Not in the top 1,000 by GitHub stars
Gen-Verse/PAST-Bench
PAST-Bench: Benchmarking the Foundations of Recursive Self-Improvement in Personal Agents
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
agents/agent-zero/skills/a0-contribute-plugin/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → f8223517ae74
No earlier version was observed for comparison.
agents/agent-zero/skills/a0-create-plugin/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → f8223517ae74
No earlier version was observed for comparison.
agents/agent-zero/skills/a0-debug-plugin/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → f8223517ae74
No earlier version was observed for comparison.
agents/agent-zero/skills/a0-development/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → f8223517ae74
No earlier version was observed for comparison.
agents/agent-zero/skills/a0-manage-plugin/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → f8223517ae74
No earlier version was observed for comparison.
agents/agent-zero/skills/a0-plugin-router/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → f8223517ae74
No earlier version was observed for comparison.
agents/agent-zero/skills/a0-review-plugin/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → f8223517ae74
No earlier version was observed for comparison.
agents/agent-zero/skills/create-skill/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → f8223517ae74
No earlier version was observed for comparison.
agents/nanobot/nanobot/skills/clawhub/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → f8223517ae74
No earlier version was observed for comparison.
agents/nanobot/nanobot/skills/cron/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → f8223517ae74
No earlier version was observed for comparison.
agents/nanobot/nanobot/skills/github/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → f8223517ae74
No earlier version was observed for comparison.
agents/nanobot/nanobot/skills/memory/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → f8223517ae74
No earlier version was observed for comparison.
agents/nanobot/nanobot/skills/skill-creator/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → f8223517ae74
No earlier version was observed for comparison.
agents/nanobot/nanobot/skills/summarize/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → f8223517ae74
No earlier version was observed for comparison.
agents/nanobot/nanobot/skills/tmux/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → f8223517ae74
No earlier version was observed for comparison.
agents/nanobot/nanobot/skills/weather/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → f8223517ae74
No earlier version was observed for comparison.
self-evolve-tasks-v2/_shared/home_fixtures/update_ability/EP03_recall_then_modify/skills/onboarding-playbook-cache/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → f8223517ae74
No earlier version was observed for comparison.
self-evolve-tasks-v2/_shared/home_fixtures/update_ability/PC02_sop_patch_01/skills/billing-incident-sop/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → f8223517ae74
No earlier version was observed for comparison.
self-evolve-tasks-v2/_shared/home_fixtures/update_ability/PC02_sop_patch_01/skills/billing-refund-sop/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → f8223517ae74
No earlier version was observed for comparison.
self-evolve-tasks-v2/_shared/home_fixtures/update_ability/PC02_sop_patch_01/skills/legacy-billing-sop-archive/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → f8223517ae74
No earlier version was observed for comparison.
self-evolve-tasks-v2/_shared/home_fixtures/update_ability/PC02_sop_patch_02/skills/http-client-migration/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → f8223517ae74
No earlier version was observed for comparison.
self-evolve-tasks-v2/_shared/home_fixtures/update_ability/PC02_sop_patch_02/skills/legacy-http-client-archive/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → f8223517ae74
No earlier version was observed for comparison.
self-evolve-tasks-v2/_shared/home_fixtures/update_ability/PC02_sop_patch_02/skills/python-networking-style/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → f8223517ae74
No earlier version was observed for comparison.
self-evolve-tasks-v2/_shared/home_fixtures/update_ability/SM03_fact_correction/skills/phoenix-rollout-review/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → f8223517ae74
No earlier version was observed for comparison.
self-evolve-tasks-v2/_shared/home_fixtures/update_ability/SM04_rule_migration/skills/review-routing-archive/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → f8223517ae74
No earlier version was observed for comparison.
self-evolve-tasks-v2/_shared/home_fixtures/update_ability/SM06_temporary_exception_pollution/skills/risk-review-archive/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → f8223517ae74
No earlier version was observed for comparison.
self-evolve-tasks-v2/_shared/home_fixtures/update_ability/SM07_scoped_rule_migration/skills/scoped-routing-archive/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → f8223517ae74
No earlier version was observed for comparison.
self-evolve-tasks-v2/_shared/preseed/pg06_control_scope_patch_mismatch/skills/kappa_review_workflow/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → f8223517ae74
No earlier version was observed for comparison.
self-evolve-tasks-v2/proactive_information_gathering/PG01_release_decision_followup/_family_seed/skills/release_followup_lookup/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → f8223517ae74
No earlier version was observed for comparison.
self-evolve-tasks-v2/proactive_information_gathering/PG02_ops_exception_desk/_family_seed/skills/ops_exception_desk_workflow/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → f8223517ae74
No earlier version was observed for comparison.
self-evolve-tasks-v2/proactive_information_gathering/PG03_oncall_handoff_lookup/_family_seed/skills/oncall_handoff_lookup/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → f8223517ae74
No earlier version was observed for comparison.
self-evolve-tasks-v2/proactive_information_gathering/PG04_temporary_waiver_audit/_family_seed/skills/temporary_waiver_audit/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → f8223517ae74
No earlier version was observed for comparison.
self-evolve-tasks-v2/proactive_information_gathering/PG05_change_freeze_followup/_family_seed/skills/change_freeze_lookup/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → f8223517ae74
No earlier version was observed for comparison.
self-evolve-tasks-v2/proactive_information_gathering/PG06_kappa_integration_review/_family_seed/skills/kappa_review_workflow/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → f8223517ae74
No earlier version was observed for comparison.
Verified commit f8223517ae7491e776b69793d9f11e9d074ab42e
git clone --filter=blob:none --no-checkout https://github.com/Gen-Verse/PAST-Bench.git .hotskills/gen-verse-past-bench && git -C .hotskills/gen-verse-past-bench checkout --detach f8223517ae7491e776b69793d9f11e9d074ab42e
# Copy each selected skill directory from .hotskills/gen-verse-past-bench into .agents/skills/<skill-name>/Heat
0.3- Star growth, last 7 daysNot available
- Star growth, last 24 hoursNot available
- Rank movement, last 7 daysNot available
- Commits, last 30 daysNot available
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekNot available
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
30-day change not yet available: not enough history.
