agent-wiki-compare-out…
Compare successful and failed normalized agent trajectories to derive evidence-backed agent-wiki guidelines. Use when Codex has multiple runs for the same or…
Remove a repo from the unified repos list and delete its local clone.
$ npx -y skills add AgentToolkit/altk-evolve --skill evolve-lite-unsubscribe --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/evolve-lite-unsubscribeContext preview
The summary Claude sees to decide when to auto-load this skill.
Remove a repo from the unified repos list and delete its local clone.
name: evolve-lite:unsubscribe description: Remove a repo from the unified repos list and delete its local clone.
Remove a configured repo (any scope) from `evolve.config.yaml` and delete its local clone at `.evolve/entities/subscribed/{name}/`. Warn the user before removing a write-scope repo since any unpushed local publish commits will be lost.
Run:
python3 .bob/skills/evolve-lite-unsubscribe/scripts/unsubscribe.py --list
Show the repos to the user (including `scope` and `notes`) and ask which one to remove.
Confirm deletion of `.evolve/entities/subscribed/{name}/`. If the repo has `scope: write`, add a warning that unpushed local publish commits will be lost.
python3 .bob/skills/evolve-lite-unsubscribe/scripts/unsubscribe.py --name {name}Tell the user the repo was removed.
the recall mirror)
Coding agents repeat the same mistakes because they start fresh every session. Evolve gives agents memory — they learn from what worked and what didn't, so each session is better than the last.
Repo: AgentToolkit/altk-evolve
Compare successful and failed normalized agent trajectories to derive evidence-backed agent-wiki guidelines. Use when Codex has multiple runs for the same or…
Read all atomic guidelines in wiki-twobatch/guidelines/ and propose themed clusters that group near-duplicates. Writes cluster pages and updates _config.yaml;…
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…
Read a normalized Claude Code trajectory JSON and extract reusable guidelines into wiki-twobatch/guidelines/. Use when mining saved trajectories for reusable…
Ingest one or more agent trajectories (raw bob/claude traces or normalized JSON) into an agent-wiki end-to-end — convert, summarize, extract guidelines,…
Read a normalized Claude Code trajectory JSON and write an episodic summary page to wiki-twobatch/summaries/. Use when summarizing one or more saved…