Loading...
Loading...
Found 19,288 Skills
A/B test agent variants measuring quality and total session token cost across simple and complex benchmarks. Use when creating compact agent versions, validating agent changes, comparing internal vs external agents, or deciding between variants for production. Use for "compare agents", "A/B test", "benchmark agents", or "test agent efficiency". Do NOT use for evaluating single agents, testing skills, or optimizing prompts without variant comparison.
Phase-gated git commit workflow with validation, staging, and CLAUDE.md compliance enforcement. Use when creating commits, staging changes, or when PR workflows need standardized commits. Triggers: "commit changes", "save work", "create commit", or internal skill invocation from PR workflows. Do NOT use for merge commits, rebases, amends, cherry-picks, or emergency rollbacks requiring raw git speed.
RED-GREEN-REFACTOR testing for agents: dispatch subagents with known inputs, capture verbatim outputs, verify against expectations. Use when creating, modifying, or validating agents and skills. Use for "test agent", "validate agent", "verify agent works", or pre-deployment checks. Do NOT use for feature requests, simple prompt edits without behavioral impact, or agents with no structured output to verify.
Run, monitor, resume, merge, and debug Ralph loops. Use this skill whenever the user asks to operate `ralph run` or `ralph loops`, inspect loop state, recover suspended loops, analyze diagnostics, or unblock merge queue issues.
CUE schema authoring for Perses plugins: define data models, write validation constraints, create JSON examples, implement Grafana migration schemas in migrate/migrate.cue. Educational skill that explains CUE patterns specific to Perses plugin development. Use for "perses cue schema", "perses model", "plugin schema", "cue validation perses". Do NOT use for dashboard CUE definitions (use perses-dac-pipeline).
This skill provides the 12 critical story questions for screenplay evaluation. Covers concept, theme, audience reaction, beginning, ending, rising tensions, characters, protagonist, motivation, antagonist, and believability. Use when: evaluating a screenplay draft, identifying story weaknesses, preparing for rewrites, or validating fundamentals before submission.
Agent skill for collective-intelligence-coordinator - invoke with $agent-collective-intelligence-coordinator
Agent skill for authentication - invoke with $agent-authentication
Agent skill for v3-performance-engineer - invoke with $agent-v3-performance-engineer
Agent skill for performance-analyzer - invoke with $agent-performance-analyzer
Agent skill for orchestrator-task - invoke with $agent-orchestrator-task
Use the `datadog` CLI to manage Datadog resources — monitors, metrics, events, logs, services, errors, and pipelines. Invoke this skill whenever the user asks to query, create, update, or delete Datadog monitors, search logs or errors, check metric values, list APM services, or manage log pipelines. Also trigger when the user mentions Datadog observability tasks like "check the error rate", "look at monitors", "search logs for errors", "list services", or "set up a log pipeline".