installing-cli-tools
Skill169 starsChanged 56 days agoMITView on GitHub
Install, upgrade, configure, and verify developer CLI tools safely. Use when a user asks to install a new CLI, command-line app, SDK tool, package-manager binary, GitHub release binary, language runtime tool, or AI/vendor CLI; configure shell PATH/completions; run first login; set API keys, tokens, or env variables for a CLI; migrate an existing CLI install; or troubleshoot a CLI installation while avoiding secret leakage.
- Reads credentials
- Installs packages
In this repository23 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- agentic-readinessSkill
- bug-fix-protocolSkill
- clipboardSkill
- code-that-fits-in-your-headSkill
- fetch-url-as-markdownSkill
- fpf-problem-solvingSkill
- hooks-managementSkill
- investigating-repository-historySkill
- maintaining-macos-healthSkill
- maintaining-windows-healthSkill
- mcp-managementSkill
- plan-modeSkill
- plugins-managementSkill
- prompt-engineeringSkill
- refactoring-csharpSkill
- repo-activity-summarySkill
- semantic-scholar-deepSkill
- settings-managementSkill
- skills-managementSkill
- ubiquitous-languageSkill
- windows-qa-engineerSkill
The file
We split this skill into the rules it gives an agent
8 rules. About 0 are common, 4 are distinctive, and 4 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- could be automatic: a setting could enforce it
- Distinctive: line 10
Use this skill to take a CLI from "not installed" to "usable and verified" without exposing credentials in chat, logs, shell history, or …
- Very specific: line 15
Check current state with narrow commands such as command -v tool, tool --version, package-manager queries, and existing config file paths …
- Very specific: line 24
Verify with tool --version, tool doctor or equivalent, and a non-destructive authenticated command if relevant.
- Very specific: line 29
Never read, print, summarize, grep, or search for existing secret values in .env, shell rc files, keychains, SSH keys, cloud credential …
- Distinctive: line 46
Use precise commands and avoid noisy discovery.
- Very specific: line 64
Do not add API keys, tokens, passwords, or provider credentials to .zshrc, .bashrc, .profile, .config/fish/config.fish, or project shell …
- Distinctive: line 68
Verify both installation and authentication without destructive actions:
- Distinctive: line 75
If verification requires a paid operation, mutation, or secret display command, do not run it.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Installing CLI Tools
Overview
Use this skill to take a CLI from "not installed" to "usable and verified" without exposing credentials in chat, logs, shell history, or repo files. Treat installation and secret setup as separate phases.
Workflow
- Identify the exact CLI, target OS/architecture, intended use, and whether authentication is required.
- Check current state with narrow commands such as
command -v tool,tool --version, package-manager queries, and existing config file paths only when needed. - Research current official installation docs before acting unless the user supplied an exact trusted source. Prefer official docs, package registry pages, signed release notes, or the upstream GitHub release.
- Choose the least surprising install method:
- Existing project manager (
brew,npm,pipx,uv tool,cargo install,go install) when official and maintained. - Vendor installer only when it is the official path and its behavior is understood.
- Manual binary install only after verifying architecture, checksum/signature when available, permissions, and destination.
- Existing project manager (
- Install to a user-writable, reversible location when possible. Avoid
sudounless the install path truly requires it and the user has agreed. - Wire PATH/completions only as narrowly as needed. Never edit shell startup files to add secrets.
- Configure authentication through a safe channel.
- Verify with
tool --version,tool doctoror equivalent, and a non-destructive authenticated command if relevant. - Report what changed, where files were placed, how to undo it, and whether any restart/new shell is needed.
Secret Handling
Never read, print, summarize, grep, or search for existing secret values in .env, shell rc files, keychains, SSH keys, cloud credential files, or password-manager vaults. Do not run broad commands like env, printenv, or recursive token searches.
For new credentials, use the safest supported option in this order:
- Browser/device OAuth or official
tool auth login. - The platform's secure setup flow or connector for that provider.
- OS credential store, such as macOS Keychain, through commands that accept the secret via stdin or hidden prompt.
- Tool-specific config command that prompts interactively and does not echo the input.
- A local secrets manager such as
op,bw,pass,gopass, ordirenvwith a secret backend, if the user already uses it. - A plaintext env file only when the user explicitly asks for it or the CLI has no safer option; write placeholders by default and set mode
0600.
Do not put secret values in command arguments, chat messages, shell history, logs, generated docs, git commits, package manager config, MCP config, or shell startup files. If a command needs a value, prefer an interactive prompt, stdin, or a temporary file with 0600 permissions that is removed immediately after use.
Before accepting a credential from the user, state the destination and persistence model in one sentence, for example: "This will store the token in macOS Keychain under service example-cli; I will not print it back." If the current environment cannot safely accept hidden input, stop and ask the user to run the official login command locally.
Installation Checks
Use precise commands and avoid noisy discovery. Good checks:
command -v example
example --version
brew list --versions example
npm view example-cli version
python3 -m pipx listFor GitHub release binaries, verify the asset matches OS and CPU architecture. Use shasum -a 256 when upstream publishes checksums. Prefer signed or notarized macOS artifacts when available.
For installer scripts fetched over the network, do not pipe directly into a shell unless the user explicitly requests that official install style. Prefer downloading to a temporary file, reading the script enough to understand what it changes, then running it.
Shell Integration
Modify shell files only for PATH, completions, aliases requested by the user, or non-secret configuration. Before editing, identify the active shell and target file. Keep edits idempotent and bounded by clear comments when adding a block.
Do not add API keys, tokens, passwords, or provider credentials to .zshrc, .bashrc, .profile, .config/fish/config.fish, or project shell hooks. For env variables that point to non-secret paths or feature flags, explain why they are safe.
Verification
Verify both installation and authentication without destructive actions:
- Installation:
tool --version,tool help, or package-manager metadata. - PATH: open a fresh shell or source only the changed file when safe.
- Auth:
tool auth status,whoami,account show, or a read-only API call. - Failure: capture exact non-secret error text and classify whether the issue is PATH, missing dependency, architecture, permissions, network, or authentication.
If verification requires a paid operation, mutation, or secret display command, do not run it. Use the vendor's status command or ask the user for permission to run a specific safe alternative.
Rollback
Track install actions as you go. When finishing, include the uninstall command or manual rollback path:
- Package manager uninstall command.
- Files, symlinks, launch agents, or completions created.
- Shell file block added.
- Credential entry name only, never the value.
For failed installs, clean temporary files and partial symlinks when that is clearly safe. Ask before deleting user-owned config, caches, or credentials.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

