From dodi-dev
Use when executing an implementation plan — dispatches subagent per task with self-review, verification along the way, and commits
How this skill is triggered — by the user, by Claude, or both
Slash command
/dodi-dev:implementThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Execute a plan by dispatching a fresh subagent per task. Each subagent implements, tests, self-reviews, and commits. No heavy review gates per task — the full review happens after all tasks complete (see `dodi-dev:review`).
Execute a plan by dispatching a fresh subagent per task. Each subagent implements, tests, self-reviews, and commits. No heavy review gates per task — the full review happens after all tasks complete (see dodi-dev:review).
dodi-dev:reviewNever dispatch multiple implementers in parallel — they'll conflict.
| Status | Action |
|---|---|
| DONE | Mark complete, next task |
| DONE_WITH_CONCERNS | Read concerns. If correctness issue, address first. If observation, note and proceed |
| NEEDS_CONTEXT | Provide missing context, re-dispatch |
| BLOCKED | Assess: provide more context, use more capable model, break task smaller, or escalate to human |
Never ignore an escalation or retry without changes.
After each subagent completes, verify its claims before moving on:
git diff or git log to confirm changes were actually madenpx claudepluginhub dodi-hq/dodi-skills --plugin dodi-devExecutes implementation plans by dispatching fresh subagents per task with two-stage review (spec compliance then code quality). Use when you have a written plan with independent tasks.
Executes implementation plans in current session by dispatching fresh subagents per independent task, with two-stage reviews: spec compliance then code quality.
Executes implementation plans by dispatching fresh subagents for independent tasks in the current session, with two-stage reviews: spec compliance then code quality.