adversarial-review
CommandAdversarial, reproduce-by-execution review of a GitHub PR (fan-out sub-agents, verify, draft review)
Convert a saved trajectory into a reusable agent skill (SKILL.md + supporting scripts) that future agents can invoke to skip rediscovered work. Use when a session captured a non-trivial workflow worth promoting from a free-text guideline to an executable skill.
> /plugin marketplace add AgentToolkit/altk-evolve> /plugin install evolve-lite@evolve-marketplace
description: Convert a saved trajectory into a reusable agent skill (SKILL.md + supporting scripts) that future agents can invoke to skip rediscovered work. Use when a session captured a non-trivial workflow worth promoting from a free-text guideline to an executable skill.
Use the `evolve-lite-synthesize-skill` skill on the current conversation. Follow the skill's instructions exactly.
Evolve helps AI agents learn from experience. It turns past trajectories into reusable guidelines that help agents complete future tasks, without changing model weights.
Adversarial, reproduce-by-execution review of a GitHub PR (fan-out sub-agents, verify, draft review)
Mirror a just-saved native memory into the shared evolve store so it becomes shareable and auditable
Analyze saved trajectories and recall audit events offline to record whether recalled guidelines influenced completed sessions.
Publish a private entity (guideline, feedback, project or reference) to a configured write-scope repo.
Apply data-retention rules to the local evolve store — flag or delete stale and unused memories and expired sessions (dry-run by…
Save the current conversation as a trajectory JSON file in OpenAI chat completion format for analysis and fine-tuning
Implement tasks incrementally — build, test, verify, commit. Add "auto" to run the whole plan in one approved pass.