Not in the top 1,000 by GitHub stars
andrader/jup
jup is a command-line tool for installing and managing agent skills across different ai agents, scopes, and projects.
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
skills/create-gemini-agent/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 2019ba873fb3
No earlier version was observed for comparison.
skills/jup/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 2019ba873fb3
No earlier version was observed for comparison.
skills/jup-architect/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 2019ba873fb3
No earlier version was observed for comparison.
skills/jup-roadmap/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 2019ba873fb3
No earlier version was observed for comparison.
Verified commit 2019ba873fb316d685d09c29bfe30b8c281af8bf
git clone --filter=blob:none --no-checkout https://github.com/andrader/jup.git .hotskills/andrader-jup && git -C .hotskills/andrader-jup checkout --detach 2019ba873fb316d685d09c29bfe30b8c281af8bf
# Copy each selected skill directory from .hotskills/andrader-jup into .agents/skills/<skill-name>/git clone --filter=blob:none --no-checkout https://github.com/andrader/jup.git .hotskills/andrader-jup && git -C .hotskills/andrader-jup checkout --detach 2019ba873fb316d685d09c29bfe30b8c281af8bf
# Copy each selected skill directory from .hotskills/andrader-jup into .gemini/skills/<skill-name>/Heat
1.7- 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
- create-gemini-agent
skills/create-gemini-agent - jup
skills/jup - jup-architect
skills/jup-architect - jup-roadmap
skills/jup-roadmap
How it works
create-gemini-agent
When your agent uses it
Create a custom Gemini agent by defining its system prompt, tools, and configuration in a markdown file.
What it loads into context
Frontmatter
30 tokensAlways available to the agent
SKILL.md
2,726 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
- What are subagents?
- How to use subagents
- Creating custom subagents
- Subagent tool isolation
- Managing subagents
- Remote subagents (Agent2Agent)
- Extension subagents
- Disabling subagents
Files
SKILL.mdcore13,145 bytesSKILL.mdcore13,145 bytesSKILL.mdcore13,145 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubWhen your agent uses it
What it loads into context
Frontmatter
0 tokensAlways available to the agent
SKILL.md
722 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
- Core Concepts
- Usage Instructions
- Agent Specifics
Files
SKILL.mdcore2,682 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubjup-architect
When your agent uses it
Use when analyzing the jup codebase, identifying technical debt, suggesting architectural improvements, or ensuring high engineering standards.
What it loads into context
Frontmatter
32 tokensAlways available to the agent
SKILL.md
715 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
- How to Use This Skill
- Core Architectural Values
- Key Areas of Focus
- Process Flow
- Deliverables
Files
SKILL.mdcore3,181 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubjup-roadmap
When your agent uses it
Use when iterating on the jup roadmap, brainstorming new features, or refining existing ideas into specs.
What it loads into context
Frontmatter
30 tokensAlways available to the agent
SKILL.md
602 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
- How to Use This Skill
- Core Ideation Principles
- Process Flow
- Deliverables
Files
SKILL.mdcore2,541 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubSkills included
- create-gemini-agent
- jup-architect
- jup-roadmap
Repository facts
- License
- No license detected
- Created
- Mar 22, 2026
- Last pushed
- Aug 8, 2026
- Forks
- 3
- Open issues
- 0
- Project activity
- Slowing
Before you install
Instructions onlyAutomated signals, not a guarantee
Checked Nov 6, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 2 notes
skills/create-gemini-agent/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/create-gemini-agent/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- No broad tool permissions
- No dangerous shell commands
- 2 network referencesin 1 file: jup/SKILL.md:16
- No hidden or obfuscated text
- No instruction overrides
- No executable scripts
- No access to secrets
- No requests to vote in Hot
Show all 2 signals by file
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: 2 facts
- Network access in prose of the SKILL.mdjup/SKILL.md:16Low confidence
- Network access in prose of the SKILL.mdjup/SKILL.md:17Low confidence
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Compatible | Standard SKILL.md skills/create-gemini-agent/SKILL.md | .claude/skills/<skill-name>/ |
| Codex | Native | Manifest AGENTS.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md skills/create-gemini-agent/SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Native | Path .gemini/agents/advocate-con.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md skills/create-gemini-agent/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md skills/create-gemini-agent/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.
