From evolving-lite
Auto-activates on session start or 'continue'/'resume' to read memory JSON for active project progress/next steps/failures, orient Claude, announce status, suggest one task.
npx claudepluginhub primeline-ai/evolving-liteThis skill uses the workspace's default tool permissions.
On every session start, perform this bootup sequence:
Compares coding agents like Claude Code and Aider on custom YAML-defined codebase tasks using git worktrees, measuring pass rate, cost, time, and consistency.
Designs and optimizes AI agent action spaces, tool definitions, observation formats, error recovery, and context for higher task completion rates.
Designs, implements, and audits WCAG 2.2 AA accessible UIs for Web (ARIA/HTML5), iOS (SwiftUI traits), and Android (Compose semantics). Audits code for compliance gaps.
On every session start, perform this bootup sequence:
Read ${CLAUDE_PLUGIN_ROOT}/_memory/index.json for:
active_project: Which project the user was working onlast_session: When the last session wasIf active_project is set, read ${CLAUDE_PLUGIN_ROOT}/_memory/projects/{active_project}.json for:
progress: Array of recent progress entriesnext_step: What was planned nextfailures: Known blockers or failuresBased on memory:
Output a compact status line:
Evolving Lite | Session {n} | Tier {tier} | {experience_count} experiences
Last: {last_progress_summary}
Next: {next_step}
If this is the first session ever (no progress), announce:
Evolving Lite v1.0 | First session | {prewarmed_count} pre-warmed experiences loaded
Ready to work. The system learns from your corrections automatically.
If the user hasn't specified what to work on, suggest the next_step from memory. Don't start multiple tasks - pick one.
When the user says "continue", "weiter", "weitermachen", "fortsetzen", or "resume":
${CLAUDE_PLUGIN_ROOT}/_memory/sessions/When a session ends naturally (user says goodbye, or Stop hook fires):