System Prompt Writing Guide
cashew-labs/libretto
Lays out a minimal, iteration-first approach to writing system prompts for LLM agents, with model-specific notes for Claude, GPT, Gemini, and Codex.
Delegate tasks to Gemini CLI as an agent. An agent skill from michaleiatrak-star/Lex-Machina.
$ npx skills add michaleiatrak-star/Lex-Machina --skill gemini-agent -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install michaleiatrak-star/Lex-Machina gemini-agent --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/michaleiatrak-star/Lex-Machina.git skills-src && mkdir -p .claude/skills && cp -r skills-src/tools/claude-dev-config/skills/gemini-agent .claude/skills/gemini-agent && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "gemini-agent" agent skill from https://github.com/michaleiatrak-star/Lex-Machina/tree/main/tools/claude-dev-config/skills/gemini-agent into .claude/skills/gemini-agent/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "gemini-agent", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/michaleiatrak-star/Lex-Machina/tree/main/tools/claude-dev-config/skills/gemini-agentType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add michaleiatrak-star/Lex-Machina --skill gemini-agent -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install michaleiatrak-star/Lex-Machina gemini-agent --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/michaleiatrak-star/Lex-Machina.git skills-src && mkdir -p .agents/skills && cp -r skills-src/tools/claude-dev-config/skills/gemini-agent .agents/skills/gemini-agent && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "gemini-agent" agent skill from https://github.com/michaleiatrak-star/Lex-Machina/tree/main/tools/claude-dev-config/skills/gemini-agent into .agents/skills/gemini-agent/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "gemini-agent", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add michaleiatrak-star/Lex-Machina --skill gemini-agent -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install michaleiatrak-star/Lex-Machina gemini-agent --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/michaleiatrak-star/Lex-Machina.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/tools/claude-dev-config/skills/gemini-agent .cursor/skills/gemini-agent && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "gemini-agent" agent skill from https://github.com/michaleiatrak-star/Lex-Machina/tree/main/tools/claude-dev-config/skills/gemini-agent into .cursor/skills/gemini-agent/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "gemini-agent", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/michaleiatrak-star/Lex-Machina.git --path tools/claude-dev-config/skills/gemini-agent--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add michaleiatrak-star/Lex-Machina --skill gemini-agent -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install michaleiatrak-star/Lex-Machina gemini-agent --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/michaleiatrak-star/Lex-Machina.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/tools/claude-dev-config/skills/gemini-agent .gemini/skills/gemini-agent && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "gemini-agent" agent skill from https://github.com/michaleiatrak-star/Lex-Machina/tree/main/tools/claude-dev-config/skills/gemini-agent into .gemini/skills/gemini-agent/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "gemini-agent", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install michaleiatrak-star/Lex-Machina gemini-agentInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add michaleiatrak-star/Lex-Machina --skill gemini-agent -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/michaleiatrak-star/Lex-Machina.git skills-src && mkdir -p .github/skills && cp -r skills-src/tools/claude-dev-config/skills/gemini-agent .github/skills/gemini-agent && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "gemini-agent" agent skill from https://github.com/michaleiatrak-star/Lex-Machina/tree/main/tools/claude-dev-config/skills/gemini-agent into .github/skills/gemini-agent/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "gemini-agent", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add michaleiatrak-star/Lex-Machina --skill gemini-agent -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install michaleiatrak-star/Lex-Machina gemini-agent --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/michaleiatrak-star/Lex-Machina.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/tools/claude-dev-config/skills/gemini-agent .opencode/skills/gemini-agent && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "gemini-agent" agent skill from https://github.com/michaleiatrak-star/Lex-Machina/tree/main/tools/claude-dev-config/skills/gemini-agent into .opencode/skills/gemini-agent/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "gemini-agent", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
gemini-agentDelegate tasks to Gemini CLI as an agent. An agent skill from michaleiatrak-star/Lex-Machina.
Gemini Agent is an agent skill from michaleiatrak-star/Lex-Machina. Delegate tasks to Gemini CLI as an agent. Use when the user wants to offload token-heavy work to Gemini, get a second opinion from a different model, or run Gemini with a custom system prompt. Triggers include "use Gemini to review X", "ask Gemini to Y", "run Gemini on Z", "delegate to Gemini", "have Gemini check X".
