featbit

Makes product or AI changes reversible before they are visible, and defines who sees the change, how much traffic, and how expansion will be controlled. Activate when triggered by CF-03 or CF-04 from the release-decision framework, or when user says "feature…

Evaluates collected data to determine if evidence is sufficient to decide, then frames the outcome as CONTINUE, PAUSE, ROLLBACK CANDIDATE, or INCONCLUSIVE. Activate when triggered by CF-06 or CF-07 from the release-decision framework, or when user says…

Creates and manages experiments as database-backed records — the unified replacement for an online A/B test dashboard. Activate when user is ready to start collecting data for a hypothesis, wants to set up an experiment, needs to pull or organize experiment…

FeatBit release decision philosophy and control framework. Activate when the user is anywhere in the loop from intent to implementation to feedback to next iteration and needs the right decision lens, not a fixed workflow. Triggers — "release decision", "what…

Converts a clear business goal into a falsifiable hypothesis before implementation begins. Activate when triggered by CF-02 from the release-decision framework, or when a goal exists but there is no explicit causal claim linking a change to an expected…

Extracts the real business outcome when the user has a vague direction or jumps to tactics before the goal is clear. Activate when triggered by CF-01 from the release-decision framework, or when user says "I want to improve X", "we should add Y", "increase…

Captures structured learnings at the end of an experiment or release cycle so the next iteration starts from evidence rather than memory. Activate when triggered by CF-08 from the release-decision framework, or when user says "what did we learn", "close this…

Defines the primary success metric, guardrails, and event instrumentation for a hypothesis before exposure begins. Activate when triggered by CF-05 from the release-decision framework, or when user asks "how do I measure this", "what metrics should I use",…

Convert a manual QA test script into automated test code that follows the repository's existing testing patterns, frameworks, and conventions. Use when the user provides (or points to) a manual test script (e.g., CP-01, CP-02) and wants it turned into…

Review automated test code generated from a manual QA test script, verifying every manual step is covered, assertions are sound, and the code will actually work. Use when the user has generated test code (e.g., from qa-test-automator) and wants a structured…

End-to-end FeatBit experimentation workflow with Bayesian A/B/n analysis. Use when shaping product intent, writing a hypothesis, defining feature flags and rollout strategy, designing metrics and instrumentation, creating or analyzing experiment runs,…

Routes FeatBit engineering questions to current official sources. Use for integrating any FeatBit SDK or OpenFeature provider; managing FeatBit resources with Terraform; deploying, upgrading, maintaining, or observing FeatBit with Docker Compose, Kubernetes…

Guides creating new FeatBit releases with chart updates, version bumps, image updates, and migration handling. Use when user asks to create FeatBit release, bump FeatBit version, update chart version, or prepare new FeatBit deployment.

Provides step-by-step guidance for integrating feature flags into FeatBit MCP Server tools and code paths. Use when user asks about "add feature flag", "gate a tool", "control tool release", "McpToolFlagGate", "IFeatureFlagEvaluator", "ReleaseEnabled", "hide…

Expert guidance for creating VSCode Copilot custom instructions, prompt files, and AGENTS.md files. Use when user wants to create, modify, or understand .github/copilot-instructions.md, .instructions.md, AGENTS.md, or .prompt.md files. Includes YAML…

FeatBit Skill for Feature Flag Management and Evaluation. (1) CRUD operations on feature flags. (2) Evaluate flags for users.