Individual skills in this repository
- a0-contribute-plugin
agents/agent-zero/skills/a0-contribute-plugin - a0-create-plugin
agents/agent-zero/skills/a0-create-plugin - a0-debug-plugin
agents/agent-zero/skills/a0-debug-plugin - a0-development
agents/agent-zero/skills/a0-development - a0-manage-plugin
agents/agent-zero/skills/a0-manage-plugin - a0-plugin-router
agents/agent-zero/skills/a0-plugin-router - a0-review-plugin
agents/agent-zero/skills/a0-review-plugin - create-skill
agents/agent-zero/skills/create-skill - clawhub
agents/nanobot/nanobot/skills/clawhub - cron
agents/nanobot/nanobot/skills/cron - github
agents/nanobot/nanobot/skills/github - memory
agents/nanobot/nanobot/skills/memory - skill-creator
agents/nanobot/nanobot/skills/skill-creator - summarize
agents/nanobot/nanobot/skills/summarize - tmux
agents/nanobot/nanobot/skills/tmux - weather
agents/nanobot/nanobot/skills/weather - onboarding-playbook-cache
self-evolve-tasks-v2/_shared/home_fixtures/update_ability/EP03_recall_then_modify/skills/onboarding-playbook-cache - billing-incident-sop
self-evolve-tasks-v2/_shared/home_fixtures/update_ability/PC02_sop_patch_01/skills/billing-incident-sop - billing-refund-sop
self-evolve-tasks-v2/_shared/home_fixtures/update_ability/PC02_sop_patch_01/skills/billing-refund-sop - legacy-billing-sop-archive
self-evolve-tasks-v2/_shared/home_fixtures/update_ability/PC02_sop_patch_01/skills/legacy-billing-sop-archive - http-client-migration
self-evolve-tasks-v2/_shared/home_fixtures/update_ability/PC02_sop_patch_02/skills/http-client-migration - legacy-http-client-archive
self-evolve-tasks-v2/_shared/home_fixtures/update_ability/PC02_sop_patch_02/skills/legacy-http-client-archive - python-networking-style
self-evolve-tasks-v2/_shared/home_fixtures/update_ability/PC02_sop_patch_02/skills/python-networking-style - phoenix-rollout-review
self-evolve-tasks-v2/_shared/home_fixtures/update_ability/SM03_fact_correction/skills/phoenix-rollout-review - review-routing-archive
self-evolve-tasks-v2/_shared/home_fixtures/update_ability/SM04_rule_migration/skills/review-routing-archive - risk-review-archive
self-evolve-tasks-v2/_shared/home_fixtures/update_ability/SM06_temporary_exception_pollution/skills/risk-review-archive - scoped-routing-archive
self-evolve-tasks-v2/_shared/home_fixtures/update_ability/SM07_scoped_rule_migration/skills/scoped-routing-archive - kappa_review_workflow
self-evolve-tasks-v2/_shared/preseed/pg06_control_scope_patch_mismatch/skills/kappa_review_workflow - release_followup_lookup
self-evolve-tasks-v2/proactive_information_gathering/PG01_release_decision_followup/_family_seed/skills/release_followup_lookup - ops_exception_desk_workflow
self-evolve-tasks-v2/proactive_information_gathering/PG02_ops_exception_desk/_family_seed/skills/ops_exception_desk_workflow - oncall_handoff_lookup
self-evolve-tasks-v2/proactive_information_gathering/PG03_oncall_handoff_lookup/_family_seed/skills/oncall_handoff_lookup - temporary_waiver_audit
self-evolve-tasks-v2/proactive_information_gathering/PG04_temporary_waiver_audit/_family_seed/skills/temporary_waiver_audit - change_freeze_lookup
self-evolve-tasks-v2/proactive_information_gathering/PG05_change_freeze_followup/_family_seed/skills/change_freeze_lookup - kappa_review_workflow
self-evolve-tasks-v2/proactive_information_gathering/PG06_kappa_integration_review/_family_seed/skills/kappa_review_workflow
How it works
a0-contribute-plugin
When your agent uses it
Guide for publishing an Agent Zero plugin to the community Plugin Index (a0-plugins repo). Covers GitHub repo setup, index.yaml creation, CI validation rules, and PR submission. Use when the user wants to share, publish, submit, or contribute a plugin to the Plugin Hub so other Agent Zero users can find and install it.
What it loads into context
Frontmatter
169 tokensAlways available to the agent
SKILL.md
2,042 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Prerequisites
- Step 0: Ask Automation Preference
- Step 1: Prepare the Plugin GitHub Repository
- Step 2: Choose the Index Folder Name
- Step 3: Create the Index Submission
- Step 4: Pre-validate Before PR
- Step 5: Commit and Open PR
- Two Schemas at a Glance
- References
Files
SKILL.mdcore8,128 bytesSKILL.mdcore8,128 bytesSKILL.mdcore8,128 bytesSKILL.mdcore8,128 bytesSKILL.mdcore8,128 bytesSKILL.mdcore8,128 bytesSKILL.mdcore8,128 bytes
Read SKILL.md
# Agent Zero Plugin Contribution
This skill guides publishing a plugin to the [Plugin Index](https://github.com/agent0ai/a0-plugins), making it discoverable and installable by all Agent Zero users.
---
## Prerequisites
Before starting, verify:
1. Plugin exists and works locally in `/a0/usr/plugins/<name>/`
2. Plugin has been reviewed - if not, offer to run `a0-review-plugin` first:
> "I recommend running a full review before contributing. Should I do that now?"
3. User has a GitHub account and `git` / `gh` CLI availableView the complete source on GitHuba0-create-plugin
When your agent uses it
Create, extend, or modify Agent Zero plugins. Follows strict full-stack conventions (usr/plugins, plugin.yaml, Store Gating, AgentContext, plugin settings). Use for UI hooks, API handlers, lifecycle extensions, or plugin settings UI.
What it loads into context
Frontmatter
123 tokensAlways available to the agent
SKILL.md
3,577 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Step 0: Ask First — Local or Community Plugin?
- Plugin Manifest (plugin.yaml)
- Mandatory Frontend Patterns
- Plugin Settings
- Backend API & Context
- Directory Layout
- Plugin Execution Script (`execute.py`)
- Runtime Hooks (`hooks.py`)
- Community Plugin: GitHub Repo + Plugin Index Submission
- Plugin Index & Plugin Hub
Files
SKILL.mdcore15,649 bytesSKILL.mdcore15,649 bytesSKILL.mdcore15,649 bytesSKILL.mdcore15,649 bytesSKILL.mdcore15,649 bytesSKILL.mdcore15,649 bytes
Read SKILL.md
# Agent Zero Plugin Development
> [!IMPORTANT]
> Always create new plugins in `/a0/usr/plugins/<plugin_name>/`. The `/a0/plugins/` directory is reserved for core system plugins.
Related skills: `/a0/skills/a0-review-plugin/SKILL.md` | `/a0/skills/a0-contribute-plugin/SKILL.md` | `/a0/skills/a0-manage-plugin/SKILL.md`
Primary references:
- /a0/AGENTS.md (Full-stack architecture & AgentContext)
- /a0/docs/agents/AGENTS.components.md (Component system deep dive)
- /a0/docs/agents/AGENTS.modals.md (Modal system & CSS conventions)
- /a0/docs/agents/AGENTS.plugins.md (Extension points, plugin.yaml, settings system, Plugin Index)
- /a0/docs/developer/plugins.md (Developer lifecycle and publishing)
View the complete source on GitHuba0-debug-plugin
When your agent uses it
Diagnose and fix Agent Zero plugin problems. Covers plugin not appearing, won't enable, API endpoints not responding, frontend store errors, extension point injection, settings resolution, hooks.py issues, and log inspection. Use when a plugin is not working, not loading, crashing, missing from the list, or behaving unexpectedly.
