Clangd LSP
v1.0.0C/C++ language server (clangd) providing code intelligence, diagnostics, and formatting for .c, .h, .cpp, .cc, .cxx, .hpp, .hxx files. Use when working with C or C++ code that needs autocomplete, go-to-definition, find references, error detection, or refactoring support.
⭐ 0· 1.1k·4 current·4 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name, description, and SKILL.md all describe clangd-based C/C++ language-server functionality. The instructions only require standard LLVM/clang tooling and project build metadata (compile_commands.json/.clangd), which are appropriate and expected for this purpose.
Instruction Scope
SKILL.md stays on-topic: it explains how to install clangd, verify it, format/compile/analyze local source files, and configure project compile flags. It does not instruct reading or exfiltrating unrelated files, accessing secrets, or contacting unexpected external endpoints.
Install Mechanism
There is no automated install spec — the skill is instruction-only. It recommends standard, well-known package managers (brew/apt/dnf/pacman/winget) or official LLVM releases on GitHub, which is proportionate and low-risk compared with arbitrary download URLs or extract/install scripts.
Credentials
No environment variables, credentials, or configuration paths are required. The requested artifacts (compile_commands.json, .clangd) are project-local and appropriate for language-server operation.
Persistence & Privilege
always is false and the skill is user-invocable. There is no indication it attempts to persist or modify other skills or global agent configuration; autonomous invocation is allowed but is the platform default and not excessive here.
Assessment
This skill appears to be what it claims: a set of instructions for installing and using clangd and related LLVM tools. Before using it, be aware that: (1) you must install system packages (brew/apt/dnf/pacman/winget or GitHub releases) — only run installers you trust; (2) commands like clang-tidy --fix or build commands can modify files or run build steps, so review them before execution; and (3) avoid letting an agent run build or analysis on sensitive or untrusted code without review. If you want the agent to act on your code, ensure it only has access to the repositories/projects you intend to expose.Like a lobster shell, security has layers — review code before you run it.
latestvk97cq1ase5q0yvdyre6wjbcwbn80thmk
License
MIT-0
Free to use, modify, and redistribute. No attribution required.