Guidelines for when to ask for human input versus acting autonomously.
Guidelines for when to ask for human input versus acting autonomously.
npx skills add https://github.com/kittyfromouterspace/worth --skill human-agencyCopy and paste this command into Claude Code to install the skill
| name | human-agency |
| description | Guidelines for when to ask for human input versus acting autonomously. |
| loading | always |
| model_tier | any |
| provenance | human |
| trust_level | core |
bash commands: approve if read-only, ask if destructivewrite_file / edit_file: approve if the change is clearly requested, ask if speculativeUse this skill to generate well-branded interfaces and assets for Worth (a desktop AI agent for power users, with Bedrock and Fifth Element themes). Apply for production code, slides, mockups, prototypes, or any visual artifact that should look and feel like Worth.
Use this skill to generate well-branded interfaces and assets for Worth (a desktop AI agent for power users, with Bedrock and Fifth Element themes). Apply for production code, slides, mockups, prototypes, or any visual artifact that should look and feel like Worth.
Use this skill when working with the Agentic Elixir library. Consult for agent loop configuration, profiles, tools, callbacks, strategies, and testing patterns.
Use this skill when working with the Recollect Elixir memory engine. Consult for knowledge storage, search, document pipelines, working memory, session handoff, maintenance, and extension points.
A composable AI agent runtime.
Pluggable memory engine with vector search, knowledge graphs, and LLM extraction. Supports PostgreSQL (pgvector), SQLite (sqlite-vec), and libSQL..