Daily Data Tracker
v1.0.0每日数据追踪与历史记录。维护每日关键指标的历史表格（日期/Revenue/Gross Adds/EOP/Paid Subs/端拆分），支持 WoW 计算和趋势分析。数据追加到 memory/powerbi-daily-track.md 的历史表。
⭐ 0· 13·0 current·0 all-time
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 promise a daily KPI tracker and history; the SKILL.md only instructs appending rows to memory/powerbi-daily-track.md and computing WoW and simple trend rules. It does not request unrelated credentials, binaries, or installs, so the declared purpose aligns with what it actually does.
Instruction Scope
Instructions are narrowly scoped to appending lines, adding remarks, and computing WoW/moving averages. They assume the user/agent already '抓完数据' (has fetched the data) but do not instruct how to fetch external data. The skill writes to the agent memory path (memory/powerbi-daily-track.md) — this is expected but worth noting because that file is persistent.
Install Mechanism
No install spec and no code files (instruction-only). This is the lowest-risk install pattern — nothing is downloaded or written beyond the memory file the instructions target.
Credentials
The skill declares no environment variables, credentials, or config paths and the instructions do not reference any external secrets. Required privileges are minimal and proportional to the stated purpose.
Persistence & Privilege
The skill writes to a persistent memory file (memory/powerbi-daily-track.md). It does not request always:true or modify other skills, but users should be aware that business metrics will be stored in agent memory and may persist across sessions or be included in later agent context.
Assessment
This skill appears coherent and low-risk, but consider these practical points before installing: (1) confirm that storing business metrics in agent memory is acceptable for your privacy and retention policies — agent memory may be persistent and visible to other agent runs; (2) the skill assumes you (or the agent) will provide the daily data — it does not fetch external data itself, so verify where the data comes from and that fetching/ingestion is handled securely; (3) test in a sandbox to ensure it appends (not overwrites) and formats rows correctly; (4) consider backups/encryption for the memory file if the metrics are sensitive; (5) review agent access controls so only authorized users/agents can read the memory file.Like a lobster shell, security has layers — review code before you run it.
latestvk972r8nm9g0602ysztf97yzyes84ncm2
License
MIT-0
Free to use, modify, and redistribute. No attribution required.