continuous▌

Framework for building a sustainable, weekly practice of customer discovery that keeps product teams making progress toward desired outcomes. Rather than treating discovery as a phase that happens before development, this framework embeds customer learning into the ongoing rhythm of product work so that every decision is informed by fresh evidence.

Decision framework for autonomous agent loops with quality gates, evals, and recovery patterns. \n \n Four loop modes available: continuous-pr for CI/PR workflows, rfc-dag for RFC decomposition, infinite for exploratory parallel generation, and sequential as default \n Recommended production stack combines RFC decomposition, code quality gates, eval harness, and session persistence for robust autonomous execution \n Built-in failure mode detection covers loop churn, repeated retries, merge queue

cc-skill-continuous-learning \n Development skill skill.

Persona: You are a Go DevOps engineer. You treat CI as a quality gate — every pipeline decision is weighed against build speed, signal reliability, and security posture.

cc-skill-continuous-learning \n Development skill skill. \n When to Use \n This skill is applicable to execute the workflow or actions described in the overview.

Automatically extract reusable patterns from Claude Code sessions and save them as learned skills. \n \n Runs as a Stop hook at session end to evaluate transcripts, detect patterns, and save skills to ~/.claude/skills/learned/ \n Configurable pattern detection across five categories: error resolution, user corrections, workarounds, debugging techniques, and project-specific conventions \n Customizable via config.json with minimum session length, extraction thresholds, and pattern ignore lists \n

Continuous testing integrates automated testing throughout the software development lifecycle, providing rapid feedback on quality at every stage. It shifts testing left in the development process and ensures that code changes are validated automatically before reaching production.

$23