letta/setting-profile-images/SKILL.md
Sets Letta Desktop and Letta Code agent profile images by writing profile.png into an agent MemFS repository. Use when the user asks to add, change, generate, or fix an agent avatar, profile picture, profile image, or Desktop agent photo.
npx skillsauth add letta-ai/skills setting-profile-imagesInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Letta Desktop displays an agent profile image from the agent memory repository at:
$MEMORY_DIR/profile.png
The Desktop/local backend API reads the same file via:
GET /v1/agents/:agent_id/profile-picture
For local Desktop agents, do not PATCH arbitrary agent metadata for the avatar. Write profile.png into MemFS and commit it.
scripts/set_profile_image.py.profile.png to the target agent's memory repo.LETTA_BASE_URL and LETTA_API_KEY are available.Locate this skill's script if needed:
SCRIPT=$(find ~/letta/skills ~/.letta/skills -path '*/setting-profile-images/scripts/set_profile_image.py' -print -quit)
Set the current agent's profile image:
python3 "$SCRIPT" /path/to/avatar.png
The script uses, in order:
--memory-dir, if passed$MEMORY_DIR$LETTA_MEMORY_DIR~/.letta/lc-local-backend/memfs/$AGENT_ID/memorypython3 "$SCRIPT" /path/to/avatar.png \
--agent-id agent-local-... \
--local-backend-dir ~/.letta/lc-local-backend
python3 "$SCRIPT" /path/to/avatar.jpg --size 512
python3 "$SCRIPT" /path/to/avatar.jpg --no-commit
python3 "$SCRIPT" /path/to/avatar.jpg --verify
--size controls the square output size in pixels. Use 512 unless there is a reason not to.--no-commit writes the file but leaves the memory repo uncommitted.--verify calls /v1/agents/:agent_id/profile-picture after writing, when API env vars are present.If the script is unavailable:
cp /path/to/avatar.png "$MEMORY_DIR/profile.png"
git -C "$MEMORY_DIR" add profile.png
git -C "$MEMORY_DIR" commit --author="$AGENT_NAME <[email protected]>" -m 'Add agent profile image'
Make sure the image is a reasonably sized square PNG before copying.
tools
Test any GUI app or change on a Daytona Windows remote desktop sandbox. Use to launch a GUI program, sync a local project, take a screenshot, record a video, or share a clickable live-desktop link with a teammate. Generic — the only dependency is Daytona. For Linux, use remote-desktop-testing-linux.
tools
Test any GUI app or change on a Daytona Linux (Ubuntu xfce4 + noVNC) remote desktop sandbox. Use to launch a GUI program, sync a local project, take a screenshot, record a video, or share a clickable live-desktop link with a teammate. Generic — the only dependency is Daytona. For Windows, use remote-desktop-testing-windows.
testing
Configures Letta agents' own runtime behavior, including model, context window, system prompt, reasoning, conversation overrides, compaction settings, and compaction prompts. Use when an agent or user asks to self-modify, tune summarization/compaction, change identity/system instructions, adjust model settings, or test conversation-scoped overrides.
testing
Navigates archived ChatGPT or Claude-style conversation exports and a MemFS reference archive on demand. Use when recalling what a past assistant knew, searching old conversations, rendering specific chats, seeding reference memory from export sidecars, or mining historical context without doing a full import.