Its SKILL.md is about 630 tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files, including scripts (for example `README.md` and `scripts/gemini_interface.py`).
It sits in AI & LLM Engineering, covering Prompt engineering. It works with Google Gemini. The repository describes itself as: Analityka polskiego prawa, przygotowanie pism procesowych, weryfikacja przepisów prawa polskiego i orzecznictwa z oficjalnych źródeł z zakazem cytowania z pamięci, przygotowanie… The licence is GPL-3.0.
Read from SKILL.md and the folder at commit 8be00e7. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Ships 1 file in scripts/ (Python), which the agent can run.
Shell commands in SKILL.md call:
pythongeminiFrom the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Gemini Agent loads about 626 tokens when it runs. Until then it costs about 83 tokens; SKILL.md has 191 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
The full file from michaleiatrak-star/Lex-Machina at commit 8be00e7, republished under its GPL-3.0 licence (© michaleiatrak-star). 191 words, ~626 tokens.
.claude/skills/gemini-agent/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.Delegates tasks to Gemini CLI in headless mode using gemini_interface.py from this skill's scripts/ folder.
Prerequisite: Gemini CLI must be installed and on PATH (gemini --version should work).
python ~/.claude/skills/gemini-agent/scripts/gemini_interface.py \
--prompt "<task prompt>" \
--cwd "$(pwd)"Pass any markdown file as a persona/role for Gemini. YAML frontmatter is stripped automatically.
python ~/.claude/skills/gemini-agent/scripts/gemini_interface.py \
--prompt "<task prompt>" \
--system-md /path/to/persona.md \
--cwd "$(pwd)"If you need Gemini to read a large existing file, attach it via the --context-file argument (which uses Gemini's @file syntax under the hood):
python ~/.claude/skills/gemini-agent/scripts/gemini_interface.py \
--prompt "Review this file for security vulnerabilities." \
--context-file src/auth/login.py \
--cwd "$(pwd)"Note: For short context or summaries (a few sentences), do not create a temp file. Just include the context directly inside your --prompt string!
| Flag | Default | Description |
|---|---|---|
--prompt | required | Task prompt |
--system-md | none | Markdown file prepended as system instructions |
--context-file | none | File attached via @path in the prompt |
--cwd | current dir | Working directory for Gemini CLI |
--model | gemini-3.1-pro-preview | Gemini model ID |
--verbose | off | Stream all output; default is final response only |
# Launch as a background task so Claude can continue working in parallel
Bash("python ~/.claude/skills/gemini-agent/scripts/gemini_interface.py --prompt '...' --cwd $(pwd)", run_in_background=true)Gemini has no conversation context. Include everything it needs:
© michaleiatrak-star, GPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 2 other files (scripts) in tools/claude-dev-config/skills/gemini-agent of michaleiatrak-star/Lex-Machina.
Open the folder on GitHubat commit 8be00e7
Gemini Agent next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Gemini Agent this skillmichaleiatrak-star/Lex-Machina | 267 | — | ~626 | Automated safety check: Pass | GPL-3.0 | |
| System Prompt Writing Guidecashew-labs/libretto | 904 | — | ~570 | Automated safety check: Pass | MIT | |
| Image Ad Clonekrusemediallc/arcads-claude-code | 1.6k | — | ~2.4k | Automated safety check: Notes | MIT | |
| AI Image Prompts SkillLeoYeAI/openclaw-master-skills | 2.2k | — | ~4.3k | Automated safety check: Pass | MIT | |
| Codebase Managementgiancarloerra/SocratiCode | 3.3k | 1 repos | ~1.8k | Automated safety check: Pass | AGPL-3.0 | |
| Prompt Improverseverity1/claude-code-prompt-improver | 1.9k | 1 repos | ~1.7k | Automated safety check: Pass | MIT |
cashew-labs/libretto
Lays out a minimal, iteration-first approach to writing system prompts for LLM agents, with model-specific notes for Claude, GPT, Gemini, and Codex.
krusemediallc/arcads-claude-code
A skill your agent uses when the user wants to reverse-engineer an existing image ad into a reusable prompt template.