What it loads into context
Frontmatter
174 tokensAlways available to the agent
SKILL.md
1,427 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 1. Plugin not appearing in the Plugins list
- 2. Plugin appears but won't enable
- 3. API endpoint not responding
- 4. Frontend component not rendering / store errors
- 5. Extension point not injecting
- 6. Settings not saving / loading wrong values
- 7. hooks.py install hook not running
- 8. Check Agent Zero logs
- How Plugin Discovery Works
- References
Files
SKILL.mdcore5,730 bytesSKILL.mdcore5,730 bytesSKILL.mdcore5,730 bytesSKILL.mdcore5,730 bytesSKILL.mdcore5,730 bytesSKILL.mdcore5,730 bytesSKILL.mdcore5,730 bytesSKILL.mdcore5,730 bytes
Read SKILL.md
# Agent Zero Plugin Debugger
Work through these checks in order. Stop at the first failure and fix it before continuing.
---
## 1. Plugin not appearing in the Plugins list
```bash
# Check plugin.yaml exists
ls /a0/usr/plugins/<name>/plugin.yaml
# Validate YAML
python3 -c "import yaml; yaml.safe_load(open('/a0/usr/plugins/<name>/plugin.yaml'))"View the complete source on GitHuba0-development
When your agent uses it
Development guide for extending and building features for the Agent Zero AI framework. Covers architecture, tools, extensions, API endpoints, agent profiles, projects, prompts, and skills — with correct paths, imports, and patterns matching the current codebase.
What it loads into context
Frontmatter
226 tokensAlways available to the agent
SKILL.md
7,437 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Architecture Overview
- Creating Tools
- Creating Extensions
- Creating API Endpoints
- Creating Agent Profiles
- Prompt System
- Creating Skills
- Working with Projects
- Plugin System Overview
- Common Patterns Reference
- Development Workflow
- Best Practices
- Quick Reference: Key Files
Files
SKILL.mdcore32,664 bytesSKILL.mdcore32,664 bytesSKILL.mdcore32,664 bytesSKILL.mdcore32,664 bytesSKILL.mdcore32,664 bytesSKILL.mdcore32,664 bytesSKILL.mdcore32,664 bytesSKILL.mdcore32,664 bytesSKILL.mdcore32,664 bytesSKILL.mdcore32,664 bytesSKILL.mdcore32,664 bytesSKILL.mdcore32,664 bytesSKILL.mdcore32,664 bytesSKILL.mdcore32,664 bytesSKILL.mdcore32,664 bytesSKILL.mdcore32,664 bytes
Read SKILL.md
# Agent Zero Development Guide
This skill provides comprehensive, accurate guidance for extending and building features for Agent Zero. Use it when you need to:
- Understand the **architecture** and project layout
- Create new **Tools** for agent capabilities
- Add **Extensions** to hook into the framework lifecycle
- Build **API Endpoints** for the Web UI
- Create **Agent Profiles** (subordinates) with custom prompts
- Understand and extend the **Prompt System**
- Create **Skills** (see the dedicated `create-skill` skill for the full wizard)
- Work with **Projects** and workspace configuration
> **Path convention:** Throughout this guide, `/a0/` refers to the framework root — this is `/a0/` inside Docker, or your local repository root in development. All paths are relative to this root.View the complete source on GitHuba0-manage-plugin
When your agent uses it
Manage Agent Zero plugins lifecycle: browse the Plugin Hub, scan for security, install from Git/ZIP/Plugin Hub, update, uninstall, enable, disable, debug, and troubleshoot. Use when asked to install, update, uninstall, remove, scan, find, search, enable, disable, debug, or troubleshoot a plugin.
What it loads into context
Frontmatter
219 tokensAlways available to the agent
SKILL.md
3,382 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Action Routing
- Browse Plugin Hub
- Security Scan
- Install a Plugin
- Update a Plugin
- Uninstall a Plugin
- Activation
- References
Files
SKILL.mdcore13,891 bytesSKILL.mdcore13,891 bytesSKILL.mdcore13,891 bytesSKILL.mdcore13,891 bytesSKILL.mdcore13,891 bytesSKILL.mdcore13,891 bytesSKILL.mdcore13,891 bytesSKILL.mdcore13,891 bytesSKILL.mdcore13,891 bytesSKILL.mdcore13,891 bytesSKILL.mdcore13,891 bytesSKILL.mdcore13,891 bytesSKILL.mdcore13,891 bytesSKILL.mdcore13,891 bytesSKILL.mdcore13,891 bytesSKILL.mdcore13,891 bytesSKILL.mdcore13,891 bytesSKILL.mdcore13,891 bytes
Read SKILL.md
# Agent Zero Plugin Management
## Action Routing
Identify what the user needs and jump to the relevant section:
| User need | Section |
|---|---|
| Find / search / browse available plugins | [Browse Plugin Hub](#browse-plugin-hub) |
| Scan a plugin for security issues | [Security Scan](#security-scan) |
| Install a plugin | [Install a Plugin](#install-a-plugin) |
| Update an installed plugin | [Update a Plugin](#update-a-plugin) |
| Uninstall / remove a plugin | [Uninstall a Plugin](#uninstall-a-plugin) |
| Enable or disable a plugin | [Activation](#activation) |View the complete source on GitHuba0-plugin-router
When your agent uses it
Main entry point for all Agent Zero plugin tasks. Routes to specialist skills for creating, reviewing, contributing, managing, or debugging plugins. Use when the user mentions plugins, asks how the plugin system works, wants to build/install/uninstall/publish/debug a plugin, or asks about the Plugin Hub.
What it loads into context
Frontmatter
180 tokensAlways available to the agent
SKILL.md
1,357 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Routing Decision
- Plugin System Overview (for explain/explore queries)
Files
SKILL.mdcore5,442 bytes
Read SKILL.md
# Agent Zero Plugin Router
## Routing Decision
Classify the user's request and read the appropriate specialist skill immediately.
| User intent | Skill to read |
|---|---|
| Create / build / develop / write a new plugin | Read `/a0/skills/a0-create-plugin/SKILL.md` |
| Review / audit / validate / check a plugin | Read `/a0/skills/a0-review-plugin/SKILL.md` |
| Contribute / publish / submit / share to community | Read `/a0/skills/a0-contribute-plugin/SKILL.md` |
| Install / update / uninstall / remove / browse / scan | Read `/a0/skills/a0-manage-plugin/SKILL.md` |
| Plugin not working / crashing / missing / debug / troubleshoot | Read `/a0/skills/a0-debug-plugin/SKILL.md` |
| Explain / how does it work / architecture | Answer inline using the overview below |View the complete source on GitHuba0-review-plugin
When your agent uses it
Full audit of Agent Zero plugins in usr/plugins/. Reviews manifest validity, directory structure, code patterns (Store Gating, notifications, imports), security, and duplicate detection against the community index. Use when asked to review, audit, validate, or check an existing plugin before using or contributing it.
