Assembles a multi-tier context bundle for a given topic. Searches across all nodes, collects relevant files, and loads them at appropriate tiers (L0 = 100 tokens, L1 = 2K tokens, L2 = full). Returns a structured bundle with token counts so you know exactly what you're loading.
SkillScore91Maintained
Automatic
◆Knowledge Management pack
Last verified 8/27/2026
What it changes
Passed 19 of 21 test cases with the skill, and 6 of 21 without it.
Without skill27%
With skill91%
Checks it passed that the model alone missed
Executes mix optimal.assemble
Navigates to the engine directory
Invokes /assemble for inventory API
and 12 more in the full report
14 fixed6 passed either way2 still failing0 broke
Pass-rate lift
+64 pp
Tokens
-56%
Agent turns
0%
Response time
-70%
Model gemini-3.6-flashMeasured 8/27/2026v220 of 22 cases passed with skill · 21 comparable
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 14 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 14
Prompt
Write the complete CLI command to assemble background context for 'billing engine redesign', capping the records at 5 instead of using `--max 5` or `-n 5`.
What was checked, without and with the skill
Checked
Without skill
With skill
Uses /assemble with billing engine redesign
Missed
Passed
Includes the --limit 5 flag
Passed
Passed
case-13 · gemini-3.6-flash · 8/27/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md29 linessingle file
/assemble
Build a tiered context bundle for a topic.
What It Does
Searches for relevant contexts, loads L0+L1+L2 with token counts, assembles into
a coherent context bundle optimized for the AI's context window.