To partition large workspaces (100+ files) into scoped subagent tasks when context is insufficient.
SkillScore78Maintained
Automatic
◆AI Engineer pack
Last verified 8/27/2026
What it changes
Passed 16 of 21 test cases with the skill, and 9 of 21 without it.
Without skill43%
With skill78%
Checks it passed that the model alone missed
Selects the Summarize & Index strategy.
Schedules an extra pass to resolve shared-interface changes.
Selects the Summarize & Index strategy as the default tie-breaker.
and 7 more in the full report
10 fixed8 passed either way3 still failing2 broke
Pass-rate lift
+35 pp
Tokens
-22%
Agent turns
0%
Response time
-56%
Model gemini-3.6-flashMeasured 8/27/2026v318 of 23 cases passed with skill · 21 comparable
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 10 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 10
Prompt
When inspecting an existing repository map file during scope planning, what action should be taken first to view the high-level sections without reading the entire file?
What was checked, without and with the skill
Checked
Without skill
With skill
Greps for section headers starting with hash symbols inside CODEMAP.md before drawing scope boundaries.
Missed
Passed
case-05 · 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.md61 linessingle file
<large_workspace_handling>
Workspace partitioning strategist. Draws scope boundaries, dispatches subagents.
<when_to_use_skill>
Large workspaces exceeding single-agent context window. Partitions into write-scopes where every file belongs to exactly one scope, and merged results address the original request completely.
</when_to_use_skill>
<core_concepts>
All Rosetta prep steps MUST be FULLY completed, load-project-context skill loaded and fully executed
If CODEMAP.md missing, RECOMMEND USER TO USE FLOW init-workspace-flow.md to initialize repository (CODEMAP.md is missing)
Grep # headers of CODEMAP before scoping
Two strategies (mutually exclusive):
Summarize & Index
Work distribution
Summarization & Indexing
Research without changing code, navigable index with module summaries, etc.
Assign subagents: scope paths, goal, context, inputs, output format, boundaries, constraints, and level of detail
Subagents to USE SKILL reverse-engineering if needed for code analysis
Request slightly more information than actually needed for better understanding
Summarize all outputs
Subagent: discoverer, explore, etc.
Subagent output structure: analysis scope, TLDR answer, quick navigation with relevance, details with subsections per each logical group (globs, purpose, key components, relevant findings, dependencies), cross-group map, follow ups required
Subagents to use relevance classification:
High: group directly addresses the research question
Medium: group has supporting information or context
Low: group tangentially related, included for completeness
Work distribution
Coordinated modifications via contract-scoped parallel subagents with explicit boundaries and success criteria
Split work across subagents and provide: scope paths, goal, context, inputs, output format, boundaries, constraints, operations, and success criteria
Subagents decide and execute work within declared scope