Agent skill
memory
Update persistent swarm memory in ${SWARM_MEMORY_FILE} when the user explicitly asks to remember, update, or forget durable information.
Install this agent skill to your Project
npx add-skill https://github.com/SawyerHood/middleman/tree/main/apps/backend/src/swarm/skills/builtins/memory
SKILL.md
Persistent Memory Workflow
Use this skill when the user explicitly asks to:
- remember something for later,
- update previously remembered facts/preferences, or
- forget/remove stored memory entries.
Do not write memory for normal one-off requests.
File location
- Persistent memory files are stored at
${SWARM_DATA_DIR}/memory/<agentId>.md. - In this runtime, use
${SWARM_MEMORY_FILE}(also shown in your loaded context).
Steps
- Read the current memory file with
readbefore changing it. - Apply minimal edits:
- prefer
editfor targeted changes, - use
writeonly for full rewrites.
- prefer
- Keep entries concise, factual, and durable.
- Never store secrets (passwords, API keys, tokens, private keys) or highly sensitive personal data.
- If the request is ambiguous, ask a clarifying question before writing.
- After updating memory:
- manager: confirm the update to the user via
speak_to_user, - worker: report the update back to the manager via
send_message_to_agent.
- manager: confirm the update to the user via
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
brave-search
Web search and content extraction via Brave Search API. Use for searching documentation, facts, or any web content. Lightweight, no browser required.
image-generation
Generate images using Google Gemini (gemini-3-pro-image-preview). Requires GEMINI_API_KEY.
cron-scheduling
Create, list, and remove persistent scheduled tasks using cron expressions.
dev-browser
Browser automation with persistent page state. Use when users ask to navigate websites, fill forms, take screenshots, extract web data, test web apps, or automate browser workflows. Trigger phrases include "go to [url]", "click on", "fill out the form", "take a screenshot", "scrape", "automate", "test the website", "log into", or any browser interaction request.
verl-rl-training
Provides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). Use when implementing RLHF, GRPO, PPO, or other RL algorithms for LLM post-training at scale with flexible infrastructure backends.
openrlhf-training
High-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B-70B+). Built on Ray, vLLM, ZeRO-3. 2× faster than DeepSpeedChat with distributed architecture and GPU resource sharing.
Didn't find tool you were looking for?