subagent-driven-development
Use when executing implementation plans with independent tasks in the current session
Install with Tessl CLI
npx tessl i github:projectbluefin/dakota --skill subagent-driven-developmentOverall
score
61%
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillEvaluation — 99%
↑ 1.34xAgent success when using this skill
Validation for skill structure
Evaluation results
100%
45%Execute a Three-Task Implementation Plan
Orchestrating a multi-task implementation plan with correct review ordering and task tracking
Extract all tasks and create TodoWrite upfront
100%
100%
Fresh subagent per task
100%
100%
Spec compliance review before code quality review
0%
100%
Final code reviewer after all tasks
0%
100%
Mark tasks complete in TodoWrite
100%
100%
100%
20%Write Subagent Dispatch Prompts
Constructing spec reviewer and implementer subagent prompts with correct patterns
Full task text in implementer prompt
100%
100%
Context or scene-setting in implementer prompt
100%
100%
Spec reviewer distrust instruction
100%
100%
Spec reviewer checks for missing AND extra work
50%
100%
Implementer asked to self-review before reporting
0%
100%
100%
65%Execute a Five-Task Plan with Independent Tasks
Sequential task execution with no parallel implementation subagents
One implementer at a time
0%
100%
Full review cycle before next task
50%
100%
Fresh subagent for each task
100%
100%
Final review after all tasks
0%
100%
95%
-5%Dispatch Code Quality Reviewer for a Completed Task
Constructing code quality reviewer dispatch with correct prerequisites and inputs
Spec compliance passes before code quality dispatch
100%
83%
Git SHA references included
100%
100%
Implementation description and requirements included
100%
100%
Fix loop for quality issues
100%
100%
100%
Handle Review Failures in Subagent Workflow
Handling review failures with correct fix-and-re-review loop
Implementer fixes spec reviewer issues
100%
100%
Spec re-review after fix
100%
100%
Code quality review only after spec passes
100%
100%
Task not marked complete with open issues
100%
100%
- Evaluated
- Agent
- Claude Code
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.