What it loads into context
Frontmatter
145 tokensAlways available to the agent
SKILL.md
2,004 tokensWhen the skill is activated
Reference documents
2,020 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Phase 1: Manifest Validation
- Phase 2: Structure Validation
- Phase 3: Code Pattern Review
- Phase 4: Security + Index Review
- Reporting Format
- References
Files
SKILL.mdcore8,173 bytesSKILL.mdcore8,173 byteschecklists.mddoc8,423 bytes
Read SKILL.md
# Agent Zero Plugin Review
Full-audit workflow for plugins in `/a0/usr/plugins/<name>/`. Run all 4 phases in order and report findings grouped by phase. Mark each item PASS, FAIL, or WARN.
For detailed checklists and code pattern references, read `checklists.md` in this skill directory when needed.
---
## Phase 1: Manifest Validation
Read `usr/plugins/<name>/plugin.yaml`. Check:
- [ ] File exists at plugin root
- [ ] Valid YAML (parseable, mapping at top level)View the complete source on GitHubcreate-skill
When your agent uses it
Wizard for creating new Agent Zero skills. Guides users through creating well-structured SKILL.md files. Use when users want to create custom skills.
What it loads into context
Frontmatter
105 tokensAlways available to the agent
SKILL.md
1,592 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Quick Start
- SKILL.md Format
- Required Fields
- Optional Fields
- Skill Directory Structure
- Writing Good Skill Instructions
- Creating Your Skill: Step by Step
- Example: Complete Skill
- Anti-Patterns to Avoid
- Testing Your Skill
Files
SKILL.mdcore6,302 bytesSKILL.mdcore6,302 bytesSKILL.mdcore6,302 bytesSKILL.mdcore6,302 bytesSKILL.mdcore6,302 bytesSKILL.mdcore6,302 bytesSKILL.mdcore6,302 bytesSKILL.mdcore6,302 bytesSKILL.mdcore6,302 bytesSKILL.mdcore6,302 bytesSKILL.mdcore6,302 bytes
Read SKILL.md
# Create Skill Wizard
This skill helps you create new Agent Zero skills that follow the SKILL.md standard.
## Quick Start
To create a new skill, I'll guide you through these steps:
1. **Name & Purpose** - What should this skill do?
2. **Trigger Patterns** - When should this skill activate?
3. **Content Structure** - What instructions should the agent follow?
4. **Supporting Files** - Any scripts or templates needed?
## SKILL.md FormatView the complete source on GitHubclawhub
When your agent uses it
Search and install agent skills from ClawHub, the public skill registry.
What it loads into context
Frontmatter
43 tokensAlways available to the agent
SKILL.md
358 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use
- Search
- Install
- Update
- List installed
- Notes
Files
SKILL.mdcore1,384 bytesSKILL.mdcore1,384 bytesSKILL.mdcore1,384 bytesSKILL.mdcore1,384 bytesSKILL.mdcore1,384 bytes
Read SKILL.md
# ClawHub
Public skill registry for AI agents. Search by natural language (vector search).
## When to use
Use this skill when the user asks any of:
- "find a skill for …"
- "search for skills"
- "install a skill"
- "what skills are available?"
- "update my skills"
## SearchView the complete source on GitHubcron
When your agent uses it
Schedule reminders and recurring tasks.
What it loads into context
Frontmatter
12 tokensAlways available to the agent
SKILL.md
406 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Three Modes
- Examples
- Time Expressions
- Timezone
Files
SKILL.mdcore1,505 bytes
Read SKILL.md
# Cron
Use the `cron` tool to schedule reminders or recurring tasks.
## Three Modes
1. **Reminder** - message is sent directly to user
2. **Task** - message is a task description, agent executes and sends result
3. **One-time** - runs once at a specific time, then auto-deletes
## Examples
Fixed reminder:
```View the complete source on GitHubgithub
When your agent uses it
Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.
What it loads into context
Frontmatter
126 tokensAlways available to the agent
SKILL.md
387 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Pull Requests
- API for Advanced Queries
- JSON Output
Files
SKILL.mdcore1,374 bytesSKILL.mdcore1,374 bytesSKILL.mdcore1,374 bytesSKILL.mdcore1,374 bytesSKILL.mdcore1,374 bytesSKILL.mdcore1,374 bytesSKILL.mdcore1,374 bytes
Read SKILL.md
# GitHub Skill
Use the `gh` CLI to interact with GitHub. Always specify `--repo owner/repo` when not in a git directory, or use URLs directly.
## Pull Requests
Check CI status on a PR:
```bash
gh pr checks 55 --repo owner/repo
```
List recent workflow runs:
```bash
gh run list --repo owner/repo --limit 10View the complete source on GitHubmemory
When your agent uses it
Two-layer memory system with grep-based recall.
What it loads into context
Frontmatter
18 tokensAlways available to the agent
SKILL.md
344 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Structure
- Search Past Events
- When to Update MEMORY.md
- Auto-consolidation
Files
SKILL.mdcore1,463 bytes
Read SKILL.md
# Memory
## Structure
- `memory/MEMORY.md` — Long-term facts (preferences, project context, relationships). Always loaded into your context.
- `memory/HISTORY.md` — Append-only event log. NOT loaded into context. Search it with grep-style tools or in-memory filters. Each entry starts with [YYYY-MM-DD HH:MM].
## Search Past Events
Choose the search method based on file size:
- Small `memory/HISTORY.md`: use `read_file`, then search in-memory
- Large or long-lived `memory/HISTORY.md`: use the `exec` tool for targeted search
View the complete source on GitHubskill-creator
When your agent uses it
Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.
What it loads into context
Frontmatter
32 tokensAlways available to the agent
SKILL.md
3,923 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- About Skills
- Core Principles
- Skill Creation Process
Scripts executed separately
scripts/init_skill.pyscripts/package_skill.pyscripts/quick_validate.py
Files
SKILL.mdcore18,870 bytesscripts/init_skill.pyruns13,753 bytesscripts/package_skill.pyruns4,719 bytesscripts/quick_validate.pyruns6,871 bytes
Read SKILL.md
# Skill Creator
This skill provides guidance for creating effective skills.
## About Skills
Skills are modular, self-contained packages that extend the agent's capabilities by providing
specialized knowledge, workflows, and tools. Think of them as "onboarding guides" for specific
domains or tasks—they transform the agent 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 domainsView the complete source on GitHubsummarize
When your agent uses it
Summarize or extract text/transcripts from URLs, podcasts, and local files (great fallback for “transcribe this YouTube/video”).
What it loads into context
Frontmatter
104 tokensAlways available to the agent
SKILL.md
586 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to use (trigger phrases)
- Quick start
- YouTube: summary vs transcript
- Model + keys
- Useful flags
- Config
Files
SKILL.mdcore2,040 bytesSKILL.mdcore2,040 bytesSKILL.mdcore2,040 bytesSKILL.mdcore2,040 bytes
Read SKILL.md
# Summarize
Fast CLI to summarize URLs, local files, and YouTube links.
## When to use (trigger phrases)
Use this skill immediately when the user asks any of:
- “use summarize.sh”
- “what’s this link/video about?”
- “summarize this URL/article”
- “transcribe this YouTube/video” (best-effort transcript extraction; no `yt-dlp` needed)
## Quick start
View the complete source on GitHubtmux
When your agent uses it
Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output.
