agenttoolkit/altk-evolve
30 skills
$npx skills add agenttoolkit/altk-evolveSkillInstalls
adapt-memoryMirror a just-saved native memory into the shared evolve store so it becomes shareable and auditableagent-wiki-consolidate-guidelinesRead all atomic guidelines in wiki-twobatch/guidelines/ and propose themed clusters that group near-duplicates.agent-wiki-consultConsult an agent-wiki for guidelines relevant to the task at hand. The wiki itself documents how to retrieve from it (AGENTS.md).agent-wiki-extract-guidelinesRead a normalized Claude Code trajectory JSON and extract reusable guidelines into wiki-twobatch/guidelines/.agent-wiki-ingestIngest one or more agent trajectories (raw bob/claude traces or normalized JSON) into an agent-wiki end-to-end — convert, summarize, extract guidelines,…agent-wiki-summarizeRead a normalized Claude Code trajectory JSON and write an episodic summary page to wiki-twobatch/summaries/.agent-wiki-synthesize-skillRead a normalized Claude Code trajectory JSON and produce a wiki-resident SKILL.md page that future agents can invoke.agent-wiki-tasksDiscover task families across summaries and write per-family comparison pages with findings narrative.doctorDiagnose evolve health on Claude — verify the CLAUDE.md @import is actually loading the thin EVOLVE.md into sessionsevolve-lite-adapt-memoryMirror a just-saved native memory into the shared evolve store so it becomes shareable and auditableevolve-lite-provenanceAnalyze saved trajectories and recall audit events offline to record whether recalled guidelines influenced completed sessions.evolve-lite-publishPublish a private guideline to a configured write-scope repo.evolve-lite-retentionApply data-retention rules to the local evolve store — flag or delete stale and unused memories and expired sessions (dry-run by default)evolve-lite-saveCaptures the current session's successful workflow and saves it as a reusable skill with SKILL.md and helper scriptsevolve-lite-save-trajectorySave the current conversation as a trajectory JSON file in OpenAI chat completion format for analysis and fine-tuningevolve-lite-subscribeAdd a shared guidelines repo (read-scope subscription or write-scope publish target) to the unified repos list.evolve-lite-syncPull the latest guidelines from every configured repo (read- and write-scope).evolve-lite-synthesize-skillConvert a saved trajectory into a reusable agent skill (SKILL.md + supporting scripts) that future agents can invoke to skip rediscovered work.evolve-lite-unsubscribeRemove a repo from the unified repos list and delete its local clone.learnMust be used near the end of any non-trivial turn that produced potentially reusable tools, guidance, errors, workarounds, or workflows, so those lessons are…provenanceAnalyze saved trajectories and recall audit events offline to record whether recalled guidelines influenced completed sessions.publishPublish a private guideline to a configured write-scope repo.recallMust be used at the start of any non-trivial task involving code changes, debugging, repo exploration, file inspection, or environment/tooling investigation to…retentionApply data-retention rules to the local evolve store — flag or delete stale and unused memories and expired sessions (dry-run by default)saveCaptures the current session's successful workflow and saves it as a reusable skill with SKILL.md and helper scriptssave-trajectorySave the current conversation as a trajectory JSON file in OpenAI chat completion format for analysis and fine-tuningsubscribeAdd a shared guidelines repo (read-scope subscription or write-scope publish target) to the unified repos list.syncPull the latest guidelines from every configured repo (read- and write-scope).synthesize-skillConvert a saved trajectory into a reusable agent skill (SKILL.md + supporting scripts) that future agents can invoke to skip rediscovered work.unsubscribeRemove a repo from the unified repos list and delete its local clone.