings
# Review warnings and ensure operations are intentional is_valid, warnings = planner.validate_plan(plan) for warning in warnings: print(warning) # If operations are safe, approve anyway if is_valid: # Still valid, just warnings planner.approve_plan(plan)
Steps executing out of order
# Ensure order values are sequential steps[0]['order'] = 1 steps[1]['order'] = 2 steps[2]['order'] = 3
File Structure
task-planner-validator/ βββ task_planner.py # Main library βββ examples.py # Usage examples βββ test_basic.py # Test suite βββ README.md # Full documentation βββ QUICKSTART.md # Quick start guide βββ API.md # API reference βββ SKILL.md # This file βββ LICENSE # MIT License
Requirements
Python 3.8 or higher No external dependencies!
Testing
# Run basic tests python test_basic.py # Run examples python examples.py # Both should show "β ALL TESTS PASSED"
Getting Help
π Read full documentation in README.md π Check QUICKSTART.md for quick examples π See API.md for complete API reference π‘ Browse examples.py for real code π Report issues on GitHub
License
MIT License - see LICENSE file
Author
cerbug45 GitHub: @cerbug45 β If you find this useful, star the repository on GitHub!
Category context
Agent frameworks, memory systems, reasoning layers, and model-native orchestration.
Source: Tencent SkillHub
Largest current source with strong distribution and engagement signals.
Package contents
Included in package
6 Docs
- API.md
- CHANGELOG.md
- CONTRIBUTING.md
- GITHUB_SETUP.md
- QUICKSTART.md
- README.md