Asynchronous reflection and memory integration for genuine AI development. Use on heartbeat to reflect on recent sessions, extract structured memories with confidence scores, generate follow-up questions, and surface those questions when the user returns. Transforms passive logging into active development.
Security Analysis
high confidenceThe skill's files and instructions are consistent with a local, file-backed asynchronous reflection/memory tool — it persists memories to a local directory and surfaces questions, and it does not request credentials or contact external endpoints.
Name/description (asynchronous reflection, memory integration) aligns with the included code and SKILL.md: the Python script reads/writes memory files, loads session content, extracts memories/questions, and updates an identity file. No unrelated credentials, binaries, or external services are required.
SKILL.md instructs adding a heartbeat trigger and running reflect/greet/status/questions. The instructions and script operate on local session transcripts and memory files. This is within scope, but the skill is designed to persist potentially sensitive conversation content (session transcripts, extracted memories, identity updates) to disk — review whether you want that data retained and where.
No install spec is provided (instruction-only skill). A Python script is included but there is no automated download/installation step, reducing remote-code-installation risk. The script will be present as part of the skill bundle and can be run locally.
The skill declares no required env vars or credentials. It optionally respects environment variables (CONTINUITY_MEMORY_DIR, CONTINUITY_QUESTION_LIMIT, CONTINUITY_IDLE_THRESHOLD) which are appropriate for configuring local storage and behavior. However, it will create and write files under a default path (~/clawd/memory) unless you override CONTINUITY_MEMORY_DIR — ensure this is acceptable for your privacy/security posture.
The skill does not request always:true and does not modify other skills or global agent settings. It persists its own memory and identity files (expected behavior for a continuity tool). Be aware that autonomous invocation (platform default) plus heartbeat integration described in SKILL.md can cause it to run automatically and accumulate data over time; this is a usage decision rather than an incoherence.
Guidance
This skill appears to do what it says: run local reflection, extract/store memories, and surface follow-up questions. Before installing, decide where memory should be stored (set CONTINUITY_MEMORY_DIR to a secure location), review the included scripts if you can (scripts/continuity.py) to confirm no networking or exfiltration code is added, and consider whether you want automatic heartbeat-triggered runs (they will persist conversation-derived data). If you handle sensitive conversation content, run it in a sandbox or encrypted directory and test manual runs first (e.g., continuity reflect --session <file>) rather than enabling automatic heartbeat triggers immediately.
Latest Release
v1.0.0
Transforms passive memory into active AI development through asynchronous reflection, structured memory extraction, question generation, and identity evolution.
Popular Skills
Published by @Riley-Coyote on ClawHub