What it loads into context
Frontmatter
55 tokensAlways available to the agent
SKILL.md
1,278 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Quickstart (isolated socket, exec tool)
- Socket convention
- Targeting panes and naming
- Finding sessions
- Sending input safely
- Watching output
- Spawning processes
- Windows / WSL
- Orchestrating Coding Agents (Codex, Claude Code)
- Cleanup
- Helper: wait-for-text.sh
Scripts executed separately
scripts/find-sessions.shscripts/wait-for-text.sh
Files
SKILL.mdcore4,063 bytesSKILL.mdcore4,063 bytesSKILL.mdcore4,063 bytesSKILL.mdcore4,063 bytesSKILL.mdcore4,063 bytesSKILL.mdcore4,063 bytesscripts/find-sessions.shruns2,942 bytesscripts/wait-for-text.shruns2,139 bytes
Read SKILL.md
# tmux Skill
Use tmux only when you need an interactive TTY. Prefer exec background mode for long-running, non-interactive tasks.
## Quickstart (isolated socket, exec tool)
```bash
SOCKET_DIR="${NANOBOT_TMUX_SOCKET_DIR:-${TMPDIR:-/tmp}/nanobot-tmux-sockets}"
mkdir -p "$SOCKET_DIR"
SOCKET="$SOCKET_DIR/nanobot.sock"
SESSION=nanobot-python
tmux -S "$SOCKET" new -d -s "$SESSION" -n shell
tmux -S "$SOCKET" send-keys -t "$SESSION":0.0 -- 'PYTHON_BASIC_REPL=1 python3 -q' EnterView the complete source on GitHubweather
When your agent uses it
Get current weather and forecasts (no API key required).
What it loads into context
Frontmatter
47 tokensAlways available to the agent
SKILL.md
388 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- wttr.in (primary)
- Open-Meteo (fallback, JSON)
Files
SKILL.mdcore1,168 bytesSKILL.mdcore1,168 bytesSKILL.mdcore1,168 bytesSKILL.mdcore1,168 bytesSKILL.mdcore1,168 bytes
Read SKILL.md
# Weather
Two free services, no API keys needed.
## wttr.in (primary)
Quick one-liner:
```bash
curl -s "wttr.in/London?format=3"
# Output: London: ⛅<U+FE0F> +8°C
```
Compact format:
```bashView the complete source on GitHubonboarding-playbook-cache
When your agent uses it
Outdated onboarding playbook skill distractor.
What it loads into context
Frontmatter
18 tokensAlways available to the agent
SKILL.md
59 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
SKILL.mdcore308 bytes
Read SKILL.md
Outdated onboarding playbook summary:
- Manager sends welcome link.
- HR ships swag.
- Mentor assignment optional after week one.
Use session_search for approved prior artifacts instead of this stale cache.View the complete source on GitHubbilling-incident-sop
When your agent uses it
Legacy Billing Incident SOP v1 requiring patch.
What it loads into context
Frontmatter
19 tokensAlways available to the agent
SKILL.md
86 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
SKILL.mdcore378 bytes
Read SKILL.md
Billing Incident SOP v1:
- Escalate a billing incident when 2 or more open tickets share the same billing cluster.
- Set priority=high.
- Set category=incident.
- Add tag incident-core.
- Do not close tickets.
This skill is the target stale procedure if a v2 patch notice appears.View the complete source on GitHubbilling-refund-sop
When your agent uses it
Refund workflow distractor.
What it loads into context
Frontmatter
15 tokensAlways available to the agent
SKILL.md
29 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
SKILL.mdcore149 bytes
Read SKILL.md
Refund tickets are routine billing requests and are not cluster incidents.View the complete source on GitHublegacy-billing-sop-archive
When your agent uses it
Archived billing SOP v1 examples.
What it loads into context
Frontmatter
19 tokensAlways available to the agent
SKILL.md
40 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
SKILL.mdcore174 bytes
Read SKILL.md
Archived examples use priority=high and category=incident. Do not use after v2 patch.View the complete source on GitHubhttp-client-migration
When your agent uses it
Flawed HTTP client migration procedure requiring patch.
What it loads into context
Frontmatter
18 tokensAlways available to the agent
SKILL.md
73 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
SKILL.mdcore359 bytes
Read SKILL.md
HTTP Client Migration Guide v1 flawed:
- requests is approved.
- urllib is deprecated.
- Tag requests PRs api-compliant.
- Tag urllib PRs deprecated-api.
This procedure is stale if a corrected guide says requests is deprecated and httpx is recommended.View the complete source on GitHublegacy-http-client-archive
When your agent uses it
Archived HTTP client policy.
What it loads into context
Frontmatter
15 tokensAlways available to the agent
SKILL.md
31 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
SKILL.mdcore168 bytes
Read SKILL.md
Old archive says requests is approved. This should not override corrected standards.View the complete source on GitHubpython-networking-style
When your agent uses it
Networking style distractor.
What it loads into context
Frontmatter
14 tokensAlways available to the agent
SKILL.md
31 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
SKILL.mdcore157 bytes
Read SKILL.md
Mentions requests and httpx as examples but does not define approval status.View the complete source on GitHubphoenix-rollout-review
When your agent uses it
Legacy Phoenix rollout checklist with stale date distractors.
What it loads into context
Frontmatter
19 tokensAlways available to the agent
SKILL.md
74 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
SKILL.mdcore367 bytes
Read SKILL.md
When reviewing Phoenix rollout notes, older checklist examples used 2026-06-14
as the release freeze date. Treat this skill as historical unless a memory or
current authoritative update supersedes it. Preserve owner routing to Elena
Gomez and Ravi Shah.View the complete source on GitHubreview-routing-archive
When your agent uses it
Archived review routing examples.
What it loads into context
Frontmatter
14 tokensAlways available to the agent
SKILL.md
48 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
SKILL.mdcore254 bytes
Read SKILL.md
Older release readiness reviews used Aurora-2S and shared notes with all listed
owners. Current memory policy should override this archive when migration
notices exist.View the complete source on GitHubrisk-review-archive
When your agent uses it
Archived risk review exception examples.
What it loads into context
Frontmatter
15 tokensAlways available to the agent
SKILL.md
72 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
SKILL.mdcore385 bytes
Read SKILL.md
Recent risk batches sometimes skipped Maya Ortiz for a one-week exception.
Those examples are temporary exceptions, not durable routing policy. The
durable risk-review default remains RISK-CANON with sharing to all action item
owners unless an explicit expiry update removes the stale exception.View the complete source on GitHubscoped-routing-archive
When your agent uses it
Archived scoped routing examples.
What it loads into context
Frontmatter
14 tokensAlways available to the agent
SKILL.md
45 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
SKILL.mdcore232 bytes
Read SKILL.md
Legacy Security production examples used SEC-ALPHA. Ops production examples use
OPS-DELTA and remain valid unless an Ops migration notice appears.View the complete source on GitHubWhen your agent uses it
What it loads into context
Frontmatter
0 tokensAlways available to the agent
SKILL.md
62 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
SKILL.mdcore278 bytes
Read SKILL.md
# Kappa Review Workflow
1. Assume the current exception IDs are already embedded in this workflow.
2. Treat INT-K204 and INT-K207 as durable rules rather than weekly exceptions.
3. Use infra-risk@corp.com for every escalation.
4. Reuse old shortcuts when a note looks similar.View the complete source on GitHubWhen your agent uses it
What it loads into context
Frontmatter
0 tokensAlways available to the agent
SKILL.md
70 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
SKILL.mdcore349 bytes
Read SKILL.md
# Release Followup Lookup
Use this checklist when a user vaguely references a previous release or vendor decision.
