modern-cli-tools
- Repo stars 0
- Author updated Live
- Author repo skills-registry
- Domain
- Other
- Compatible agents
-
- Claude Code
- Cursor
- Cline
- Codex
- Windsurf
- Gemini CLI
- +20
- Trust score
- 88 / 100 · community maintained
- Author / version / license
- @tomevault-io · no license declared
- Token usage
- Lean
- Setup complexity
- Guided setup
- External API key
- Not required
- Operating systems
- macOS · Linux · Windows
- Runtime requirements
- Node.js · Python
- Permissions
-
- Read-only
- Shell exec
- Write / modify
- Network behavior
- External requests
- Install commands
- 26 variants
Profile is derived at build time from SKILL.md and install vectors. Subject to drift from author intent.
Heads up: 未限定 allowed-tools，默认拥有全部工具权限。
---
name: modern-cli-tools
description: Use at session start and before running shell commands involving Python, Node.js, file search, o…
category: other
runtime: Node.js / Python
---
# modern-cli-tools output preview
## PART A: Task fit
- Use case: Use at session start and before running shell commands involving Python, Node.js, file search, or HTTP requests. Use when this capability is needed. These commands are prohibited. No exceptions, no fallback. makes outbound network calls; runs on Node.js. Works with Claude Code, Cursor, Cline and 23 more..
- Inputs: target material, constraints, expected output, and acceptance criteria.
- Evidence boundary: follow “NEVER USE These Commands / Modern Replacements / Tool Not Installed?” and do not present inference as author intent.
## PART B: Execution result
- **01** The card summarizes the use case; runtime output centers on “Use at session start and before running shell commands involving Python, Node.js, file search, or HTTP requests. Use when this capability is needed. These commands are prohibited. No exceptions, no fallback. makes outbound network calls; runs on Node.js. Works with Claude Code, Cursor, Cline and 23 more.”.
- **02** When the source has headings, the agent prioritizes “NEVER USE These Commands / Modern Replacements / Tool Not Installed?” so the result follows the author’s structure.
- **03** Typical output includes task judgment, concrete steps, required commands or file edits, validation, and follow-up options.
- **04** Risk context follows the fingerprint: read files, run shell commands, write/modify files; may access external network resources; usually needs no extra API key.
## Running Rules
- read files, run shell commands, write/modify files; may access external network resources; usually needs no extra API key.
- Validate with a small sample before expanding scope.
- Return the result, validation criteria, and next iteration options. Choose the trigger
The source does not require a stable slash command. After installation, invoke the skill by name and describe the task.
Provide inputs and boundaries
Name target files or source material, expected output, forbidden changes, and whether network or shell access is allowed. Permission fingerprint: read files, run shell commands, write/modify files.
Validate with a small run
Start with a small task and check whether the result follows “NEVER USE These Commands / Modern Replacements / Tool Not Installed?”. Inspect diffs, logs, previews, or tests before expanding scope.
Review before delivery
Confirm the final output includes a concrete result, evidence, and next action. If it stays generic, tighten inputs, boundaries, and acceptance criteria.
---
name: modern-cli-tools
description: Use at session start and before running shell commands involving Python, Node.js, file search, o…
category: other
source: tomevault-io/skills-registry
---
# modern-cli-tools
## When to use
- Use at session start and before running shell commands involving Python, Node.js, file search, or HTTP requests. Use w…
- Use it when the task has clear inputs, repeatable steps, and validation criteria.
## What to provide
- Target material, scope, expected result, and forbidden changes.
- Whether network, commands, file writes, or external services are allowed.
## Execution rules
- Organize steps around “NEVER USE These Commands / Modern Replacements / Tool Not Installed?” and keep inference separate from source facts.
- read files, run shell commands, write/modify files; may access external network resources; usually needs no extra API key.
- Validate with a small sample before expanding the task.
## Output requirements
- Return the deliverable, key evidence, validation method, and next action.
- Mark missing information as unknown; do not invent commands, platforms, or dependencies. Evidence boundary and execution chain
The author source anchors workflow facts; repository files anchor sources and commands; Fluxly only adds fit, limitations, and quality judgment.
skill "modern-cli-tools" {
input -> user goal + target files + boundaries + acceptance criteria
context -> NEVER USE These Commands / Modern Replacements / Tool Not Installed?
rules -> SKILL.md triggers / order / output contract
runtime -> Node.js / Python | read files, run shell commands, write/modify files | may access external network resources
guardrails -> usually needs no extra API key + small-sample validation + diff/log review
output -> copyable result + checklist + next iteration
}Modern CLI Tools
NEVER USE These Commands
These commands are prohibited. No exceptions, no fallback.
Python:
pip,pip3,pip install,pip freezepython -m venv,virtualenvpython,python3(to run scripts — useuv runinstead)
Node.js:
npm,npm install,npm run,npxyarn
Node Versions:
nvm
Shell:
grep— userg(ripgrep)find— usefd
HTTP:
curl,wget— usexh
Modern Replacements
| Task | Command | Replaces |
|---|---|---|
| Install Python package | uv add <pkg> |
pip install |
| Run Python tool (one-off) | uvx <tool> |
pipx run / pip install + run |
| Run Python script | uv run script.py |
python script.py |
| Run Python tests | uv run pytest |
python -m pytest |
| Sync Python environment | uv sync |
pip install -r requirements.txt |
| Manage Python version | uv python install 3.12 |
pyenv / system python |
| Install Node packages | pnpm install |
npm install / yarn |
| Run Node script | pnpm run <script> |
npm run / yarn |
| Install Node version | fnm install <version> |
nvm install |
| Use Node version | fnm use <version> |
nvm use |
| Search file contents | rg <pattern> |
grep -r |
| Find files | fd <pattern> |
find . -name |
| Make HTTP request | xh GET <url> |
curl / wget |
Tool Not Installed?
Do NOT fall back to the legacy tool. Stop and tell the user to install the modern tool:
| Tool | Official Site |
|---|---|
| uv / uvx | https://github.com/astral-sh/uv |
| pnpm | https://pnpm.io |
| fnm | https://github.com/Schniz/fnm |
ripgrep (rg) |
https://github.com/BurntSushi/ripgrep |
| fd | https://github.com/sharkdp/fd |
| xh | https://github.com/ducaale/xh |
Example message to user:
"
rg(ripgrep) is not installed. Install it from https://github.com/BurntSushi/ripgrep before continuing."
Red Flags — You Are About to Violate This Skill
| Thought | Reality |
|---|---|
| "The tool isn't installed" | Tell the user to install it. Do NOT fall back to legacy tool. |
| "Just this once" | No exceptions. Use the modern tool or stop. |
| "This is a CI/container environment" | Still applies. Notify the user if the tool is unavailable. |
| "The existing script already uses pip/npm" | Tell the user to migrate. Do not propagate legacy tool usage. |
| "It's faster/easier to use grep here" | Use rg. It is faster. |
| "The user didn't ask me to use modern tools" | This skill is always active. It applies regardless. |
Source: atomikpanda/modern-cli-tools — distributed by TomeVault.
Decide Fit First
Design Intent
How To Use It
Boundaries And Review