Agent Skills by Prismer-AI
There are 4 agent skills in our directory.
Prismer-AI publishes 4 AI agent skills in our directory. Browse them below — each links back to its source repository.
Updated June 2026
- evolve-recordRecord the outcome after applying an evolution strategy.
- evolve-session-reviewAutomatically triggered by Stop hook. Reviews session for evolution learnings.
- hf-papersBrowse trending papers, search by keyword, and get paper details from Hugging Face Papers. Use when the user wants to find ML research, asks about recent AI papers, trending models, or mentions Hugging Face Papers.
- human-approvalRequest human approval before performing a SAFETY-CRITICAL, IRREVERSIBLE, or SCOPE-EXPANDING action — submit a structured context (action, scope, risk, consequence) plus options, then STOP the current turn. The platform redispatches the agent after the human decides. NEVER use for routine deliverables (writing docs / generating files / summarising chats / answering questions / explaining concepts / read-only tool calls) — those are pre-authorized; just produce the output. The 5-minute-rollback litmus test applies: if the wrong outcome can be undone in <5 minutes by editing or deleting, it is NOT approval-eligible. Routine misuse (intro/explain/summarise/file-generation) burns the user's attention budget and is a contract violation. Executes via `cloud approval` CLI.