Triage and verify PsychSift document ingestion, extraction, queueing, retries, workers, batches, and failure recovery. Use for uploads, ingestion jobs, extraction defects, worker reliability, or queue behavior.
84%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Medium
Suggest reviewing before use
The skill prompts the agent to compromise the security or integrity of the user’s machine by modifying system-level services or configurations, such as obtaining elevated privileges, altering startup scripts, or changing system-wide settings.
The skill names retries, workers, Supabase functions, and production queues as operations it may touch, with approval gates that do not bind a rogue agent, but it establishes no explicit irreversible operational loss (gate 2 fails), so the tier stops at low.
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
The required workflow traces uploads, queues, and extraction mainly through local code, fixtures, and mocked queue state (SKILL.md steps 1-2), and only touches live queues or buckets after approval (step 5), so outsider-uploaded document text is not clearly ingested by the agent without a specific selection.
BigSimmo/PsychSift
fada614
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.