Deepscan Monitor
v0.1.0Run and monitor PapersFlow DeepScan jobs. Use when the user wants long-running research progress, intermediate findings, final reports, or plotting from a co...
⭐ 0· 177·0 current·0 all-time
byPapersFlow@papersareflowing
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description (monitoring DeepScan jobs) match the SKILL.md steps (start run, poll live snapshots, fetch reports, summarize, plot). The SKILL.md expects the agent to call named tool-like operations (run_deepscan, get_deepscan_live_snapshot, get_deepscan_status, get_deepscan_report, summarize_evidence, run_python_plot), which is consistent with a monitoring skill.
Instruction Scope
Instructions are narrowly scoped to managing and reporting on DeepScan runs (polling, summarizing, plotting). They do not instruct the agent to read arbitrary files, export secrets, or contact unrelated endpoints. The polling guidance implies repeated API calls, which is expected for long-running job monitoring.
Install Mechanism
No install spec and no code files — this is instruction-only, so nothing is written to disk or downloaded. Lowest-risk install footprint.
Credentials
The skill declares no environment variables or credentials. That is coherent if the platform already exposes the referenced deepscan tool operations to the agent; if PapersFlow requires API keys, those are not declared here — confirm where/how authentication to PapersFlow is provided to the agent.
Persistence & Privilege
always is false (no permanent auto-inclusion). Model invocation is allowed (default) which is normal for skills. The skill does not request any system-wide config changes or elevated privileges.
Assessment
This skill appears to be what it says: a set of instructions for monitoring DeepScan jobs that uses platform-provided operations. Before installing, confirm that your agent environment actually exposes the named operations (run_deepscan, get_deepscan_live_snapshot, etc.) and that any PapersFlow API credentials (if required) are provided separately and scoped appropriately. Be aware the skill will poll the service for updates (causing repeated API calls) and may run plotting via run_python_plot — confirm plotting is performed in a safe sandbox and that no private data will be sent to unknown external endpoints.Like a lobster shell, security has layers — review code before you run it.
latestvk97a1d5kr34y6whgsmzmnmtp2n82p367
License
MIT-0
Free to use, modify, and redistribute. No attribution required.