AI Usage Audit — Monthly Retrospective & Insights
v1.0.0Generates a monthly HTML report analyzing your recent AI conversations by theme, efficiency patterns, output value, and collaboration quality with actionable...
⭐ 0· 80·0 current·0 all-time
by@jjliu6
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
The skill declares a single purpose — analyzing chat history and producing an HTML retrospective — and its runtime instructions only ask for conversation-history tools (recent_chats, conversation_search). There are no unrelated env vars, binaries, or install steps required, so requested capabilities align with the stated purpose.
Instruction Scope
The SKILL.md explicitly instructs the agent to pull many pages of recent conversations (paginate, multiple rounds, supplement with searches) and to surface specific conversation snippets as evidence. This is appropriate for the analysis task but means the skill will access potentially large amounts of sensitive chat content. Also the trigger list is broad (including casual phrases), which increases the chance of inadvertent data collection if the agent is invoked automatically.
Install Mechanism
Instruction-only skill with no install spec, no downloads, and no code files. This is low-risk from an installation/execution perspective — nothing is written to disk by the skill itself.
Credentials
The skill requests no environment variables, credentials, or config paths. It relies on platform-provided conversation-history tools; those tools are expected for the stated purpose. There are no extra or unrelated secrets requested.
Persistence & Privilege
always:false (normal). The skill can be invoked autonomously by the agent (platform default). Combined with broad trigger phrases and the instruction to pull extensive history, this could lead to surprising data access if users haven't explicitly consented each time. The skill does not request persistent installation or modify other skills' configs.
Assessment
This skill appears to do what it says: it analyzes your chat history and builds a report. Before enabling or invoking it, consider: (1) Privacy: it will fetch many conversations from the specified time window — only enable it if you consent to that data being read for analysis. (2) Scope: specify a narrow time range or specific projects if you want to limit exposure. (3) Triggers: the skill's trigger list is broad (casual phrases), so prefer manual invocation rather than allowing autonomous runs. (4) Sharing: confirm how the generated HTML/report will be stored or shared by your agent (local only vs. uploaded somewhere). (5) Platform permissions: check what the platform's recent_chats and conversation_search tools can access and whether they log or transmit data externally. If you need stronger guarantees, run the prompt manually within a session you control and inspect the output before saving or sharing it.Like a lobster shell, security has layers — review code before you run it.
latestvk971sr0dg240q5ap1k93b3y1xn839gwf
License
MIT-0
Free to use, modify, and redistribute. No attribution required.