Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →ganyuanran/subagent-driven-development
Use when executing implementation plans with independent tasks in the current session
Passed 12 of 17 test cases with the skill, and 9 of 17 without it.
and 3 more in the full report
6 fixed9 passed either way5 still failing2 broke
Tokens, turns and time describe resource use, not a dollar price.
This benchmark measured an earlier version of the skill.
A newer attempt on gemini-3.8-flash on 10/18/2026 did not produce a publishable comparison (not comparable). The snapshot above is the previously measured run.
One of 6 test cases the skill fixed. Same model, same prompt, with and without the skill.
The implementer subagent just reported DONE for task 2 (adding input validation). I want to quickly check code formatting and lint rules before checking whether it fulfilled all requirements in the spec. Is it acceptable to run the code quality review first to catch quick typos before spending time on spec compliance?
| Checked | Without skill | With skill |
|---|---|---|
| Enforces running spec compliance review before code quality review. | Missed | Passed |
The instructions your model reads when the skill loads.
→ Have an implementation plan with independent tasks? → Fresh subagent per task + two-stage review.
Execute plan by dispatching fresh subagent per task, with two-stage review after each: spec compliance review first, then code quality review.
Why subagents: You delegate tasks to specialized agents with isolated context. By precisely crafting their instructions and context, you ensure they stay focused and succeed at their task. They should never inherit your session's context or history — you construct exactly what they need. This also preserves your own context for coordination work.
Core principle: Fresh subagent per task + two-stage review (spec then quality) = high quality, fast iteration
Use when you have a written implementation plan with mostly independent tasks and want to stay in the current session. For cross-session execution, use executing-plans instead.
Before the first repo write, the coordinating agent records
TaskStartSnapshot. Same-task agents share the current workspace. The
coordinator is the only default Git mutation owner for staging, commits,
branches, and worktrees; implementers and reviewers edit/verify/report but do
not mutate Git lifecycle state. Task complexity, TDD, planning, subagents, or a
main/master name does not justify isolation by itself.
test cases passed, vs 9 / 17 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.