Source profileQuality 85/100

dcc-mcp/dcc-mcp-core/python/dcc_mcp_core/skills/dcc-diagnostics/SKILL.md

dcc-diagnostics

Infrastructure skill — DCC-agnostic observability primitives: generate error reports, capture screenshots, query audit logs, inspect tool performance metrics, and monitor process health. Works in any DCC environment (Maya, Blender, Houdini, Unreal, etc.) or standalone Python. Call dcc_diagnostics__error_report first whenever a tool fails with a vague error message. Not for primary task execution — use a domain skill for actual DCC operations.

Source repository stars
39
Declared platforms
0
Static risk flags
0
Last source update
2026-08-04
Source checked
2026-08-04
DecisionCompatibilityInstallWorkflowPermissionsEvidenceSource

Decision brief

What it does—and where it fits

Cross-DCC observability and debugging tools powered by dcc-mcp-core.

Best for

    Not for

    • Tasks that require unconfirmed production actions or broad system permissions.
    • Environments where the pinned source and install steps cannot be inspected.

    Compatibility matrix

    Platform support, with evidence labels

    PlatformStatusEvidenceWhat to check
    CodexNot declaredNo explicit evidencePortability before use
    Claude CodeNot declaredNo explicit evidencePortability before use
    CursorNot declaredNo explicit evidencePortability before use
    Gemini CLINot declaredNo explicit evidencePortability before use
    Open the compatibility checker

    Installation

    Inspect first. Install second.

    The source command is displayed only when detected. A safe inspection prompt is always available so your agent can explain every action before execution.

    Source-detected install commandSource
    npx skills add https://github.com/dcc-mcp/dcc-mcp-core --skill "python/dcc_mcp_core/skills/dcc-diagnostics"
    Safe inspection promptEditorial

    Inspect the Agent Skill "dcc-diagnostics" from https://github.com/dcc-mcp/dcc-mcp-core/blob/874c7b52c12587529827990c497d2c8292e5d875/python/dcc_mcp_core/skills/dcc-diagnostics/SKILL.md at commit 874c7b52c12587529827990c497d2c8292e5d875. List every install step, command, network request, credential, file read/write, external action, and rollback step. Explain whether it fits my task. Do not install or execute anything until I approve.

    Workflow

    What the source asks the agent to do

    1. 01

      Recommended debugging workflow

      When a DCC tool fails with a vague error, call tools in this order:

      When a DCC tool fails with a vague error, call tools in this order:
    2. 02

      Usage with any DCC MCP server

      os.environ["DCCMCPSKILLPATHS"] = "/path/to/dcc-diagnostics"

      os.environ["DCCMCPSKILLPATHS"] = "/path/to/dcc-diagnostics"from dccmcpmaya import startserver or dccmcpblender, etc.handle = startserver(port=8765)
    3. 03

      Tools

      Start here when any tool fails. Collects a single-response diagnostic bundle:

      Log tail: last N lines of dcc-mcp-..log, extracting ERROR/WARNING linesFailed jobs: recent failed/interrupted entries from the SQLite job-persistence DBProcess snapshot: PID, platform, Python version, active DCCMCP env vars
    4. 04

      dccdiagnosticserrorreport

      Start here when any tool fails. Collects a single-response diagnostic bundle:

      Log tail: last N lines of dcc-mcp-..log, extracting ERROR/WARNING linesFailed jobs: recent failed/interrupted entries from the SQLite job-persistence DBProcess snapshot: PID, platform, Python version, active DCCMCP env vars

    Permission review

    Static risk signals and limitations

    No configured static risk pattern was detected

    This is not proof of safety. Runtime behavior, indirect dependencies, and hidden external systems are outside the static scan.

    Evidence record

    Why each signal appears

    EvidenceSourceComputedTestedEditorial
    SignalValueEvidence typeMeaning
    Quality score85/100ComputedDocumentation, specificity, maintenance, and trust rules
    Repository stars39SourceRepository attention, not individual Skill quality
    Compatibility0 platformsSourceDeclared in the catalog source record
    Usage guideautomated source guideEditorialGenerated or reviewed according to the visible evidence level

    Pinned source

    Provenance and original SKILL.md

    Repository
    dcc-mcp/dcc-mcp-core
    Skill path
    python/dcc_mcp_core/skills/dcc-diagnostics/SKILL.md
    Commit
    874c7b52c12587529827990c497d2c8292e5d875
    License
    MIT
    Collected
    2026-08-04
    Default branch
    main
    View the original SKILL.md

    DCC Diagnostics

    Cross-DCC observability and debugging tools powered by dcc-mcp-core.