LeoYeAI/openclaw-master-skills
Recommend curated prompts from a 10,000+ real-world image generation prompt library.
giancarloerra/SocratiCode
Set up, index, and manage SocratiCode codebase indexing. An agent skill from giancarloerra/SocratiCode.
severity1/claude-code-prompt-improver
This skill enriches vague prompts with targeted research and clarification before execution.
ynulihao/AgentSkillOS
Master advanced prompt engineering techniques to maximize LLM performance, reliability, and controllability in production.
michaleiatrak-star/Lex-Machina
Safely prune stale git worktrees and local branches left over from past sessions, deleting only those with no unique work so no commit is ever lost.
michaleiatrak-star/Lex-Machina
Analiza, redakcja, negocjacje i generowanie umów oraz dokumentów korporacyjnych, HR i RODO: ryzyka klauzul, B2B/B2C, praca, najem, IT/SaaS, IP, founders, finansowanie i PZP.
michaleiatrak-star/Lex-Machina
Audyt jakości, spójności i bezpieczeństwa systemu prawnych skilli: zależności, wersje, mapy Dz.U., treść merytoryczna, propagacja zmian, deduplikacja i bramki jakości.
michaleiatrak-star/Lex-Machina
Prawo cywilne, rodzinne i gospodarcze: KC, KPC, spadki, rodzina, spółki, upadłość, restrukturyzacja, windykacja i odpowiedzialność kontraktowa/deliktowa.
michaleiatrak-star/Lex-Machina
Prawo konstytucyjne i ustrojowe: Konstytucja, organy państwa, TK, źródła prawa, legislacja i skarga konstytucyjna; analiza z aktualną weryfikacją źródeł.
michaleiatrak-star/Lex-Machina
Prawo administracyjne i sądowoadministracyjne: KPA, PPSA, decyzje, bezczynność, WSA/NSA, egzekucja administracyjna, cudzoziemcy i postępowania urzędowe.
Works with
Categories
Delegate tasks to Gemini CLI as an agent. An agent skill from michaleiatrak-star/Lex-Machina. Gemini Agent is an agent skill from michaleiatrak-star/Lex-Machina. Delegate tasks to Gemini CLI as an agent.
Gemini Agent fits situations like: the user wants to offload token-heavy work to Gemini; get a second opinion from a different model; run Gemini with a custom system prompt; include use Gemini to review X.
Run `npx skills add michaleiatrak-star/Lex-Machina --skill gemini-agent -a claude-code`. Or copy the skill folder (tools/claude-dev-config/skills/gemini-agent in michaleiatrak-star/Lex-Machina) into .claude/skills/gemini-agent in your project. Claude Code loads it when a task matches its description.
Run `npx skills add michaleiatrak-star/Lex-Machina --skill gemini-agent -a codex`. Or copy the skill folder (tools/claude-dev-config/skills/gemini-agent in michaleiatrak-star/Lex-Machina) into .agents/skills/gemini-agent in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add michaleiatrak-star/Lex-Machina --skill gemini-agent -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/gemini-agent, .gemini/skills/gemini-agent, .github/skills/gemini-agent and .opencode/skills/gemini-agent in your project.
Going by SKILL.md and its folder, Gemini Agent needs Python for the scripts in its folder and the command-line tools its instructions call (python and gemini). Our summary lists: Python 3.
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
Gemini Agent is published under the GPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 626 tokens (SKILL.md is roughly 2.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Gemini Agent: System Prompt Writing Guide (cashew-labs/libretto, 904 stars), Image Ad Clone (krusemediallc/arcads-claude-code, 1.6k stars), AI Image Prompts Skill (LeoYeAI/openclaw-master-skills, 2.2k stars) and Codebase Management (giancarloerra/SocratiCode, 3.3k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
michaleiatrak-star (a GitHub user) maintains it in michaleiatrak-star/Lex-Machina, which has 267 GitHub stars. The repository holds 35 skills in this directory. The repository was last updated on October 10, 2026.
Source: michaleiatrak-star/Lex-Machina on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.