agent zero x skills #861
Open
agent zero x skills #861
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This commit completes the replacement of Agent Zero's legacy "instruments" system with the open SKILL.md standard (originally developed by Anthropic). - Remove INSTRUMENTS from Memory.Area enum, keep only SKILLS - Update memory.py to load skills instead of instruments - Update memory_consolidation.py docstrings - Delete agent.system.instruments.md (deprecated) - Update solving.md: "prefer skills" instead of "prefer instruments" - Update tips.md: Skills section with SKILL.md standard reference - Update tool.skills.md: Cross-platform compatibility note - architecture.md: Full rewrite of Skills section with SKILL.md format - installation.md: Update directory structure references - extensibility.md: Update component terminology - README.md: Update navigation links - Update memory dashboard filter options (instruments → skills) - Update area color mappings - .gitignore: Update skill patterns (builtin instead of default) - .dockerignore: Same patterns - backup.py: Update backup include patterns - Cross-platform: Works with Claude Code, Cursor, Goose, Codex CLI - YAML frontmatter for structured metadata - Semantic recall from vector memory - Token efficient (not in system prompt) 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <[email protected]>
## Skills Added - brainstorming: Structured requirements exploration before implementation - debugging: Systematic debugging methodology - tdd: Test-driven development workflow - code_review: Comprehensive code review checklist - git_workflow: Git branching and collaboration best practices - api_development: RESTful and GraphQL API design - docker_devops: Container and CI/CD best practices - database_design: Schema design and query optimization - prompt_engineering: LLM prompt crafting best practices - security_audit: OWASP-based security review - create_skill: Wizard for creating new skills easily ## Changes - Removed legacy instruments directory completely - Updated README, docs, and knowledge files to reference skills - Added skills_cli.py for easy skill management - All skills follow open SKILL.md standard (Anthropic) - Compatible with Claude Code, Cursor, Goose, Codex CLI, Copilot ## Usage - Skills auto-load into memory via vector database - Use `python -m python.helpers.skills_cli` for management - Create custom skills in skills/custom/ 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <[email protected]>
Add CONTRIBUTING-SKILLS.md with complete documentation for: - SKILL.md standard format with YAML frontmatter - Quick start guide using CLI tool - Step-by-step skill creation tutorial - Best practices for semantic matching - Testing and validation workflows - Sharing skills with the community - Cross-platform compatibility notes 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <[email protected]>
- Introduced Skills tab in the web UI for better user interaction
Replace Anthropic-specific _skill_args injection with standard CLI
argument conventions that work with any script regardless of origin.
Changes:
- Pass arguments via sys.argv (Python), process.argv (Node.js), and
positional parameters (Shell) instead of proprietary global injection
- Add arg_style parameter: "positional" (default), "named", or "env"
- positional: sys.argv = ['script.py', 'val1', 'val2']
- named: sys.argv = ['script.py', '--key1', 'val1', '--key2', 'val2']
- env: only SKILL_ARG_* environment variables
- Always set SKILL_ARG_* environment variables as fallback
- Fix CodeExecution missing 'log' attribute by calling before_execution()
- Update agent prompt documentation with new conventions and examples
This enables skills_tool to work with standard CLI scripts that use
sys.argv, argparse, click, or any other argument parsing method,
rather than requiring scripts to be written specifically for Agent Zero.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Summary
Changes
New Features
skills_importandskills_import_previewendpoints with dry-run supportArchitecture
skills/shared/<namespace>/skills/custom/<namespace>/usr/projects/<name>/.a0proj/skills/<namespace>/