Memory that outlives the session: what an agent writes down at the end of its work, how notes are shaped so recall works, promoting working knowledge to permanent memory, superseding facts instead of appending contradictions, staleness and dated facts, and the written memory record. It teaches the discipline of persistent agent memory; it never predicts what a model will remember in-context and never recommends a storage product. Use when asking "agent memory", "persistent memory", "memory file", "what should the agent remember", "note anatomy", "promote to memory", "supersede stale facts", "knowledge cleanup", "recall between sessions", "memory record", "note-taking system for agents". Not for in-window context budgeting and compaction (ac-prompt-engineer), not for vector index mechanics and chunking (ac-retrieval-and-vector-systems), not for mid-task session handoff checkpoints (ac-handoff).
cp -r cryptoskill/skills/exchanges/anoscranel-ac-agent-memory-and-recall .claude/skills/clawhub install anoscranel-ac-agent-memory-and-recallCapabilities below are detected automatically by an open-source scanner that reads the skill's text and scripts (see how this is computed). Not measured means the scanner couldn't make a confident call — it is NOT a green check, and you should treat it as a possible red flag until a human or a stronger scanner has measured it.
analysis_only Phase 1 single-mode classification — multi-mode breakdown deferred to Phase 2.
External services this skill needs in order to work. The skill's behavior depends on these services being up, honest, and unchanged. Today we only show services we recognize from a curated list of ~50 well-known hosts (exchanges, RPC providers, data APIs); a complete dependency list — including every package, library, and binary the skill installs or imports — is on the roadmap.
anthropic.comNo one has audited this skill yet. That is different from “audited and clean” — it just means no professional reviewer (a security firm, the CryptoSkill team, or a verified independent researcher) has signed off on it. There are no audit reports to read. How reviewer levels work →
SKILL.md → SOURCE.md → TRUST.auto.yaml → Browse directory →
Auto-generated by cryptoskill/extract-capabilities/0.3.1 · hosted-service list version 2026-09-06 · how this is computed