Verify IGGDA gate signal clears
Run checks until all three completeness conditions hold and the terminal gate emits its clear signal.
/goal clear on condition met | IGGDA's terminal gate (REQ-IGGDA-028) emits the equivalent clear signal when all 3 completeness conditions hold. |
claude-code
More testing loops
Trim what loads before first paint
Reduce the data downloaded before the first screen appears, with tests and screenshots guarding behavior and appearance.
Reduce the data [web app] downloads before its first screen appears. First record passing tests, mobile and desktop screenshots, and compressed transferred bytes—the data actually downloaded. Use the build report only to suggest candidates. Defer, compress, or remove one item, then rebuild and rerun every check. Keep it only if tests pass, screenshots are pixel-identical, and bytes decrease; otherwise revert. Stop when no safe candidate remains, progress stalls, or approval is needed. Return measurements, changes, and untested states.
testingmedium risk
# GitHub Workflows Documentation This directory contains GitHub…
Community ralph loop for testing, sourced from github. Verified exit condition, evaluator-gated.
# GitHub Workflows Documentation This directory contains GitHub Actions workflows that provide AI-powered development assistance for this repository. Each workflow offers different capabilities to help with code review, testing, and architecture planning. ## Available Workflows - [Claude PR Review](#claude-pr-review) - Documentation-only PR updates using Claude AI - [Cursor Verify](#cursor-verify) - Cursor Cloud GPT-5.1 agent review plus regression tests triggered via comments - [Jules Spec & Plan](#jules-spec--plan) - Architecture planning and specification generation using Google's Jules AI --- ## Claude PR Review Workflow File: .github/workflows/claude review.yml ### Overview This workflow uses Anthropic's Claude AI to automatically review pull requests for documentation accuracy. Claude now focuses solely on keeping written assets aligned with the latest code changes while deferring bug fixes and security work to Cursor. ### Features - Automatic PR Documentation Pass : Runs when non-draft PRs are opened, updated, reopened, or marked ready for review - Draft PR Handling : Automatic reviews are skipped for draft PRs to avoid premature feedback -
testingmedium risk
--- name: slot-machine description: Use when a well-specified…
Community ralph loop for testing, sourced from github. Verified exit condition, evaluator-gated.
--- name: slot-machine description: Use when a well-specified task has meaningful design choices and you want to maximize quality by comparing multiple independent attempts. Works for coding, writing, and custom task types. Triggers on "slot-machine", "best-of-N", "pull the lever", "parallel implementations", or when quality matters more than speed and the spec is clear enough for independent work. --- # Slot Machine Best-of-N parallel implementation for any task type. Run N independent attempts at the same spec in parallel. Review each. Pick the best — or synthesize the best elements into a single winner. Core principle: LLMs are probabilistic. More attempts = better outcomes. Trade compute for quality. Announce at start: "I'm using the slot-machine skill ({profile name} profile) to run N parallel implementations." ## What This Is NOT Standard multi-agent patterns split DIFFERENT tasks across agents (frontend, backend, tests in parallel). Every major tool does this — it's table stakes. Slot-machine gives the SAME spec to N agents and compares their FULL attempts. The value isn't parallelism — it's competition and selection. Each slot is an independent attem
testingmedium risk