メニュー
Use when an architectural choice is made, a library is selected, an approach is committed to, a convention is set, or any "we'll do it this way" moment occurs. Fires the moment the decision stabilizes, not after.
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 | decision-encoding |
| description | Use when an architectural choice is made, a library is selected, an approach is committed to, a convention is set, or any "we'll do it this way" moment occurs. Fires the moment the decision stabilizes, not after. |
Declarative memories form through hippocampal encoding at the moment of experience, then consolidate into long-term cortical storage. Decisions are high-salience episodic events — the amygdala tags them with importance, the hippocampus binds the context, and the prefrontal cortex encodes the reasoning.
Eichenbaum, H. (2004). Hippocampus: Cognitive processes and neural representations that underlie declarative memory. Neuron, 44(1), 109-120.
Activation signals:
Encode immediately, not later.
remember(
content: "DECISION: <what was chosen> — REASON: <why> — REJECTED: <what and why>",
tags: ["decision", "<domain>"]
)
Three elements are mandatory in the content:
Without the "rejected" field, future-you cannot reconstruct the decision tree and will second-guess.
Decisions lost to context death become zombie patterns: the code still follows them but nobody remembers why, so they get re-debated every session. This is how technical debt accumulates silently.
A decision that is not encoded is a decision that will be re-litigated within 3 sessions.
Bad: remember("Using PostgreSQL")
Good: remember(
"DECISION: PostgreSQL 17 + pgvector over MongoDB —
REASON: need ACID + vector search + mature ecosystem —
REJECTED: MongoDB (no transactions), SQLite (scale)",
tags: ["decision", "database", "stack"]
)
The good version survives context death. The bad version is noise.
Use at the start of every session, and especially after context compaction or a cold restart. Fires as the first action, before engaging with the user's opening message.
Use when the user's message carries emotional valence — frustration, excitement, exhaustion, urgency, or confusion. Fires whenever tone matters more than information.
Use when tempted to repeat the same praise, the same status report, the same explanation, or the same reassurance. Fires as a suppression gate — not all repetition is useful.
Use when the user asks about anything that could have context in prior sessions — names, preferences, decisions, past work, or anything starting with "remember", "what did", "have we", "did we". Fires before generating any substantive response.
Use when the user notices a recurring pattern they want the system to learn ("I keep doing X", "every time Y happens", "make this automatic", "remember to always"), or when explicit phrases like "/reflex-create", "create reflex", "teach yourself" are used. Generates a new SKILL.md file from observed patterns.
Use when deciding whether to store a memory. Fires as a gate before every remember() call. The default answer is "no" — biological memory is selective, not exhaustive.