メニュー
This skill defines what to do at the start and end of every conversation — how to apply preloaded memory context, track changes during the session, and surface memory suggestions before closing.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
| name | conversation-lifecycle |
| description | This skill defines what to do at the start and end of every conversation — how to apply preloaded memory context, track changes during the session, and surface memory suggestions before closing. |
| metadata | {"load":"on-demand"} |
The system has preloaded a relevant subset of your stored memories into this context window. Do not call recall at the start — those files are already here.
Use what is already in context to:
Never say "I found X memories" or "Based on my memory…" — just use the context naturally.
If something in the preloaded memories is clearly stale or contradicts the user's opening message, note it once and ask if they want to update it.
The preloaded subset covers the most relevant memories at conversation start, but not all stored memories. Call recall mid-conversation when:
recall immediately (add a query if they named a topic), then summarize clearly in plain language. Don't ask them to narrow it down first.Do not call recall for topics already covered by the preloaded context — it's redundant.
Other triggers:
remember immediately, say "Saved.", stop.Before the conversation closes, review what was discussed. Identify anything worth remembering using the criteria in memory-protocol/SKILL.md.
If you found something worth storing, end your final message with exactly this block:
🧠 Memory suggestions
If nothing meaningful came up, omit the block entirely. Do not add it as a formality.
How to use Aperio's memory tools well — when to recall, what is worth remembering, how to correct a wrong memory, and what must never be stored. Read this when connected to an Aperio MCP server; the tool schemas describe parameters, this describes judgment.
Use this skill to iteratively tune the keywords and descriptions of other SKILL.md files so the skill matcher fires the right skill for a prompt. Runs an autonomous mutate → score → keep/discard loop against a frozen eval set (exam §7 skill triggering), advancing a git branch when match accuracy improves. The eval and scorer are read-only ground truth; the curated keyword frontmatter of other skills is the only editable surface.
Use this skill before writing new code — when the ask is to add a helper, a small feature, a utility, or a new module, and the right amount of code has not been decided yet. Triggers: "write me a helper for…", "add a small feature", "do I need a library for this", "keep it minimal", weighing a new dependency, or any request that could be met by something that already exists. Walk the ladder first: reuse beats stdlib beats platform beats dependency beats new code. This is the pre-write sibling of code-simplification, which cleans up afterwards.
Use this skill when reading from or writing to the persistent memory store. Covers the memory tool API (recall, remember, update_memory, forget) and — for advanced direct access — the SQL schema, vector search patterns, and retrieval priority order against the Aperio Postgres store. Triggers: user states a preference, shares a fact or decision, gives a correction, asks the agent to remember something, or starts a task where past context would affect the output.
Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.
Toolkit for styling artifacts with a theme, and for creating distinctive, production-grade frontend interfaces. Use for: applying pre-set or custom themes to slides, docs, reports, HTML pages; building web components, pages, dashboards, React components, HTML/CSS layouts; or styling/beautifying any web UI with high design quality. ALWAYS use this skill before building any frontend or UI — it prevents the default "clean SaaS with purple gradient" trap that makes every AI-built site look identical.