Menu
Use image-scoring MCP tools to debug scoring failures, check database health, and investigate system issues. Trigger when the user asks to debug scoring, investigate failure, or check database health.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
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 | mcp-debugging-workflow |
| description | Use image-scoring MCP tools to debug scoring failures, check database health, and investigate system issues. Trigger when the user asks to debug scoring, investigate failure, or check database health. |
Apply this skill when the user asks to:
On is-be-mcp: search("scoring failures") → dispatch("diagnostics.get_error_summary", {}).
dispatch("diagnostics.check_database_health", {})
dispatch("jobs.get_failed_images", {"limit": 50})
dispatch("diagnostics.get_model_status", {})
On is-be-mcp: dispatch("jobs.get_runner_status", {}) and/or dispatch("jobs.get_recent_jobs", {}). If search finds no matching action, use optional is-be-live with MCP_SSE_PROFILE=full for legacy raw tools.
dispatch("logs.read_debug_log", {"lines": 100}) or dispatch("logs.search_logs", {"pattern": "error|failed"})
is-be-mcp → search / dispatchis-be-live (same compact tools when WebUI is running)execute_code / full legacy raw tools: is-be-live + MCP_SSE_PROFILE=full + ENABLE_MCP_EXECUTE_CODE=1 when neededAlign with product UI: pipeline stages are Discovery → Inspection → Quality Analysis → Similarity Clustering → Tagging; DB uses phase_code; REST uses scoring / tagging / clustering. See docs/technical/PIPELINE_TERMINOLOGY.md.