Self improving agents through iterations
This repository also configures its own agents. See what altk-evolve tells them →
Skill Claude CodeCodex needs its repo
Read all atomic guidelines in wiki-twobatch/guidelines/ and propose themed clusters that group near-duplicates. Writes cluster pages and updates config.yaml; originals are preserved with a supersededby: backref.
Skill Claude CodeCodex needs its repo
Consult an agent-wiki for guidelines relevant to the task at hand. The wiki itself documents how to retrieve from it (AGENTS.md). Use this skill once you know what task or sub-task you're about to do — not at session start.
Skill Claude CodeCodex needs its repo
Read a normalized Claude Code trajectory JSON and extract reusable guidelines into wiki-twobatch/guidelines/. Use when mining saved trajectories for reusable lessons.
Skill Claude CodeCodex needs its repo
Ingest one or more agent trajectories (raw bob/claude traces or normalized JSON) into an agent-wiki end-to-end — convert, summarize, extract guidelines, synthesize skills, optionally compare outcomes, consolidate into clusters, and catalog. Use when you have a batch of traces to turn into a wiki in one pass.
Skill Claude CodeCodex needs its repo
Read a normalized Claude Code trajectory JSON and write an episodic summary page to wiki-twobatch/summaries/. Use when summarizing one or more saved trajectories into the agent wiki.
Skill Claude CodeCodex needs its repo
Read a normalized Claude Code trajectory JSON and produce a wiki-resident SKILL.md page that future agents can invoke. Use when a trajectory captured a non-trivial successful workflow worth promoting from a free-text guideline to an executable, callable artifact.
Skill Claude CodeCodex needs its repo
Discover task families across summaries and write per-family comparison pages with findings narrative. Updates wiki-twobatch/config.yaml task definitions and writes tasks/ task.md.
Skill Claude CodeCodex
Mirror a just-saved native memory into the shared evolve store so it becomes shareable and auditable.
Skill Claude CodeCodex
Analyze saved trajectories and recall audit events offline to record whether recalled guidelines influenced completed sessions.
Skill Claude CodeCodex
Publish a private entity (guideline, feedback, project, user or reference) to a configured write-scope repo.
Skill Claude CodeCodex
Apply data-retention rules to the local evolve store — flag or delete stale and unused memories and expired sessions (dry-run by default).
Skill Claude CodeCodex
Save the current conversation as a trajectory JSON file in OpenAI chat completion format for analysis and fine-tuning.
Skill Claude CodeCodex
Add a shared guidelines repo (read-scope subscription or write-scope publish target) to the unified repos list.
Skill Claude CodeCodex
Pull the latest guidelines from every configured repo (read- and write-scope).
Skill Claude CodeCodex
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.
Skill Claude CodeCodex
Remove a repo from the unified repos list and delete its local clone.
Skill Claude CodeCodex
Must be used near the end of any non-trivial turn that produced potentially reusable tools, guidance, errors, workarounds, or workflows, so those lessons are saved for future turns.
Skill Claude Code
Must be used at the start of any non-trivial task involving code changes, debugging, repo exploration, file inspection, or environment/tooling investigation to surface stored guidance before analysis or tool use.
Skill Claude CodeCodex needs its repo
Compare successful and failed normalized agent trajectories to derive evidence-backed agent-wiki guidelines. Use when Codex has multiple runs for the same or similar task, evaluator outcomes, failed/successful variants, benchmark trajectories, or wants to learn rules from contrasts rather than from one trajectory…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: