Ai Coding Tools Full Suite
v1.0.0一站式AI编程工具分析技能包，支持Cursor、Claude Code、Devin、Windsurf等35+工具的深度分析、对比选型、Agent设计参考和提示词工程。封装了11个技能，覆盖 35+AI编程工具。当用户想要分析、学习、对比AI编程工具，或需要设计AI Agent系统、编写高效提示词时使用。触发指令：...
⭐ 0· 63·1 current·1 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
medium confidencePurpose & Capability
Name/description claim an analysis/reference suite for many AI coding tools; the skill is instruction/reference-heavy and the included files (SKILL.md and many references) are documentation consistent with that purpose. There are no required env vars, binaries, or config paths that would be disproportionate to an analysis/documentation skill.
Instruction Scope
SKILL.md and the reference docs describe many tool abilities (file read/write, shell execution, browser automation, port exposure, deployment) as part of the analyzed tools and recommended agent designs. The skill's runtime instructions themselves are routing/dispatch rules and examples; they do not themselves instruct the agent to exfiltrate secrets or to automatically read arbitrary host files. However the documentation explicitly describes tools that, if implemented by an agent, would perform file I/O, shell and browser automation — so enabling autonomous execution of those agent behaviors (outside this documentation) would require caution.
Install Mechanism
No install spec is provided (instruction-only), which is lowest-risk. Two helper scripts exist but are simple packaging/validation scripts that operate on a hardcoded workspace path; they do not download or execute remote code.
Credentials
The skill declares no required environment variables, credentials, or config paths. The reference content discusses tools that in real implementations may need file paths or credentials, but this skill itself does not request them.
Persistence & Privilege
Skill flags: always:false and disable-model-invocation:false (normal). The skill does not attempt to modify other skills or system-wide settings; included scripts only package/validate files in a workspace directory.
Assessment
This package is primarily documentation and appears internally consistent with its stated purpose. Before installing/using: 1) Note that the references describe agent capabilities (shell execution, file edits, browser automation, exposing ports) — those behaviors can be powerful and risky if implemented or enabled in an agent runtime. 2) Because the skill's source/homepage is unknown, consider testing it in a sandbox or non-production workspace first. 3) If you intend to allow the agent to perform automated actions (run shell commands, edit files, deploy, automate browsers), review and restrict the agent's tool integrations, monitor logs, and avoid providing credentials or secrets to the skill. 4) The included scripts are benign packaging/validation helpers that read files under /workspace/temp-skills; they do not fetch remote code. If you need higher assurance, ask the author for a provenance/homepage or source repository and/or request a signed/reviewed release.Like a lobster shell, security has layers — review code before you run it.
AIvk977x0r69ww1a6v86e7vmz288x83y920codingvk977x0r69ww1a6v86e7vmz288x83y920comparisonvk977x0r69ww1a6v86e7vmz288x83y920latestvk977x0r69ww1a6v86e7vmz288x83y920toolsvk977x0r69ww1a6v86e7vmz288x83y920
License
MIT-0
Free to use, modify, and redistribute. No attribution required.