@pskoett

intent-framed-agent captures explicit intent at the planning-to-execution boundary, monitors for scope drift during coding work via structured checkpoints, and closes sessions with resolution records. designed for non-trivial implementation tasks only.

agent-teams-simplify-and-harden runs parallel audit loops over implementation, cycling simplify and harden passes until code stabilizes or iteration limit hits. audit findings drive remediation in repeating cycles.

plan-interview is a stub skill with installation instructions and a philosophy statement. no actionable interview planning logic, inputs, outputs, or decision framework are defined.

dx-data-navigator exposes a postgresql database query interface for analyzing developer experience metrics. the skill description mentions use cases but the actual skill definition is incomplete and lacks procedural depth.

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude…

self-improvement — an installable skill for AI agents, published by pskoett/pskoett-ai-skills.

CI-only Simplify & Harden workflow for pull requests using gh-aw (GitHub Agentic Workflows). Runs headless scan-and-report checks for simplify/harden/document,…

Post-completion self-review for coding agents that runs simplify, harden, and micro-documentation passes on non-trivial code changes. Use when: a coding task…

CI-only self-improvement workflow using gh-aw (GitHub Agentic Workflows). Captures recurring failure patterns and quality signals from pull request checks,…