From aidd-dev
Autonomous iterative loop that retries until a success condition is verified. Use for guaranteed task completion with explicit criteria.
How this skill is triggered — by the user, by Claude, or both
Slash command
/aidd-dev:09-for-sureThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Autonomous loop that runs until a success condition is verified. Two phases: interactive pre-flight (human present), then autonomous execution (human gone). The agent auto-accepts everything, acts as the user, and never stops until success.
Autonomous loop that runs until a success condition is verified. Two phases: interactive pre-flight (human present), then autonomous execution (human gone). The agent auto-accepts everything, acts as the user, and never stops until success.
success_condition verified by running a command. All steps/acceptance criteria checked. File renamed to .done.md./for-sure.plan-template.md (@assets/plan-template.md). Filename: aidd_docs/tasks/<task-name>.<status>.md.None - task secrets are validated during pre-flight and documented in the tracking file.
aidd_docs/tasks/<task-name>.<status>.md and nowhere else..done.md.@actions/01-init-tracking.md - Pre-flight, create tracking file, spawn first autonomous agent.@actions/02-auto-accept.md - Auto-accept mode activation (Phase 3).@actions/03-autonomous-loop.md - Orchestrator: spawns one worker per step, verifies, checks/retries, evaluates success.@actions/01-init-tracking.md
@actions/02-auto-accept.md
@actions/03-autonomous-loop.md
@assets/plan-template.md - tracking file format (frontmatter, phases, acceptance criteria, Log)npx claudepluginhub ai-driven-dev/frameworkDefines a goal with measurable success criteria and runs an autonomous plan-execute-validate loop until criteria are met or limits reached.
Executes tasks iteratively until completion with structured completion signals, stagnation detection, and dual-condition exit gates. Useful for autonomous multi-step workflows.
Auto-loop execution workflow with quality gates. Use when starting any non-trivial implementation task. Provides automatic task decomposition, code implementation, testing (L1-L4), and iterative quality gates until completion. Invoke with /autoworker.