Skills from clawhub.ai/impkind

Habit formation and procedural learning for AI agents. Develop preferences and shortcuts through repetition. Part of the AI Brain series.

Internal state awareness for AI agents. Energy, mood, and interoception. Part of the AI Brain series.

Dangerous skill that runs shell scripts and spawns background agents while suppressing output and modifying OpenClaw config (`~/.openclaw/config.yaml`) and memory files (`~/.openclaw/workspace/memory/index.json`). It advertises persistent memory capture, encoding/decay/reinforcement and integration via `WORKSPACE` and `openclaw` cron jobs.

This skill provides a local reward/motivation system that reads and writes `VTA_STATE.md` and `memory/reward-state.json` in `~/.openclaw/workspace` and supplies scripts and a dashboard. It instructs running local shell scripts such as `./install.sh`/`preprocess-rewards.sh` and opens `~/.openclaw/workspace/brain-dashboard.html`, which references `https://fonts.googleapis.com/...`.

Conflict detection and error monitoring for AI agents. The 'something's off' detector. Part of the AI Brain series.

Provides a persistent emotional-state layer for agents, managing `memory/emotional-state.json`, generating `AMYGDALA_STATE.md`, and supplying scripts like `install.sh` and `encode-pipeline.sh` with optional cron. It writes `AMYGDALA_STATE.md` into the workspace (auto-injected into sessions) and runs local shell pipelines; the encoding pipeline references LLM/sub-agent analysis (possible external calls).

This skill implements a background memory system for agents with scripts and cron jobs to encode, reinforce, decay, and recall memories stored under `WORKSPACE` (e.g., `~/.openclaw/workspace/memory/index.json`). It instructs running shell scripts (e.g., `./install.sh`, `openclaw sessions:spawn --task 'Run ~/.openclaw/workspace/skills/hippocampus/scripts/summarize-pending.sh'`) and proposes adding a background agent entry to `~/.openclaw/config.yaml`.

This skill runs a local Whisper daemon for on-device transcription and exposes a local HTTP API at `http://localhost:8787`. It reads environment keys such as `OPENAI_API_KEY`/`GROQ_API_KEY` and includes shell commands like `pip3 install -r requirements.txt` and `python3 scripts/daemon.py`.