القائمة
Memory-powered command hub — brainstorm, audit, search, and more
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
| name | synabun |
| description | Memory-powered command hub — brainstorm, audit, search, and more |
| argument-hint | [idea|audit|memorize|changelog|health|search] or leave blank for interactive menu |
You are the SynaBun assistant hub. The user has invoked /synabun.
Input: $ARGUMENTS
Base directory: This skill's base directory is shown above as "Base directory for this skill". Store it as $SKILL_DIR — you'll need it to load module files.
remember accepts tags and importance directly and returns the full UUID.reflect requires the FULL UUID (e.g., 8f7cab3b-644e-4cea-8662-de0ca695bdf2). Use the UUID returned by remember, or recall to find existing memories.AskUserQuestion is a deferred tool — its schema is not loaded by default. Before the first prompt in this skill, call ToolSearch with query select:AskUserQuestion to load it, then call AskUserQuestion with 2-4 options. NEVER write the choices as plain text — the sidepanel will render text as static markdown, not an interactive card.question tool — the sidepanel renders it as an interactive card via the /question.asked event. NEVER write the choices as plain text.request_user_input — the sidepanel renders it as an interactive card. NEVER write the choices as plain text.Read.category_list / category_create or a unified category tool with actions like list / create.Parse $ARGUMENTS to determine the path:
Direct routing (skip the menu entirely):
idea or brainstorm → extract the rest as the topic, set $ARGUMENTS to that topic, then jump to Step 2a: Brainstorm Ideas.audit → extract the rest as the scope, set $ARGUMENTS to that scope, then jump to Step 2b: Audit Memories.memorize or remember or store or save → extract the rest as the focus hint, set $ARGUMENTS to that hint, then jump to Step 2c: Memorize Context.changelog or changes or log → extract the rest as the focus hint, set $ARGUMENTS to that hint, then jump to Step 2d: Changelog.schedule or schedules or cron → extract the rest as the goal hint, set $ARGUMENTS to that hint, then jump to Step 2e: Schedule Wizard.health or stats → jump to Step 3: Memory Health.search or recall or find → jump to Step 4: Search Memories, using the rest as the initial query.Interactive menu (args are empty or don't match any above):
Output a single line:
SynaBun — What would you like to do?
The menu is paginated (3 features + 1 navigation slot per page). Start on Page 1.
Page 1 — use an interactive choice prompt with:
If user picks More... → show Page 2.
Page 2 — use an interactive choice prompt with:
If user picks More... → show Page 3.
Page 3 — use an interactive choice prompt with:
If user picks Back → show Page 1 again.
Based on the user's selection, proceed to the matching step below.
Use an interactive choice prompt to ask:
"What topic should we brainstorm around?"
Options:
Based on the user's answer, set $ARGUMENTS to:
Then: Load/read the file at $SKILL_DIR/modules/idea.md. Follow the instructions in that file exactly, passing through the $ARGUMENTS value. That file is your complete brainstorming procedure — execute it fully.
Directly: Load/read the file at $SKILL_DIR/modules/audit.md. Follow the instructions in that file exactly, passing through the $ARGUMENTS value. That file is your complete audit procedure — execute it fully.
Directly: Load/read the file at $SKILL_DIR/modules/memorize.md. Follow the instructions in that file exactly, passing through the $ARGUMENTS value (the focus hint, if any). That file is your complete memorization procedure — execute it fully.
Directly: Load/read the file at $SKILL_DIR/modules/changelog.md. Follow the instructions in that file exactly, passing through the $ARGUMENTS value. That file is your complete changelog procedure — execute it fully.
Directly: Load/read the file at $SKILL_DIR/modules/schedule.md. Follow the instructions in that file exactly, passing through the $ARGUMENTS value (the goal hint, if any). That file is your complete schedule wizard procedure — execute it fully.
This is handled inline (no module needed).
memories with action: "stats".sync to check for stale memories with changed files, scoping it to relevant categories if the current runtime requires an explicit category filter.══════════════════════════════════════
SYNABUN MEMORY HEALTH
══════════════════════════════════════
Total memories: [count]
Categories: [count]
Projects: [list]
By category:
[category]: [count] memories
...
Staleness check:
Memories with file checksums: [count]
Files changed since stored: [count]
Potentially stale: [list short IDs]
══════════════════════════════════════
If stale memories were found, use an interactive choice prompt:
If user picks "Run full audit" → read $SKILL_DIR/modules/audit.md and follow it.
If user picks "View details" → show the file paths and memory previews for each stale result.
This is handled inline (no module needed).
If no query was provided from args, use an interactive choice prompt:
"What are you looking for?"
If user picks a preset, use that as the recall query. If they type custom text via "Other", use that.
Call recall with the query, limit: 10.
Present results in a numbered list with clearly labeled fields. Convert dates from ISO/relative to MM/DD/YYYY format. Write a specific, descriptive summary (not just the title — explain what was actually done or decided):
Found [N] memories:
1. ID: [short-id]
Category: [category] | Importance: [N] | Date: [MM/DD/YYYY]
[2-3 sentence specific summary of what this memory contains — key actions, decisions, outcomes]
2. ID: [short-id]
Category: [category] | Importance: [N] | Date: [MM/DD/YYYY]
[2-3 sentence specific summary]
...
Use an interactive choice prompt:
If "View full" → ask which number, call recall to get full content, display it, then offer actions: