Governs safe, incremental, repository-wide development workflow with continuous validation gates
51
56%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Passed
No findings from the security scan
Fix and improve this skill with Tessl
tessl review fix ./.claude/skills/autonomous-coding-workflow/SKILL.mdPerform repository-wide modifications safely, incrementally, and with continuous validation.
Before doing anything:
.github/copilot-instructions.mdAGENTS.md.junie/*.mdCLAUDE.mdIf they exist:
Before modifying code:
Do not modify code that has not been understood.
Apply only when relevant:
Work in small, verifiable steps.
After each change:
php -lvendor/bin/pint --dirty --format agentNever proceed if any of the following fail:
Before completion, additionally ensure:
After completing a module:
php -l.Do not start the next module until the current one is fully stable.
If behavior is unclear:
The task is complete only when:
fb83b36
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.