Showing 24 of 152 skills
A prompt-only coding agent loop that systematically identifies and resolves technical debt items in a codebase through iterative auditing and targeted fixes.
An automated loop for generating comprehensive, up-to-date system architecture documentation. This agent analyzes your codebase, identifies key architectural…
Validates and clarifies feature requirements before implementation begins, ensuring alignment between stakeholders and developers.
This loop helps generate a structured release roadmap by iteratively gathering project details, defining milestones, and refining the timeline through contin…
Automatically optimizes application code to meet predefined performance budgets. Uses performance audits to measure key metrics like load time, First Content…
Monitors and stabilizes scheduled jobs by automatically detecting failures, analyzing causes, and applying corrective measures. The agent iterates through jo…
No interval — Claude self-paces and ends the loop itself once 5 green runs in a row is provably met.
Run lint and typecheck, fix reported issues, and loop until the codebase is clean.
Run your test suite, fix the smallest root cause on failure, and repeat until every test passes.
Rebase or merge target branch, resolve conflicts file by file, and loop until the branch is current and tests pass.
This loop standardizes API error responses across the application to improve client-side error handling and debugging. It ensures all error responses follow…
Run the formatter, fix any remaining style issues, and loop until the codebase formats cleanly with no diffs.
This loop iteratively identifies and adds missing monitoring coverage to your codebase by analyzing test coverage, identifying gaps, and implementing targete…
Implement on a branch, run tests, push, open a PR, wait for CI, and loop until checks pass and the PR is ready to merge.
When implementation claims done, a separate verifier pass runs build, lint, and tests with no access to the implementer's rationale.
Hook that runs tests before git commit commands to block commits when the suite is red.
After code changes, find affected docs and update README, API references, and inline comments to match.
This loop automates the process of identifying and remediating security vulnerabilities in project dependencies. It continuously scans for outdated or vulner…
Run failing tests repeatedly, classify each failure as flaky or real, and fix only confirmed regressions.
Fix high/critical npm audit findings one at a time with test verification — not a blind npm audit fix --force.
Hook-based loop that runs related tests after file edits to catch regressions early.
Run automated accessibility checks on changed routes, fix violations, and repeat until the audit is clean.
When a check fails twice the same way, append a guardrail sign to .ralph/guardrails.md so the next iteration avoids repeating it.
Find and remove dead exports, unused files, and orphan dependencies — loop until knip reports clean.