Sweep the current session, repo/task context, local task files, and approved remote task stores for outstanding actionable work, then record high-confidence items in docs/outstanding-issues.md. Use when the user types /ledger or asks to extract, capture, or reconcile outstanding tasks from this session into the ledger.
91%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Low
Low-risk findings worth noting
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 workflow sweeps approved remote task stores (step 2), which, once approved, can be queues such as GitHub or Jira where outsiders can submit issues the agent then reads for outstanding work without selecting a specific item.
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.