codememory-plugin

This skill should be used when the user asks questions about past conversations, wants to recall previous discussions, references "earlier", "before", "previous", "what did we say", "remember when", or any query that requires retrieving information from conversation history. Automatically retrieves and injects relevant context from the CodeMemory memory system.

Use this skill to durably record a hard constraint or invariant that the work must respect. Invoke when the user states a must-not-break rule, a compatibility boundary, a performance budget, a security/compliance requirement, or any other guardrail that should outlive compaction. Do NOT invoke for soft preferences, style nudges, or constraints already captured earlier in the session.

Use this skill to durably record a non-trivial design or implementation decision so it survives compaction and can be recalled in future sessions. Invoke when you (or the user) commit to a meaningful technical choice — schema shape, library selection, refactor direction, breaking-change boundary, etc. Do NOT invoke for trivial choices, exploratory speculation, or decisions the user has already discarded.

Use this skill to durably record the current task or goal so future turns (and future sessions) can recall what we are trying to accomplish. Invoke when the user states a non-trivial objective, when scope is clarified after ambiguity, or when a goal is revised mid-session. Do NOT invoke for trivial follow-ups, micro-edits, or work already captured by an earlier task mark in the same session.

This skill should be used when creating conversation summaries for CodeMemory, discussing summarization quality, optimizing DAG structure, or working with the compaction system. Provides guidelines for creating high-quality summaries that preserve all important information while fitting within token budgets.