Menü
Use Graphify knowledge-graph MCP (graphify-be) or CLI for architecture / cross-module connectivity. Prefer after rg/fff fail for “how does X connect to Y”; never for pipeline/DB triage (use is-be-mcp).
Mit Codex oder Claude installieren Kopieren Sie diesen Prompt, fügen Sie ihn in Codex, Claude oder einen anderen Assistant ein und lassen Sie die Skill-Seite prüfen und installieren.
Bump semver + promote CHANGELOG Unreleased via compiled harness. Use for /release, version bumps, or tagging. Runs scripts/agent_skills/release_bump.py; LLM only when Unreleased is ambiguous. Never commit/push unless the user asks.
Vexlum Scoring MCP — compact search+dispatch on is-be-mcp / is-be-live and gallery is-ui-mcp / is-ui-live.
Choose CLI tools and safe patterns before repo work. Install checklist, bounded search/read commands, and confirmation gates. Use when navigating the codebase, running shell commands, or setting up agent tooling on Windows, WSL2, or macOS.
Inspect JSON, YAML, and API responses with jq, yq, dasel, curl, and httpie. Use for package.json, config.json, and backend health checks. Never output secrets or full credential-bearing config.
Backend build, test, lint, and verify workflows via WSL pytest, ruff, doctor, and docker compose. Use before claiming work complete or opening a PR. Do not invent ad hoc Python commands outside documented venvs.
Choose and run the right search tool: rg vs grep vs ast-grep vs fd vs fzf. Bounded repo navigation with ripgrep, fd, tree, bat, and structural search. Use when finding symbols, files, syntax patterns, or deciding which CLI search to use before reading or editing code.
| name | graphify |
| description | Use Graphify knowledge-graph MCP (graphify-be) or CLI for architecture / cross-module connectivity. Prefer after rg/fff fail for “how does X connect to Y”; never for pipeline/DB triage (use is-be-mcp). |
Local AST knowledge graph — no vector store. Soft rule: .cursor/rules/graphify.mdc (alwaysApply: false).
graphify-out/graph.json exists (build: graphify . --code-only)graphify-be is connected (or fall back to CLI)| Need | Use instead |
|---|---|
| Scoring / DB / job failures | image-scoring-mcp (is-be-mcp) |
| Literal string / filename | agent-search / fff-be |
| Graph missing | graphify . --code-only then retry; do not invent edges |
uv tool install "graphifyy[mcp]" (CLI + graphify-mcp)graphify . --code-only → graphify-out/ (gitignored).cursor/mcp.json (from mcp.example.json):"graphify-be": {
"command": "graphify-mcp",
"args": ["graphify-out/graph.json"],
"cwd": "${workspaceFolder:image-scoring-backend}"
}
graphify-be)| Tool | Args | Use for |
|---|---|---|
graph_stats | (none) | Sanity check — node/edge/community counts |
query_graph | question (req); mode bfs|dfs; depth 1–6; token_budget | Natural-language / keyword subgraph |
get_node | label | One symbol / file node |
get_neighbors | label; optional relation_filter | Direct edges |
get_community | community_id | Subsystem cluster |
god_nodes | optional top_n | Highest-degree hubs |
shortest_path | source, target; optional max_hops | Path between two concepts |
list_prs / get_pr_impact / triage_prs | GitHub PR impact (needs gh / network) | PR blast radius — skip unless user asks |
All tools accept optional project_path (absolute dir with graphify-out/graph.json).
graph_stats() # confirm graph loaded
query_graph({question: "how does ScoringRunner relate to PhaseCode"})
get_node({label: "ScoringRunner"}) # if you have a name
shortest_path({source: "ScoringRunner", target: "create_api_router"})
If MCP is unavailable, CLI equivalents:
graphify query "how does ScoringRunner relate to PhaseCode"
graphify explain "ScoringRunner"
graphify path "ScoringRunner" "create_api_router"
depth 2–3 and default token_budget; raise budget or narrow question if truncated.context_filter: ["call"] (or similar) when the question is about call edges only.secrets.json / thumbnails (see .graphifyignore).graphify cursor install (alwaysApply / hooks) — soft rule only.| Symptom | Fix |
|---|---|
| MCP server missing in Cursor | Reload MCP; confirm .cursor/mcp.json has graphify-be and graphify-out/graph.json exists |
no LLM API key on build | Use graphify . --code-only |
| Stale graph after big refactors | Re-run graphify . --code-only then graphify cluster-only . |
ModuleNotFoundError: graphify with plain python | Use graphify-mcp / uv-tool Python, not ~/.venvs/tf |