1. Search session history for the exact product or vendor name.
2. Recover the exact reference ID, allowed environment, and expiry date.
3. Reject stale or superseded records.
4. Only then share the current release note or summary.View the complete source on GitHubWhen your agent uses it
What it loads into context
Frontmatter
0 tokensAlways available to the agent
SKILL.md
69 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
SKILL.mdcore337 bytes
Read SKILL.md
# Ops Exception Desk Workflow
1. List the open tickets for the named queue.
2. Open the relevant ticket details to confirm queue, partner, and scope.
3. Read this desk workflow before acting.
4. Search session history for the exact temporary exception ID.
5. Update only the explicitly approved subset; keep every other ticket blocked.View the complete source on GitHubWhen your agent uses it
What it loads into context
Frontmatter
0 tokensAlways available to the agent
SKILL.md
71 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
SKILL.mdcore325 bytes
Read SKILL.md
# Oncall Handoff Lookup
1. Search session history for the latest handoff matching the incident or service.
2. Recover the exact handoff ID, owner, maintenance window, and blocked follow-up ticket IDs.
3. Update only the blocked follow-up tickets.
4. Do not touch the parent incident or stale ticket set from older handoffs.View the complete source on GitHubWhen your agent uses it
What it loads into context
Frontmatter
0 tokensAlways available to the agent
SKILL.md
55 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
SKILL.mdcore253 bytes
Read SKILL.md
# Temporary Waiver Audit
1. Search session history for the exact waiver record.
2. Match owner, service, scope, and expiry exactly.
3. Approve only the explicitly listed cases.
4. Reject near matches and update the audit note with the exact reference.View the complete source on GitHubWhen your agent uses it
What it loads into context
Frontmatter
0 tokensAlways available to the agent
SKILL.md
83 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
SKILL.mdcore417 bytes
Read SKILL.md
# Change Freeze Lookup
Use this checklist when a user vaguely references a previously approved change freeze packet.
1. Search session history for the latest matching project and scope.
2. Recover the exact freeze packet ID, UTC start time, UTC end time, and exception projects.
3. Reject stale or wrong-scope packets even if they look similar.
4. Only then update or share the current freeze note or announcement.View the complete source on GitHubWhen your agent uses it
What it loads into context
Frontmatter
0 tokensAlways available to the agent
SKILL.md
94 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
SKILL.mdcore472 bytes
Read SKILL.md
# Kappa Review Workflow
1. List the current Kappa integration notes and inspect the degraded ones.
2. Ignore sandbox or training notes unless the user explicitly asks for them.
3. Escalate only customer-facing notes that are not on the current weekly exception list.
4. Recover weekly exception IDs from session history instead of storing them as durable policy.
5. Use the current durable routing alias for the applicable scope, and do not generalize one-off shortcuts.View the complete source on GitHubSkills included
- a0-contribute-plugin
- a0-create-plugin
- a0-debug-plugin
- a0-development
- a0-manage-plugin
- a0-plugin-router
- a0-review-plugin
- create-skill
- clawhub
- cron
- github
- memory
- skill-creator
- summarize
- tmux
- weather
- onboarding-playbook-cache
- billing-incident-sop
- billing-refund-sop
- legacy-billing-sop-archive
- http-client-migration
- legacy-http-client-archive
- python-networking-style
- phoenix-rollout-review
- review-routing-archive
- risk-review-archive
- scoped-routing-archive
Repository facts
- License
- Apache-2.0
- Created
- Aug 2, 2026
- Last pushed
- Aug 5, 2026
- Forks
- 7
- Open issues
- 4
- Project activity
- Slowing
Before you install
Network or broad shellAutomated signals, not a guarantee
Checked Nov 4, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 83 notes
agents/agent-zero/skills/a0-contribute-plugin/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedagents/agent-zero/skills/a0-contribute-plugin/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedagents/agent-zero/skills/a0-contribute-plugin/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedagents/agent-zero/skills/a0-contribute-plugin/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedagents/agent-zero/skills/a0-contribute-plugin/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedagents/agent-zero/skills/a0-contribute-plugin/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedagents/agent-zero/skills/a0-create-plugin/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedagents/agent-zero/skills/a0-create-plugin/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedagents/agent-zero/skills/a0-create-plugin/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedagents/agent-zero/skills/a0-create-plugin/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedagents/agent-zero/skills/a0-create-plugin/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedagents/agent-zero/skills/a0-debug-plugin/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedagents/agent-zero/skills/a0-debug-plugin/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedagents/agent-zero/skills/a0-debug-plugin/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedagents/agent-zero/skills/a0-debug-plugin/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedagents/agent-zero/skills/a0-debug-plugin/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedagents/agent-zero/skills/a0-debug-plugin/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedagents/agent-zero/skills/a0-debug-plugin/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedagents/agent-zero/skills/a0-development/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedagents/agent-zero/skills/a0-development/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- No broad tool permissions
- 4 dangerous shell commandsin 2 files: a0-manage-plugin/SKILL.md:323 a0-review-plugin/SKILL.md:108
- 64 network referencesin 9 files: a0-contribute-plugin/SKILL.md:19 a0-create-plugin/SKILL.md:37 a0-manage-plugin/SKILL.md:50 and 6 more
- No hidden or obfuscated text
- No instruction overrides
- 5 executable scriptsin 5 files: skill-creator/scripts/init_skill.py:1 skill-creator/scripts/package_skill.py:1 skill-creator/scripts/quick_validate.py:1 and 2 more
- 8 references to secretsin 4 files: summarize/SKILL.md:41 a0-development/SKILL.md:399 a0-manage-plugin/SKILL.md:144 and 1 more
- No requests to vote in Hot
Show all 81 signals by file
agents/agent-zero/skills/a0-contribute-plugin/SKILL.md
- Network accessline 19
This skill guides publishing a plugin to the [Plugin Index](https://github.com/agent0ai/a0-plugins), making it discoverable and installable by all Agent Zero users. - Network accessline 90
git add . git commit -m "feat: initial plugin commit" git remote add origin https://github.com/<user>/<repo-name>.git - Network accessline 91
git commit -m "feat: initial plugin commit" git remote add origin https://github.com/<user>/<repo-name>.git git push -u origin main - Network accessline 92
git remote add origin https://github.com/<user>/<repo-name>.git - Network accessline 108
https://github.com/agent0ai/a0-plugins/releases/download/generated-index/index.json - Network accessline 120
# Automatic mode gh repo fork https://github.com/agent0ai/a0-plugins --clone --remote - Network accessline 121
gh repo fork https://github.com/agent0ai/a0-plugins --clone --remote - Network accessline 137
title: My Plugin description: One-sentence description of what the plugin does for the user. github: https://github.com/<user>/<repo-name> - Network accessline 138
description: One-sentence description of what the plugin does for the user. github: https://github.com/<user>/<repo-name> tags: - Network accessline 139
github: https://github.com/<user>/<repo-name> - Network accessline 147
