proven-app

Execute git commit with conventional commit message analysis, intelligent staging, and message generation. Use when user asks to commit changes or mentions "/commit".

Scaffold a new skill directory using the multi-YAML pattern. Use when user says /create-skill.

Write, run, and refine fast direct-mode tests for GenLayer intelligent contracts using the in-memory pytest fixtures.

Refresh documentation with deterministic generation from source files. Use when user says /docs-refresh.

Deploy, interact with, inspect, and debug GenLayer intelligent contracts with the GenLayer CLI across local Studio, hosted Studio, and testnet.

Install, upgrade, and monitor a GenLayer validator node on AMD64 Linux, including zero-downtime updates and LLM provider setup.

Lint, validate, schema-extract, and typecheck GenLayer intelligent contracts before tests or deployment.

Write and run GenLayer integration tests against GLSim, local Studio, hosted Studio, or testnet to validate full transaction flow and consensus behavior.

Create and manage Linear issues using templates for the GenLayer Heartbeat project. Use when user says /linear.

Creates GitHub pull requests with properly formatted titles that pass the check-pr-title CI validation. Use when creating PRs, submitting changes for review, or when user says /pr, /pr-create, or asks to create a pull request.

Merge GitHub pull requests with strict CI validation. Never bypasses failed checks. Use when merging PRs or when user says /pr-merge.

Manage GenLayer validators across testnets using the GenLayer CLI. Join, fund, set identity, list, and organize validators per network and owner.

Design, write, and harden GenLayer intelligent contracts, including equivalence-principle choice, validator logic, storage modeling, LLM error handling, and production-safe contract patterns.

Use when making small or medium Python edits and you want proportional cleanup while touching existing code. Focus on low-risk refactors, naming, comments, and dead code cleanup during existing work.

Use when cleaning up, reviewing, or rewriting Python comments and docstrings. Focus on removing stale or redundant comments and keeping the remaining ones accurate and useful.

Use when refactoring or reviewing Python functions for size, arguments, side effects, or single-responsibility problems. Focus on focused cleanup, not broad architectural rewrites.

Use when reviewing or refactoring Python code for duplication, obscured intent, magic numbers, abstraction problems, or avoidable conditionals. Keep the focus on core code-quality issues.

Use when renaming or reviewing Python variables, functions, classes, or modules for clarity. Focus on descriptive, unambiguous names during refactors and code review.

Use when improving or reviewing Python tests around an existing feature or bug. Focus on speed, boundary coverage, and clear test structure rather than test workflow orchestration.

Use when the user explicitly wants Python cleanup, refactoring, or clean-code review. Apply broad Python code-quality guidance without taking over domain-specific GenLayer design or testing workflows.