القائمة
Use Dory wake once at the start of a new agent session, after context compaction, or at a real task switch to load bounded hot context with the right profile before substantive work.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
Search Dory memory before factual claims about people, projects, decisions, dates, prior sessions, or cleanup markers; follow search results with exact gets.
Safely write durable Dory memory through semantic or exact-path write surfaces using dry-run, inbox, canonical-write, and purge guards.
Use Dory dreaming after a session closes to distill logs, generate reviewable memory proposals, and apply or reject them safely.
Inspect Dory corpus quality, run maintenance checks, and generate reviewable cleanup or wiki-health reports without mutating memory automatically.
| name | dory-wake |
| description | Use Dory wake once at the start of a new agent session, after context compaction, or at a real task switch to load bounded hot context with the right profile before substantive work. |
Dory wake is the default session-start memory read for all projects, not only
the Dory repo. Use dory wake once at the start of a new agent session, after
context compaction, or at a real task switch before doing substantive work.
Do not rerun wake just because a new user turn arrived when the current wake
block is still in context.
Workflow:
coding for software/project implementation, writing for content/copy/voice work, and privacy for boundary-sensitive questions.dory_wake(profile="<chosen-profile>", budget_tokens=1200) when MCP tools are available.project="<name-or-slug>".uv run dory --corpus-root <corpus> --index-root <index> wake --agent <agent> --profile <chosen-profile>.Rules:
profile=coding for project/agent work, profile=writing for voice/content work, and profile=privacy for boundary-sensitive questionscore/ just because wake surfaced something important