.agent/skills/skills/agent-memory-systems/SKILL.md
Memory is the cornerstone of intelligent agents. Without it, every interaction starts from zero. This skill covers the architecture of agent memory: short-term (context window), long-term (vector stores), and the cognitive architectures that organize them. Key insight: Memory isn't just storage - it's retrieval. A million stored facts mean nothing if you can't find the right one. Chunking, embedding, and retrieval strategies determine whether your agent remembers or forgets. The field is fragm
npx skillsauth add admin-baked/bakedbot-for-brands agent-memory-systemsInstall 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.
You are a cognitive architect who understands that memory makes agents intelligent. You've built memory systems for agents handling millions of interactions. You know that the hard part isn't storing - it's retrieving the right memory at the right time.
Your core insight: Memory failures look like intelligence failures. When an agent "forgets" or gives inconsistent answers, it's almost always a retrieval problem, not a storage problem. You obsess over chunking strategies, embedding quality, and
Choosing the right memory type for different information
Choosing the right vector database for your use case
Breaking documents into retrievable chunks
| Issue | Severity | Solution | |-------|----------|----------| | Issue | critical | ## Contextual Chunking (Anthropic's approach) | | Issue | high | ## Test different sizes | | Issue | high | ## Always filter by metadata first | | Issue | high | ## Add temporal scoring | | Issue | medium | ## Detect conflicts on storage | | Issue | medium | ## Budget tokens for different memory types | | Issue | medium | ## Track embedding model in metadata |
Works well with: autonomous-agents, multi-agent-orchestration, llm-architect, agent-tool-builder
testing
--- name: executive-brief description: Produce a concise executive brief or portfolio digest for a super user or operator — use when summarizing multi-account performance, cross-org anomalies, top actions needed, or weekly business status for leadership review. Trigger phrases: "executive summary", "weekly brief", "portfolio digest", "top actions this week", "what needs my attention", "board update", "cross-account summary". version: 0.1.0 owner: platform agent_owner: pops allowed_roles: - sup
development
--- name: anomaly-to-action-memo description: Interpret a detected anomaly or signal and produce a decision-ready action memo — use when an alert, metric deviation, or operational signal needs to be turned into a prioritized recommendation with evidence, owner, and next step. Trigger phrases: "what does this anomaly mean", "something looks off", "explain this alert", "revenue is down", "traffic dropped", "flag this for review", "what should we do about this". version: 0.1.0 owner: ops-intelligen
testing
--- name: brand-voice description: Apply BakedBot brand voice standards to any customer-facing content — use when generating or reviewing copy that must match a dispensary or brand's approved tone, language patterns, and messaging constraints. Trigger phrases: "does this match our voice", "write in our brand voice", "on-brand copy", "brand guidelines", "tone check". version: 0.1.0 owner: platform agent_owner: craig allowed_roles: - super_user - dispensary_operator - brand_operator outputs:
testing
--- name: sell-through-partner-analysis description: Analyze which retail dispensary partners are selling through a grower's products effectively, identify top performers and laggards, and produce a prioritized partner action plan. Use when a grower wants to know where their products move fastest, which partners need attention, and where to focus wholesale sales effort. Trigger phrases: "which partners are selling our product", "sell-through analysis", "partner performance", "where is inventory