Internship Daily Reflection
v1.0.0将实习中的零散记录、聊天片段和任务笔记整理成可直接粘贴的中文日报或进展汇报。适用于写日报、整理今天任务、发给导师或 leader 的进展同步，以及填写“计划阶段、汇报阶段、进展状态、进展情况、问题及原因”等固定字段。
⭐ 1· 50·0 current·0 all-time
by@npccxx
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
The name/description, SKILL.md, index.js, templates, and examples all implement the stated purpose (organize notes into Chinese reports). No unrelated dependencies, env vars, or binaries are required.
Instruction Scope
SKILL.md narrowly describes how to parse input, ask up to four follow-up questions if data is missing, and produce two templates. The runtime code follows that: it builds a prompt and either calls the provided runtime model or falls back to a local renderer. Instructions do not ask to read files or environment variables outside the provided inputs.
Install Mechanism
There is no install spec or remote download. The package contains a small index.js and supporting markdown files; nothing is fetched from external URLs or written to unexpected locations.
Credentials
The skill requires no environment variables, keys, or config paths. The code optionally uses a provided runtime model client via the context (model.generate / model.complete), which is expected for an LLM-backed skill.
Persistence & Privilege
always is false, the skill is user-invocable, and model invocation is enabled (normal). The skill does not modify other skills or system settings and does not request persistent privileges.
Assessment
This skill appears to do exactly what it says: organize scattered internship notes into structured Chinese reports and ask follow‑ups when needed. It does not request credentials or download code. Note that it will call the agent's runtime model (context.model) when available — so outputs depend on that model and could still contain subtle inaccuracies or hallucinations. If you will feed sensitive or private content into the skill, be aware the content may be included in prompts sent to your runtime model provider. Otherwise it is coherent and proportionate to its purpose.Like a lobster shell, security has layers — review code before you run it.
latestvk97dh04jqj3513tc3ynkb5qw5584s5dc
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
Runtime requirements
📝 Clawdis