From T.L-AutoDevelop
Prepare AutoDevelop for a new session by reconciling scheduler state and cleaning safe AutoDevelop-owned leftovers.
How this skill is triggered — by the user, by Claude, or both
Slash command
/T.L-AutoDevelop:develop-prepareThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
CRITICAL: You are the Main-Claude orchestrator. You do not implement repository code changes yourself.
CRITICAL: You are the Main-Claude orchestrator. You do not implement repository code changes yourself.
Your job is to:
prepare-environment modeAllowed tools: Read, Glob, Grep, Bash.
Do not edit repository files directly in this skill. Do not register tasks. Do not start workers. Do not prepare or resolve merges.
Use one Bash call to verify:
git rev-parse --is-inside-work-tree returns trueIf it fails, stop and explain the problem.
Find *.sln and *.slnx in the current directory and up to two parent directories.
From this point on, always work with the absolute solution path.
Find scheduler.ps1 from the installed plugin.
Call:
powershell.exe -NoProfile -ExecutionPolicy Bypass -File "<scheduler.ps1>" -Mode prepare-environment -SolutionPath "<solution>"
Read the returned JSON and report:
statussummaryqueueProgressSummaryqueueStallcircuitBreakerWhen you need a queue snapshot outside of prepare-environment, prefer snapshot-queue -View Compact for routine reads and only use the full view for deep debugging.
Interpretation:
status == "ready": report that AutoDevelop is readystatus == "cleaned": report what was cleaned and that AutoDevelop is now readystatus == "warning": report the warnings, but explain that AutoDevelop can still continuestatus == "blocked": stop and explain exactly what is blocking a safe session startDo not continue into queue planning or worker launch from this command.
npx claudepluginhub tleiott/t.l-marketplace4cctoolz --plugin T.L-AutoDevelopInitializes Claude Code sessions by migrating legacy harness files to .claude-harness/, creating missing state files like memory rules and config, and preparing GitHub sync.
Guides creation, editing, and verification of skills for AI coding agents using test-driven development with subagent scenarios. Use when authoring or debugging skills.