/sync
Pull the latest guidelines from every configured repo (read- and write-scope).
$ npx -y skills add AgentToolkit/altk-evolve --skill sync --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.
- You can call itInvoke it directly when you want it.
- Slash command
/sync
Context preview
The summary Claude sees to decide when to auto-load this skill.
Pull the latest guidelines from every configured repo (read- and write-scope).
SKILL.md
sync.SKILL.mdname: sync description: Pull the latest guidelines from every configured repo (read- and write-scope).
Sync Repos
Overview
Pull the latest guidelines from every repo in `evolve.config.yaml` `repos:` list — both `scope: read` (subscribe-only) and `scope: write` (publish targets). Write-scope repos use a rebase strategy so any unpushed local publish commits are preserved.
Workflow
Step 1: Run sync script
python3 ${CLAUDE_PLUGIN_ROOT}/skills/evolve-lite/sync/scripts/sync.pyStep 2: Display summary
Show the script output to the user. If there are no repos configured, tell them they can add one with `/evolve-lite:subscribe`. If there are no changes, explain that everything is already up to date.
Notes
- Read-scope repos are mirrored exactly via `git fetch` + `git reset --hard`
- Write-scope repos use `git fetch` + `git rebase` so unpushed local
publish commits are preserved
- Sync results are logged to `.evolve/audit.log`
Blog posts: IBM announcement | Hugging Face blog 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
Other skills on altk-evolve.
- /agent-wiki-consolidate-guidelines
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 `superseded_by:` backref.
Open skill - /agent-wiki-consult
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.
Open skill - /agent-wiki-extract-guidelines
Read a normalized Claude Code trajectory JSON and extract reusable guidelines into wiki-twobatch/guidelines/. Use when mining saved trajectories for reusable lessons.
Open skill - /agent-wiki-ingest
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, consolidate into clusters, and catalog. Use when you have a batch of traces to turn into a wiki in one pass.
Open skill - /agent-wiki-summarize
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.
Open skill - /agent-wiki-synthesize-skill
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.
Open skill