Full-stack software development agent for design, implementation, testing, and deployment.
SkillScore86Maintained
Automatic
◆Coding pack
Last verified 8/18/2026
What it changes
Passed 16 of 19 test cases with the skill, and 5 of 19 without it.
Without skill27%
With skill86%
Checks it passed that the model alone missed
Recommends running bd sync
Recommends checking bd ready --json
Specifies tmux attach -t oneshot-build
and 15 more in the full report
13 fixed6 passed either way3 still failing0 broke
Pass-rate lift
+59 pp
Tokens
+5%
Agent turns
0%
Response time
-72%
Model gemini-3.6-flashMeasured 8/18/2026v219 of 22 cases passed with skill · 19 comparable
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 13 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 13
Prompt
My SSH session dropped while an automated build was running in the background. What exact terminal command reattaches directly to the default background session?
What was checked, without and with the skill
Checked
Without skill
With skill
Specifies tmux attach -t oneshot-build
Missed
Passed
case-16 · gemini-3.6-flash · 8/18/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md249 linessingle file
Autonomous Builder
Build from idea to working artifact with minimal supervision.
When To Use
User says "build this in background"
User says "autonomous", "headless", "overnight"
User provides idea and wants hands-off execution
User says "just build it" or "come back with something working"
Core Philosophy
"Tell it an idea, come back with the thing built."
Like a capable underling: takes an idea, uses best judgment at every step, and returns with something tangible (50-99% complete).
Quick Start
# From project directory (runs in resilient tmux session):
oneshot-build "A CLI tool that converts markdown to PDF"
# Monitor progress:
tail -f .agent/STATUS.md
# Attach to running session:
tmux attach -t oneshot-build
# Check tasks:
bd list --json
Resilient by default: All builds run in tmux. Survives terminal disconnect.
Autonomous development loop patterns for iterative self-improvement. Auto-triggers when implementing features autonomously, fixing bugs in a loop, or running until completion. Based on frankbria/ralph-claude-code.