altk-evolve
Gives coding agents a memory of past sessions so they stop repeating mistakes. It extracts guidelines from successful and failed agent trajectories and consults them for related tasks.
33 skills135
@agenttoolkit- 135Stars earned
- 1Plugin
- 33Skills
- 12Commands
Plugins
1@agenttoolkitSkills
33adapt-memory
Mirror a just-saved native memory into the shared evolve store so it becomes shareable and auditable
@agenttoolkitagent-wiki-compare-out…
Compare successful and failed normalized agent trajectories to derive evidence-backed agent-wiki guidelines. Use when Codex has…
@agenttoolkitagent-wiki-consolidate…
Read all atomic guidelines in wiki-twobatch/guidelines/ and propose themed clusters that group near-duplicates. Writes cluster…
@agenttoolkitagent-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).…
@agenttoolkitagent-wiki-extract-gui…
Read a normalized Claude Code trajectory JSON and extract reusable guidelines into wiki-twobatch/guidelines/. Use when mining…
@agenttoolkitagent-wiki-ingest
Ingest one or more agent trajectories (raw bob/claude traces or normalized JSON) into an agent-wiki end-to-end — convert,…
@agenttoolkitagent-wiki-summarize
Read a normalized Claude Code trajectory JSON and write an episodic summary page to wiki-twobatch/summaries/. Use when…
@agenttoolkitagent-wiki-synthesize-…
Read a normalized Claude Code trajectory JSON and produce a wiki-resident SKILL.md page that future agents can invoke. Use when a…
@agenttoolkitagent-wiki-tasks
Discover task families across summaries and write per-family comparison pages with findings narrative. Updates…
@agenttoolkitdoctor
Diagnose evolve health on Claude — verify the CLAUDE.md @import is actually loading the thin EVOLVE.md into sessions
@agenttoolkitevolve-lite-adapt-memo…
Mirror a just-saved native memory into the shared evolve store so it becomes shareable and auditable
@agenttoolkitevolve-lite-provenance
Analyze saved trajectories and recall audit events offline to record whether recalled guidelines influenced completed sessions.
@agenttoolkitCommands
12adversarial-review
CommandAdversarial, reproduce-by-execution review of a GitHub PR (fan-out sub-agents, verify, draft review)
@agenttoolkitevolve-lite-adapt-memo…
CommandMirror a just-saved native memory into the shared evolve store so it becomes shareable and auditable
@agenttoolkitevolve-lite-provenance
CommandAnalyze saved trajectories and recall audit events offline to record whether recalled guidelines influenced completed sessions.
@agenttoolkitevolve-lite-publish
CommandPublish a private entity (guideline, feedback, project or reference) to a configured write-scope repo.
@agenttoolkitevolve-lite-retention
CommandApply data-retention rules to the local evolve store — flag or delete stale and unused memories and expired sessions (dry-run by…
@agenttoolkitevolve-lite-save
CommandCaptures the current session's successful workflow and saves it as a reusable skill with SKILL.md and helper scripts
@agenttoolkitevolve-lite-save-traje…
CommandSave the current conversation as a trajectory JSON file in OpenAI chat completion format for analysis and fine-tuning
@agenttoolkitevolve-lite-subscribe
CommandAdd a shared guidelines repo (read-scope subscription or write-scope publish target) to the unified repos list.
@agenttoolkitevolve-lite-sync
CommandPull the latest guidelines from every configured repo (read- and write-scope).
@agenttoolkitevolve-lite-synthesize…
CommandConvert a saved trajectory into a reusable agent skill (SKILL.md + supporting scripts) that future agents can invoke to skip…
@agenttoolkitevolve-lite-unpublish
CommandRemove your published entity from a write-scope repository and restore a private copy.
@agenttoolkitevolve-lite-unsubscrib…
CommandRemove a repo from the unified repos list and delete its local clone.
@agenttoolkitIs this you? Claim your profilePut a plugin at the top of Plugins, from $9