Browse Skills

Relay 80 To 100 Workflow defines agent-relay processes that validate features end to end before merge. It is used for workflows that need repair loops, test-fix-rerun gates, and fresh-eyes review before commit.

Relay Workflows helps build multi-agent workflows with @relayflows/core using DAG steps, agent coordination, and output chaining. Use it for review/fix loops, verification gates, and chat-native or pipeline-style orchestration.

Review Fix Signoff Loop coordinates repeated review, fix, and validation cycles with fresh agent context until independent signoff agents both approve the result. It is used for high-stakes workflows that need deterministic gates, repair passes, and final signoff reporting.

Review Fix Signoff Loop defines a workflow for implementation tasks that must cycle through review, repair, validation, and fresh-context signoff until independent reviewers agree the work is complete. Use it for high-stakes agent workflows with repairable gates, dual-verdict contracts, and PR signoff reporting.

Align Human measures how well an automatic judge agrees with human labels, including TPR/TNR, kappa, AC1, and bias checks. Use it to validate a grader, find disagreement patterns, and decide how much human review can be reduced.

Auto Arena automatically generates test queries, collects responses, and runs pairwise judging to compare multiple models or agents on a custom task. Use it to benchmark endpoints, resume evaluations, add endpoints incrementally, or swap the judge model.

Bootstrap helps you create a first evaluation when you have no labels, no traces, and no criteria yet. It generates a v0 grader, synthetic test inputs, and a roadmap for collecting human labels and calibrating the evaluator.

Claude Authenticity checks whether an API endpoint is backed by genuine Claude using weighted rule-based signals. Use it to audit Claude API keys, third-party providers, and optionally extract an injected system prompt.

Eval Design helps create stratified evaluation datasets, adversarial test cases, and labeling guides from traces, specs, or interviews. It outputs OpenJudge-compatible datasets for GradingRunner.

Eval Report synthesizes evaluation runs into a maturity assessment, cross-skill signals, weaknesses, and prioritized actions. Use it for ship-readiness reviews, evaluation audits, and health checks of the eval system itself.

Find Skills Combo decomposes complex requests into subtasks and recommends combinations of agent skills. It is used when a task spans multiple domains or when you need a best-fit set of skills instead of one skill.

Meta Eval routes users to the right evaluation workflow for LLM and agent apps. It asks about data, labels, stakes, and domain knowledge, then recommends the next sub-skill to use.