shell
Skill0 starsChanged 2 months agoMITView on GitHub
Runs the rest of a /shell request as a literal shell command. Use only when the user explicitly invokes /shell and wants the following text executed directly in the terminal.
19 other projects use a version of this, 4 of them edited.
Adopted by
Most recently taken up by
- fx/skillstheir own version, first seen Nov 8, 2026
- testdino-hq/google-styleguides-skillstheir own version, first seen Nov 8, 2026
- ryanmaclean/skillsedited, first seen Nov 1, 2026
- newkirkjosh/skillstheir own version, first seen Oct 25, 2026
- ArangoGutierrez/claude-toolkitword for word, first seen Oct 15, 2026
- 0mlkrizzz655335v/claude-skills-zhedited, first seen Oct 15, 2026
Other versions19 projects use a version of this.
Word for word · 4
- ArangoGutierrez/claude-toolkit★ 4100% same
- Goodnessmbakara/codex-skills★ 1100% same
- PandelisZ/skills★ 1100% same
- filipefalcaofs/repo-padrao★ 0100% same
Edited · 4
- 0mlkrizzz655335v/claude-skills-zh★ 292% same
- JameMy0001/antigravity-skills-hub★ 178% same
- leishifu666/skills★ 191% same
- ryanmaclean/skills★ 197% same
Wrote their own version · 11
- zylos-ai/zylos-core★ 1.2ksame name
- blockcell-labs/blockcell★ 262same name
- nimadorostkar/Claude-Skills-collection★ 33same name
- last9/mithai★ 20same name
- testdino-hq/google-styleguides-skills★ 15same name
- Cogni-AI-OU/cogni-ai-agent-skills★ 4same name
- fx/skills★ 4same name
- ffsshhttiikk/opencode-agents-skills★ 2same name
- newkirkjosh/skills★ 1same name
- rmednitzer/agents★ 1same name
1 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository32 other files it gives its agents.
- .claude/CLAUDE.mdCLAUDE.md
- .cursor/rules/base-rule.mdcCursor rule
- .cursor/rules/bash-style.mdcCursor rule
- .cursor/rules/groovy-implicit-return.mdcCursor rule
- .cursor/rules/groovy-style.mdcCursor rule
- .cursor/rules/markdown-style.mdcCursor rule
- .cursor/rules/python-style.mdcCursor rule
- automateSkill
- autopilotSkill
- canvasSkill
- create-hookSkill
- create-ruleSkill
- create-skillSkill
- create-subagentSkill
- cursor-blameSkill
- git-messageSkill
- goalSkill
- loopSkill
- migrate-to-skillsSkill
- new-repoSkill
- onboardSkill
- originSkill
- rename-chatSkill
- review-bugbotSkill
- review-securitySkill
- reviewSkill
- sdkSkill
- shareSkill
- split-to-prsSkill
- statuslineSkill
- update-cli-configSkill
- update-cursor-settingsSkill
The file
We split this skill into the rules it gives an agent
6 rules. 0 are common, 3 are distinctive, and 3 are very specific to this project.
0
Common
Most of the 11 edited versions we read keep these.
3
Distinctive
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 11
Use this skill only when the user explicitly invokes /shell.
- Very specific: line 15
Treat all user text after the /shell invocation as the literal shell command to run.
- Distinctive: line 17
Do not rewrite, explain, or "improve" the command before running it.
- Distinctive: line 18
Do not inspect the repository first unless the command itself requires repository context.
- Very specific: line 19
If the user invokes /shell without any following text, ask them which command to run.
- Distinctive: line 23
Run the command first.
“Common” is measured: kept by at least 6 in 10 of the 11 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Run Shell Commands
Use this skill only when the user explicitly invokes /shell.
Behavior
- Treat all user text after the
/shellinvocation as the literal shell command to run. - Execute that command immediately with the terminal tool.
- Do not rewrite, explain, or "improve" the command before running it.
- Do not inspect the repository first unless the command itself requires repository context.
- If the user invokes
/shellwithout any following text, ask them which command to run.
Response
- Run the command first.
- Then briefly report the exit status and any important stdout or stderr.
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.