SkillAgentSearch skills...

si

One shared brain for your whole AI fleet: attested memory, orchestration, governance and evals across Claude Code, Codex, Cursor, Gemini, Antigravity.

Install / Use

npx skills add frankxai/Starlight-Intelligence-System

Installs into whichever agent you are using.

About this skill
⚡

Claude Commands

Claude Code slash commands

Quality Score

48/100

Supported Platforms

Claude Code
Cursor
Gemini CLI
OpenAI Codex

Our assessment of si

si scores 48/100 on our quality scale, 319th of 328 Customer Support skills we index.

Its Claude Commands is 831 bytes long, lightly structured (1 heading) and no code examples: fairly brief, so expect to fill in details yourself.

It has no GitHub stars yet, so there is no community track record; judge it on its content.

Substance
14/30
Structure
5/20
Description
15/15
Adoption
0/20
Freshness
15/15

Maintenance, license and trust

  • The repository was last updated 2 days ago, so si is actively maintained.
  • Our last check on 2026-09-27 found the source still online.
  • No license is declared. By default that means all rights are reserved: you can read it, but reusing or redistributing it is not clearly permitted. Ask the author before building on it commercially.
  • Its trust signals score 80/100, with 2 cautions from licensing, adoption, age or documentation. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.

Safety scan

No issues found

Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful.

AI review by kimi-k2.7-code on 2026-09-24. Automated pattern scan on 2026-09-24. It catches known dangerous patterns, not every risk — read a skill before letting an agent act on it.

si compared with similar skills

All 4 of these similar skills score higher than si; compare them before choosing.

SkillScoreStarsUpdatedFormat
si (this skill)by frankxai4802d agoClaude Commands
Agent-Reachby Panniantong100106.4k5d agoCLAUDE.md
taste-skillby Leonxlnx100105.7ktodayCLAUDE.md
claude-memby thedotmack100105.0ktodayCLAUDE.md
Understand-Anythingby Egonex-AI10088.9k4d agoCLAUDE.md

Frequently asked questions

How do I install si?
Run npx skills add frankxai/Starlight-Intelligence-System. The install tabs above show the steps for each supported agent.
Which AI agents does si work with?
It is written for Claude Code, Cursor, Gemini CLI and OpenAI Codex, as a Claude Commands file. Other agents that read the same format can often use it too.
Is si safe to use?
Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful. It declares no license and scores 80/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
Is si still maintained?
The repository was last updated 2 days ago, so si is actively maintained.

/si Command

Route operator work to the right local CLI or native generation tool.

Load skills/orchestration/cli-tool-router.md and, when handing work to another agent, skills/orchestration/agent-handoff-packet.md.

Supported lanes: Claude, Codex, Gemini, OpenCode, Cursor, Antigravity, Grok, and native image tools.

Shortcut map:

| Repo | Antigravity | Grok | |---|---|---| | Arcanea | agyarc / agya | grarc | | SIS | agysis | grsis | | FrankX | agyfx | grfx | | GenCreator | agyg | grg | | Vibeclubs | agyvc | grvc | | AnimeLegends | agyani | grani | | DPI | agydpi | grdpi |

If the task asks for image generation or image editing, use the native image tool available in the current surface first.

Output the chosen lane, exact command/tool, task packet if needed, and verification step.

Related Skills

View on GitHub
GitHub Stars0
CategoryCustomer
Updated2d ago
Forks0

Trust signals

80/100

From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.

1 medium1 low