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 is internally consistent with its stated purpose — it reads/writes local memory files, generates and surfaces questions, and contains no network calls or external credential requirements — but it persistently stores conversation-derived data locally and includes comments that a production version would call an LLM (which would introduce network/data-exfiltration risk if implemented).
Name/description (asynchronous reflection, memory integration, question surfacing) match the provided runtime instructions and the included script. Required resources (none) are proportional to the functionality.
SKILL.md directs heartbeat integration and local CLI commands (reflect, questions, status, greet). The runtime instructions and script operate on local session files and memory files; nothing in SKILL.md instructs reading unrelated system files or accessing external endpoints. However the code and comments explicitly state that a production implementation would send transcripts to an LLM for analysis — if that is added, it could transmit sensitive conversation contents. Verify any future modifications that add network calls or external APIs.
Instruction-only with a non-invasive Python script included; there is no install spec and no downloaded/executed remote code. No package installs or external archives are pulled by the skill itself.
The skill declares no required environment variables or credentials. It optionally uses environment variables (CONTINUITY_MEMORY_DIR, CONTINUITY_QUESTION_LIMIT, etc.) for configuration, which are appropriate and non-sensitive by design.
The script persistently writes and reads files under a default path (~/clawd/memory) and will create reflection logs, questions.md, and identity.md. This is expected for a memory/continuity tool but means conversation-derived data is stored on disk. The skill is not configured as always:true and does not modify other skills' configs.
Guidance
This skill is coherent with its stated purpose and contains only local-file operations in the provided code. Before installing: 1) Review and, if desired, change the memory directory by setting CONTINUITY_MEMORY_DIR to a secure path (the default is ~/clawd/memory). 2) Understand that it will persist conversation-derived data (questions, identity, reflection logs) on disk — treat that data as sensitive and apply retention/encryption policies if needed. 3) The current analyze_session() is a placeholder; if you (or an upstream package) modify the skill to call an external LLM or other network services, audit those additions — they could transmit conversation transcripts. 4) If you do not want autonomous background reflection, do not add the heartbeat trigger described in SKILL.md. Test with non-sensitive transcripts first and review any future commits that introduce network I/O or additional environment/credential requirements.
Latest Release
v1.0.0
Transforms passive memory into active AI development
Popular Skills
Published by @Riley-Coyote on ClawHub
