Loading...
Loading...
Found 3 Skills
Benchmark CodeGraph retrieval quality on a real codebase by comparing agent behavior with vs without CodeGraph. Use when the user runs /agent-eval or asks to test, benchmark, audit, or validate a codegraph version (the local dev build or a published npm version) against a language's repo.
Add tree-sitter language support to codegraph end-to-end — wire the grammar + extractor, write tests, then benchmark extraction quality and retrieval value on 3 popular real-world repos. Use when the user runs /add-lang <language> or asks to add/support a new language (e.g. Lua, Elixir, Zig, OCaml) in codegraph.
Sets up and drives TencentDB Agent Memory (MemoryCore + MemoryHub + MemoryProxy + MemoryPanel, from AnEntrypoint/agent-memory) -- a persistent, cross-session memory and knowledge system for AI agents. Chat Memory (L0 conversation -> L1 atom -> L2 scenario -> L3 persona), a versioned Skill library extracted from past work, a Wiki + CodeGraph knowledge map over docs and code, and a human-controlled review panel. Use when the user wants an agent team to share and accumulate memory/skills/knowledge across sessions and across multiple agent frameworks (not just this one Claude Code session), when they mention "memory hub", "team memory", "chat memory", "skill library", "wiki", "codegraph", or ask to install/configure/troubleshoot the memory-tencentdb plugin, or when onboarding a new agent into an existing team's accumulated experience. As of gm's tencentdb_backend addition, this system's format can ALSO be gm's own memorize/recall/memorize-fire/memorize-prune backend for an opted-in namespace (see gm.config.json's memory.tencentdb_backend) -- when that's enabled, the verb surface an agent already knows is unchanged; only the storage target moves. Use this skill for the standalone deployment (Docker Compose, panel UI, team review) or when gm's own backend is not what's being asked about.