Git cli
v1.0.1Helper for using the Git CLI to inspect, stage, commit, branch, and synchronize code changes. Use when the user wants to understand or perform Git operations...
⭐ 1· 1.1k·15 current·16 all-time
byopenlang@openlang-cn
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description match the included files: SKILL.md gives Git CLI usage, reference docs expand commands/workflows, scripts provide small local helpers, and assets include commit/.gitignore templates. Nothing in the bundle requests unrelated services or credentials.
Instruction Scope
Runtime instructions limit actions to Git commands and the included shell scripts, prefer read-only commands, and explicitly warn about destructive commands. Scripts operate on the local repo and do not reference external endpoints or read unrelated system config.
Install Mechanism
No install spec; this is instruction-only with three small shell scripts. Nothing is downloaded or extracted from third-party URLs and the scripts are simple git wrappers.
Credentials
The skill declares no required environment variables, credentials, or config paths. The assets include a .gitignore example that mentions .env (as guidance to avoid committing secrets), which is appropriate and not a request for secrets.
Persistence & Privilege
always is false and the skill does not request permanent privileges or modify other skills. The default ability for the agent to invoke the skill autonomously remains, which is normal for skills.
Assessment
This skill appears to be what it says: a Git CLI helper with readable docs and small local scripts. Before running it, ensure Git is installed and run scripts from the intended repository root. Be aware that any commands the agent suggests (or executes, if you allow execution) that change state — especially push/pull/reset/force operations — will modify your repository or transmit data to configured remotes using whatever credentials are present in your environment; avoid running destructive commands unless you understand and approve them. If you are uncomfortable with agents executing commands that could push code, restrict command execution or review/confirm commands before running them. The included scripts are short and local (inspect them yourself if you want extra assurance).Like a lobster shell, security has layers — review code before you run it.
latestvk9758t1bhk03cyvsq3yva7weqd8315ze
License
MIT-0
Free to use, modify, and redistribute. No attribution required.