{"slug":"self-improving-agent-pipeline","title":"self-improving-agent-pipeline","description":"A pipeline of skills that implements two feedback loops for Claude Code. The inner loop (plan-interview, intent-framed-agent, context-surfing, verify-gate, simplify-and-harden) catches failures during a session — verifying against tests, detecting scope and context drift, and reviewing code before signaling done. The outer loop (learning-aggregator, harness-updater, eval-creator, pre-flight-check) captures learnings, promotes recurring patterns into CLAUDE.md as permanent rules, and turns failures into regression tests. The harness gets stronger with every cycle.","developer":"Peter Skøtt Pedersen","category":null,"reported_installs":null,"active":true,"first_seen_at":"2026-10-03T22:13:33.942Z","last_seen_at":"2026-11-12T00:07:47.335Z","last_changed_at":"2026-10-03T22:13:33.942Z","platform":"claude","sources":["Community"],"works_with":["Claude Code"],"marketplace_url":null,"repository_url":"https://github.com/pskoett/pskoett-ai-skills.git","web_data":{},"github_data":{},"catalog_sources":{"community":[{"name":"self-improving-agent-pipeline","source":{"ref":"main","sha":"20e64cec1529d9c371fdcc20c751b7ef10b68af7","url":"https://github.com/pskoett/pskoett-ai-skills.git","path":"plugin","source":"git-subdir"},"homepage":"https://github.com/pskoett/pskoett-ai-skills","description":"A pipeline of skills that implements two feedback loops for Claude Code. The inner loop (plan-interview, intent-framed-agent, context-surfing, verify-gate, simplify-and-harden) catches failures during a session — verifying against tests, detecting scope and context drift, and reviewing code before signaling done. The outer loop (learning-aggregator, harness-updater, eval-creator, pre-flight-check) captures learnings, promotes recurring patterns into CLAUDE.md as permanent rules, and turns failures into regression tests. The harness gets stronger with every cycle."}]},"manifest":{"url":"https://raw.githubusercontent.com/pskoett/pskoett-ai-skills/20e64cec1529d9c371fdcc20c751b7ef10b68af7/plugin/.claude-plugin/plugin.json","payload":{"name":"pskoett-ai-skills","author":{"url":"https://github.com/pskoett","name":"Peter Skøtt Pedersen"},"license":"MIT","version":"2.3.0","keywords":["skill-pipeline","two-loop","verify-gate","self-healing","learning-aggregator","eval-creator","pre-flight-check","context-management","control-session","multi-agent","self-improvement","code-quality","security","agent-teams"],"repository":"https://github.com/pskoett/pskoett-skills","description":"Two-loop skill pipeline for Claude Code. Inner loop (plan-interview, intent-framed-agent, context-surfing, verify-gate, self-healing, simplify-and-harden) catches failures in-session — including active runtime recovery via self-healing when a command, test, build, helper, env, or external service fails mid-task. Outer loop (learning-aggregator, harness-updater, eval-creator, pre-flight-check) captures recurring patterns, promotes them to CLAUDE.md as permanent rules, and turns failures into regression tests."},"observed_at":"2026-11-06T10:48:52Z"}}