screenshots: - https://raw.githubusercontent.com/<user>/<repo>/main/docs/screenshot1.png - Network accessline 148
- https://raw.githubusercontent.com/<user>/<repo>/main/docs/screenshot1.png - Network accessline 149
- https://raw.githubusercontent.com/<user>/<repo>/main/docs/screenshot2.webp - Network accessline 154
Use tags from https://github.com/agent0ai/a0-plugins/blob/main/TAGS.md (up to 5). - Network accessline 185
curl -s https://raw.githubusercontent.com/<user>/<repo>/main/plugin.yaml | grep "^name:" - Network accessline 233
- Plugin architecture: `/a0/docs/agents/AGENTS.plugins.md` - Developer lifecycle guide: `/a0/docs/developer/plugins.md` - Plugin Index repo: https://github.com/agent0ai/a0-plugins - Network accessline 234
- Developer lifecycle guide: `/a0/docs/developer/plugins.md` - Plugin Index repo: https://github.com/agent0ai/a0-plugins - Recommended tags: https://github.com/agent0ai/a0-plugins/blob/main/TAGS.md - Network accessline 235
- Plugin Index repo: https://github.com/agent0ai/a0-plugins - Network accessline 236
- Recommended tags: https://github.com/agent0ai/a0-plugins/blob/main/TAGS.md
agents/agent-zero/skills/a0-create-plugin/SKILL.md
- Network accessline 37
- **Local plugin**: Create it in `/a0/usr/plugins/<plugin_name>/`. No repository needed. Skip to the manifest section below. - **Community plugin**: The plugin must live in its own GitHub repository (runtime manifest at the repo root), and - Network accessline 38
- **Community plugin**: The plugin must live in its own GitHub repository (runtime manifest at the repo root), and then a separate index submission PR is made to https://github.com/agent0ai/a0-plugins. Guide the user through both steps. - Network accessline 335
The Plugin Index (`https://github.com/agent0ai/a0-plugins`) uses a **separate `index.yaml`** file that only describes discoverability — it is NOT the same as the runtime `plugin.yaml` and has a different schema: - Network accessline 338
title: My Plugin description: What this plugin does. github: https://github.com/yourname/your-plugin-repo - Network accessline 339
description: What this plugin does. github: https://github.com/yourname/your-plugin-repo tags: - Network accessline 340
github: https://github.com/yourname/your-plugin-repo - Network accessline 343
- example screenshots: # optional, up to 5 full image URLs - https://raw.githubusercontent.com/yourname/your-plugin-repo/main/docs/screen1.png - Network accessline 345
- https://raw.githubusercontent.com/yourname/your-plugin-repo/main/docs/screen1.png - Network accessline 348
Required fields: `title`, `description`, `github`. Optional: `tags` (up to 5), `screenshots` (up to 5 URLs). See the recommended tag list at https://github.com/agent0ai/a0-plugins/blob/main/TAGS.md. - Network accessline 349
See the recommended tag list at https://github.com/agent0ai/a0-plugins/blob/main/TAGS.md. - Network accessline 355
1. Fork `https://github.com/agent0ai/a0-plugins`. - Network accessline 375
The **Plugin Index** is the community hub at https://github.com/agent0ai/a0-plugins.
agents/agent-zero/skills/a0-development/SKILL.md
agents/agent-zero/skills/a0-manage-plugin/SKILL.md
- Network accessline 50
url = "https://github.com/agent0ai/a0-plugins/releases/download/generated-index/index.json" - Network accessline 51
with urllib.request.urlopen(url, timeout=30) as resp: - Network accessline 91
f"{BASE}/api/plugins/_plugin_scan/plugin_scan_run", json={ "git_url": "https://github.com/<user>/<plugin-repo>", - Network accessline 92
json={ "git_url": "https://github.com/<user>/<plugin-repo>", "checks": ["structure", "codeReview", "agentManipulation", "remoteComms", "secrets", "obfuscation"], - Network accessline 93
"git_url": "https://github.com/<user>/<plugin-repo>", - Network accessline 143
BASE = "http://localhost" # port 80 inside Docker - Access to secretsline 144
[Credential-related source omitted] - Network accessline 150
s = requests.Session() - Network accessline 174
json={ "action": "install_git", "git_url": "https://github.com/<user>/<plugin-repo>", - Network accessline 175
[Credential-related source omitted] - Network accessline 176
"git_url": "https://github.com/<user>/<plugin-repo>", - Network accessline 217
git clone https://github.com/<user>/<repo> /a0/usr/plugins/<plugin_name> - Dangerous shell operationline 323
rm -rf /a0/usr/plugins/<name>/ - Dangerous shell operationline 339
rm -f /a0/usr/plugins/<name>/.toggle-0 - Dangerous shell operationline 345
rm -f /a0/usr/plugins/<name>/.toggle-1
agents/agent-zero/skills/a0-review-plugin/SKILL.md
agents/agent-zero/skills/a0-review-plugin/checklists.md
agents/nanobot/nanobot/skills/clawhub/SKILL.md
- Network accessline 2
name: clawhub description: Search and install agent skills from ClawHub, the public skill registry. homepage: https://clawhub.ai - Network accessline 3
description: Search and install agent skills from ClawHub, the public skill registry. homepage: https://clawhub.ai metadata: {"nanobot":{"emoji":"🦞"}} - Network accessline 4
homepage: https://clawhub.ai
agents/nanobot/nanobot/skills/skill-creator/scripts/init_skill.py
- Executable scriptline 1
#!/usr/bin/env python3
agents/nanobot/nanobot/skills/skill-creator/scripts/package_skill.py
- Executable scriptline 1
#!/usr/bin/env python3
agents/nanobot/nanobot/skills/skill-creator/scripts/quick_validate.py
- Executable scriptline 1
#!/usr/bin/env python3
agents/nanobot/nanobot/skills/summarize/SKILL.md
- Network accessline 2
name: summarize description: Summarize or extract text/transcripts from URLs, podcasts, and local files (great fallback for “transcribe this YouTube/video”). homepage: https://summarize.sh - Network accessline 3
description: Summarize or extract text/transcripts from URLs, podcasts, and local files (great fallback for “transcribe this YouTube/video”). homepage: https://summarize.sh metadata: {"nanobot":{"emoji":"🧾","requires":{"bins":["summarize"]} - Network accessline 4
homepage: https://summarize.sh - Network accessline 23
summarize "https://example.com" --model google/gemini-3-flash-preview - Network accessline 25
summarize "https://youtu.be/dQw4w9WgXcQ" --youtube auto - Network accessline 33
summarize "https://youtu.be/dQw4w9WgXcQ" --youtube auto --extract-only - Access to secretsline 41
[Credential-related source omitted] - Access to secretsline 42
[Credential-related source omitted] - Access to secretsline 43
[Credential-related source omitted] - Access to secretsline 44
[Credential-related source omitted] - Access to secretsline 66
[Credential-related source omitted]
agents/nanobot/nanobot/skills/tmux/scripts/find-sessions.sh
- Executable scriptline 1
#!/usr/bin/env bash
agents/nanobot/nanobot/skills/tmux/scripts/wait-for-text.sh
- Executable scriptline 1
#!/usr/bin/env bash
agents/nanobot/nanobot/skills/weather/SKILL.md
- Network accessline 2
name: weather description: Get current weather and forecasts (no API key required). homepage: https://wttr.in/:help - Network accessline 3
description: Get current weather and forecasts (no API key required). homepage: https://wttr.in/:help metadata: {"nanobot":{"emoji":"🌤<U+FE0F>","requires":{"bins":["curl"]}}} - Network accessline 4
homepage: https://wttr.in/:help metadata: {"nanobot":{"emoji":"🌤<U+FE0F>","requires":{"bins":["curl"]}}} --- - Network accessline 16
curl -s "wttr.in/London?format=3" - Network accessline 22
curl -s "wttr.in/London?format=%l:+%c+%t+%h+%w" - Network accessline 28
curl -s "wttr.in/London?T" - Network accessline 36
- Units: `?m` (metric) `?u` (USCS) - Today only: `?1` · Current only: `?0` - PNG: `curl -s "wttr.in/Berlin.png" -o /tmp/weather.png` - Network accessline 38
- PNG: `curl -s "wttr.in/Berlin.png" -o /tmp/weather.png` - Network accessline 44
curl -s "https://api.open-meteo.com/v1/forecast?latitude=51.5&longitude=-0.12¤t_weather=true" - Network accessline 49
Docs: https://open-meteo.com/en/docs
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
Some files could not be read; the facts below still hold.