    All tools work in any DCC environment (Maya, Blender, Houdini, Unreal, 3ds Max) or standalone Python — no DCC-specific APIs required.

    Recommended debugging workflow

    When a DCC tool fails with a vague error, call tools in this order:

    1. dcc_diagnostics__error_report   ← start here: log lines + failed jobs + env
2. dcc_diagnostics__audit_log      ← sandbox-level denials and recent invocations
3. dcc_diagnostics__tool_metrics   ← identify consistently slow or failing tools
4. dcc_diagnostics__screenshot     ← capture current visual state for confirmation
5. dcc_diagnostics__process_status ← check if the DCC process is still alive

    Tools

    dcc_diagnostics__error_report

    Start here when any tool fails. Collects a single-response diagnostic bundle:

    • Log tail: last N lines of dcc-mcp-<dcc>.*.log, extracting ERROR/WARNING lines
    • Failed jobs: recent failed/interrupted entries from the SQLite job-persistence DB
    • Process snapshot: PID, platform, Python version, active DCC_MCP_* env vars
    • Diagnosis hints: actionable text explaining what is wrong and how to fix it

    Requires DccServerBase(enable_file_logging=True, enable_job_persistence=True). Both are on by default since dcc-mcp-core v0.14.6.

    dcc_diagnostics__screenshot

    Capture the current screen or a specific window as a PNG/JPEG image. Backed by the dcc_mcp_core.Capturer class which uses:

    • Windows display: DXGI Desktop Duplication API
    • Windows window: Windows.Graphics.Capture with bounded GDI fallback
    • Linux: X11 XShmGetImage
    • Fallback: Mock synthetic backend (headless/CI)

    Successful DCC-window results include window_handle, window_title, capture_backend, fallback_from, and capture_health. Treat capture_health=unverified as pixels without semantic content validation and degraded as a backend fallback. unusable_capture and desktop_unavailable are structured failures; do not retry them through another desktop or input path.

    dcc_diagnostics__audit_log

    Query the sandbox audit log from dcc_mcp_core.SandboxContext. Returns recent tool invocations with outcome (success/denied) and timestamps.

    dcc_diagnostics__tool_metrics

    Inspect per-tool performance counters from dcc_mcp_core.ToolRecorder: invocation count, success rate, average latency, P95/P99 percentiles.

    dcc_diagnostics__process_status

    Check process health via dcc_mcp_core.PyProcessMonitor. Lists tracked PIDs and their liveness status.

    Usage with any DCC MCP server

    import os

os.environ["DCC_MCP_SKILL_PATHS"] = "/path/to/dcc-diagnostics"

from dcc_mcp_maya import start_server  # or dcc_mcp_blender, etc.

handle = start_server(port=8765)
# dcc_diagnostics__error_report and all other tools are now available

    Alternatives

    Compare before choosing

    Computed 9832,606

    K-Dense-AI/scientific-agent-skills

    dask

    Distributed computing for larger-than-RAM pandas/NumPy workflows. Use when you need to scale existing pandas/NumPy code beyond memory or across clusters. Best for parallel file processing, distributed ML, integration with existing pandas code. For out-of-core analytics on single machine use vaex; for in-memory speed use polars.

    2026-08-030 platforms
    Computed 9832,606

    K-Dense-AI/scientific-agent-skills

    medchem

    Medicinal chemistry filters for compound triage. Apply drug-likeness rules (Lipinski, Veber, CNS), structural alert catalogs (PAINS, NIBR, ChEMBL), complexity metrics, and the medchem query language for library filtering.

    2026-08-030 platforms
    Computed 9832,606

    K-Dense-AI/scientific-agent-skills

    neurokit2

    Use NeuroKit2 to build or audit reproducible research workflows for physiological time-series preprocessing, event/interval analysis, multimodal alignment, variability, and complexity. Trigger when code imports neurokit2 or needs its current APIs, schemas, and method-aware validation—not for diagnosis or device validation.

    2026-08-030 platforms
    Computed 98249

    majiayu000/spellbook

    comprehensive-testing

    Complete testing strategy covering TDD workflow, test pyramid, unit/integration/E2E/property testing, framework best practices (Jest, Vitest, pytest), mock strategies, and CI integration. Use when writing tests, reviewing test quality, or establishing testing standards.

    2026-08-020 platforms