iterate Skill
Use this skill when the user asks Claude to autonomously test, fix, review, and merge a change end-to-end. Detects which lane(s) changed (frontend / backend / framework / agentspec), spawns relevant verifiers (agentic-test-loop with --require-oracle for false-green prevention; backend-verify for contracts/types/unit/se Published by microsoft in MCS-Agent-Builder.
What is iterate Skill?
Use this skill when the user asks Claude to autonomously test, fix, review, and merge a change end-to-end. Detects which lane(s) changed (frontend / backend / framework / agentspec), spawns relevant verifiers (agentic-test-loop with --require-oracle for false-green prevention; backend-verify for contracts/types/unit/se Published by microsoft in MCS-Agent-Builder. This profile combines repository metadata with install, compatibility, and usage signals so developers can quickly decide whether it fits their agent workflow before opening the source repository.
Automated repository signals based on public metadata such as recency, license, installation evidence, and adoption. These are not a security audit or endorsement.
Key capabilities
- Includes SKILL.md support
- Reusable instructions support
- Testing
- Testing use cases
Technical details
- Install or run with Copy skill directory
When to use iterate Skill
- Use it for testing.
Built with
Editorial notes
Source
- Creator: microsoft
- Repository: microsoft/MCS-Agent-Builder
- Skill file: .claude/skills/iterate/SKILL.md
What it does
Use this skill when the user asks Claude to autonomously test, fix, review, and merge a change end-to-end. Detects which lane(s) changed (frontend / backend / framework / agentspec), spawns relevant verifiers (agentic-test-loop with --require-oracle for false-green prevention; backend-verify for contracts/types/unit/se
Skill instructions
/iterate — Autonomous Test-Fix-Review-Merge Orchestrator (Layer A) Single entry point for fully-autonomous iteration on a change. The skill runs as a long-running single-turn loop: Claude detects the lane(s) involved, dispatches verifiers in parallel, fixes failures in-place, reruns until green, runs an independent facilitator review, runs multi-model-review.js review-merged as the third oracle, and auto-merges if everything passes denylist + score thresholds. When to fire - User typed /iterate. - User said "iterate", "make it work", "fix and ship", "test and verify", "iterate to green". - Claude just completed any non-trivial implementation in Layer A (frontend, backend, hooks, tools, framework). Fire automatically before announcing the work is done. - The Stop hook surfaced a paused/escalated /iterate session — resume with --resume <session-id. When NOT to fire - Inside /mcs- skills — they have their own build/eval/fix loop. For autonomous MCS iteration, use /mcs-iterate. - The user
Explore related resources
Frequently asked questions
What is iterate?
iterate is a open-source AI agent skill with Copy skill directory. Use this skill when the user asks Claude to autonomously test, fix, review, and merge a change end-to-end.
Who is iterate best for?
iterate is best for reusing agent instructions, scripts, and references, testing workflows.
How do I install iterate?
Install or run iterate using Copy skill directory. Check iterate for the latest setup command.
Is iterate actively maintained?
iterate may need a closer maintenance check before production use.
Auto-fetched from GitHub.