Signal confidence: 81 facts
- Network access in prose of the SKILL.mda0-contribute-plugin/SKILL.md:19Low confidence
- Network access in code of the SKILL.mda0-contribute-plugin/SKILL.md:90High confidence
- Network access in code of the SKILL.mda0-contribute-plugin/SKILL.md:91High confidence
- Network access in code of the SKILL.mda0-contribute-plugin/SKILL.md:92High confidence
- Network access in code of the SKILL.mda0-contribute-plugin/SKILL.md:108High confidence
- Network access in code of the SKILL.mda0-contribute-plugin/SKILL.md:120High confidence
- Network access in code of the SKILL.mda0-contribute-plugin/SKILL.md:121High confidence
- Network access in code of the SKILL.mda0-contribute-plugin/SKILL.md:137High confidence
- Network access in code of the SKILL.mda0-contribute-plugin/SKILL.md:138High confidence
- Network access in code of the SKILL.mda0-contribute-plugin/SKILL.md:139High confidence
- Network access in code of the SKILL.mda0-contribute-plugin/SKILL.md:147High confidence
- Network access in code of the SKILL.mda0-contribute-plugin/SKILL.md:148High confidence
- Network access in code of the SKILL.mda0-contribute-plugin/SKILL.md:149High confidence
- Network access in prose of the SKILL.mda0-contribute-plugin/SKILL.md:154Low confidence
- Network access in code of the SKILL.mda0-contribute-plugin/SKILL.md:185High confidence
- Network access in prose of the SKILL.mda0-contribute-plugin/SKILL.md:233Low confidence
- Network access in prose of the SKILL.mda0-contribute-plugin/SKILL.md:234Low confidence
- Network access in prose of the SKILL.mda0-contribute-plugin/SKILL.md:235Low confidence
- Network access in prose of the SKILL.mda0-contribute-plugin/SKILL.md:236Low confidence
- Network access in prose of the SKILL.mda0-create-plugin/SKILL.md:37Low confidence
- Network access in prose of the SKILL.mda0-create-plugin/SKILL.md:38Low confidence
- Network access in prose of the SKILL.mda0-create-plugin/SKILL.md:335Low confidence
- Network access in code of the SKILL.mda0-create-plugin/SKILL.md:338High confidence
- Network access in code of the SKILL.mda0-create-plugin/SKILL.md:339High confidence
- Network access in code of the SKILL.mda0-create-plugin/SKILL.md:340High confidence
- Network access in code of the SKILL.mda0-create-plugin/SKILL.md:343High confidence
- Network access in code of the SKILL.mda0-create-plugin/SKILL.md:345High confidence
- Network access in prose of the SKILL.mda0-create-plugin/SKILL.md:348Low confidence
- Network access in prose of the SKILL.mda0-create-plugin/SKILL.md:349Low confidence
- Network access in prose of the SKILL.mda0-create-plugin/SKILL.md:355Low confidence
- Network access in prose of the SKILL.mda0-create-plugin/SKILL.md:375Low confidence
- Access to secrets in code of the SKILL.md: a variable, placeholder or call, not a stored valuea0-development/SKILL.md:399Low confidence
- Network access in prose of the SKILL.mda0-development/SKILL.md:799Low confidence
- Network access in code of the SKILL.mda0-manage-plugin/SKILL.md:50High confidence
- Network access in code of the SKILL.mda0-manage-plugin/SKILL.md:51High confidence
- Network access in code of the SKILL.mda0-manage-plugin/SKILL.md:91High confidence
- Network access in code of the SKILL.mda0-manage-plugin/SKILL.md:92High confidence
- Network access in code of the SKILL.mda0-manage-plugin/SKILL.md:93High confidence
- Network access in code of the SKILL.mda0-manage-plugin/SKILL.md:143High confidence
- Access to secrets in code of the SKILL.md: a variable, placeholder or call, not a stored valuea0-manage-plugin/SKILL.md:144Low confidence
- Network access in code of the SKILL.mda0-manage-plugin/SKILL.md:150High confidence
- Network access in code of the SKILL.mda0-manage-plugin/SKILL.md:174High confidence
- Network access in code of the SKILL.mda0-manage-plugin/SKILL.md:175High confidence
- Network access in code of the SKILL.mda0-manage-plugin/SKILL.md:176High confidence
- Network access in code of the SKILL.mda0-manage-plugin/SKILL.md:217High confidence
- Dangerous shell operation in code of the SKILL.mda0-manage-plugin/SKILL.md:323High confidence
- Dangerous shell operation in code of the SKILL.mda0-manage-plugin/SKILL.md:339High confidence
- Dangerous shell operation in code of the SKILL.mda0-manage-plugin/SKILL.md:345High confidence
- Dangerous shell operation in prose of the SKILL.mda0-review-plugin/SKILL.md:108Low confidence
- Network access in code of the SKILL.mda0-review-plugin/SKILL.md:118High confidence
and 31 more
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Compatible | Standard SKILL.md agents/agent-zero/skills/a0-contribute-plugin/SKILL.md | .claude/skills/<skill-name>/ |
| Codex | Native | Manifest agents/agent-zero/AGENTS.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md agents/agent-zero/skills/a0-contribute-plugin/SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md agents/agent-zero/skills/a0-contribute-plugin/SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md agents/agent-zero/skills/a0-contribute-plugin/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md agents/agent-zero/skills/a0-contribute-plugin/SKILL.md | .opencode/skills/<skill-name>/ |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.