Updated 5d ago
by Hvftpie13
Flashmind_Gemini-3.8-Flash_Smart-agent
flashmind — Gemini 3.8 Flash Smart Agent. Gives Gemini Flash persistent memory (Engram), coding skills, and no-hallucination rules. Works in Gemini CLI, Antigravity, Cursor, VS Code, Claude Code and any MCP client.
39 GitHub stars (39)
+39 in 6 days
| Period | New stars |
|---|---|
| Oct 28 | +3 |
| Oct 29 | +1 |
| Oct 30 | +2 |
| Oct 31 | 0 |
- 4 skills (4 skills found in its SKILL.md files)
- 3 forks (3 forks)
- 5d ago last update (Last updated 5d ago)
Install
Skills CLI
npx skills add Hvftpie13/Flashmind_Gemini-3.8-Flash_Smart-agent
Asks which skills and agents to install. Just one: npx skills add Hvftpie13/Flashmind_Gemini-3.8-Flash_Smart-agent --skill no-invented-code — add -g for every project.
Claude Code
git clone https://github.com/Hvftpie13/Flashmind_Gemini-3.8-Flash_Smart-agentcp -r "Flashmind_Gemini-3.8-Flash_Smart-agent/skills/no-invented-code" ~/.claude/skills/
Copies the no-invented-code skill into ~/.claude/skills/ for every project (use .claude/skills/ for one project). Repeat for the other skills listed below.
Plugin
/plugin marketplace add Hvftpie13/Flashmind_Gemini-3.8-Flash_Smart-agent
Run inside Claude Code if the repository ships a plugin marketplace, then pick plugins from /plugin.
Skills can run code on your machine — read the SKILL.md first.
What it does
In the author's own words, from each skill's SKILL.md.
-
no-invented-code
Use whenever writing or suggesting code that calls a function, file, module, package, CLI flag, config key, environment variable, or API endpoint — especially third-party libraries, SDKs, or framework features. Prevents hallucinated APIs by checking the repo and docs before using anything.
skills/no-invented-code/SKILL.md on GitHub (opens in a new tab) -
plan-first
Use for any coding task with more than about three steps or touching more than one file — new features, refactors, migrations, multi-file changes, or vague requests like "build X" or "add Y to the app". Read the code, write a short plan, then execute step by step with checks.
skills/plan-first/SKILL.md on GitHub (opens in a new tab) -
systematic-debugging
Use when something is broken — an error message, stack trace, failing test, crash, wrong output, "it doesn't work", build failure, or unexpected behavior. Finds the root cause with evidence before changing code, then records the fix in Engram memory.
skills/systematic-debugging/SKILL.md on GitHub (opens in a new tab) -
verify-before-done
Use before claiming any coding task is finished, fixed, working, or passing — after editing code, changing config, adding dependencies, or fixing a bug. Forces running builds/tests/linters and reading the real output instead of assuming success.
skills/verify-before-done/SKILL.md on GitHub (opens in a new tab)
No skill matches that filter.
Review before you install
A skill is a set of instructions and scripts your agent will follow, and it can run code on your machine. Read the SKILL.md and any scripts first — this listing is not a security review.