Imanju App Dev Skills
v1.0.0复杂APP模块化开发技能，遵循五大核心原则进行科学、有序、可控的APP开发。适用于从零开始开发复杂APP或重构现有项目。
⭐ 0· 94·0 current·0 all-time
by@smxtx
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description (complex app modular development) match the provided files: design templates, checklists, and three small helper scripts for scaffolding, validation, and locking. Nothing required by the skill (no env vars, no binaries) is unrelated to its stated purpose.
Instruction Scope
SKILL.md focuses on development principles, templates, and local commands. Runtime instructions reference only the included scripts (generate_module.py, validate_structure.py, lock_module.sh) and local project files; there are no instructions to read unrelated system files, export secrets, or send data externally.
Install Mechanism
No install spec is provided (instruction-only). The included scripts are small, plaintext, and operate on local filesystem; there are no downloads from URLs or archive extraction steps.
Credentials
The skill requires no environment variables or credentials. The shell script uses ${USER:-developer} only to populate lock metadata, which is proportionate to its purpose.
Persistence & Privilege
always is false and the skill does not request persistent platform privileges or modify other skills' configuration. Scripts create or modify files in the working directory (.locks, module directories) which is expected behavior for a scaffolding/locking tool.
Assessment
This skill appears coherent and limited to local development helpers: it creates module folders, writes README and lock files under the current project, and checks project structure. Before installing or running: (1) review and run the scripts in a safe/test repo to confirm behavior (generate_module.py creates directories and files; lock_module.sh writes .locks/* files and a symlink); (2) ensure you are comfortable with the scripts writing to the working directory (they do not touch system paths); (3) there are no network calls or credential usage, but if you plan to let an agent invoke this skill autonomously, be aware it can run these local scripts — run with appropriate repository permissions and backups. If you want stronger guarantees, run the scripts manually rather than granting autonomous execution.Like a lobster shell, security has layers — review code before you run it.
latestvk97802a694e2be135a6r3370bd83f8ns
License
MIT-0
Free to use, modify, and redistribute. No attribution required.