Print Failure Analyst

Diagnose 3D print failures from symptoms or images, recommend slicer setting fixes, and log or analyze recurring print problems.

Security Scan

The skill is internally consistent with its stated purpose: it diagnoses print failures from text symptoms, recommends slicer fixes, and keeps a local failure log; it has no network access or secret requirements and writes a local JSON log.

Purpose & Capability

Name/description match the included code and references. The scripts implement symptom-based diagnosis, logging, history/pattern detection, and markdown reports. Required capabilities (none) are proportional to the stated purpose.

Instruction Scope

SKILL.md instructs the agent to 'analyze the image' when a user provides an image, but none of the bundled scripts perform image analysis — diagnosis scripts accept textual symptoms/descriptions only. This is a mild mismatch: image-based diagnosis is possible only if the agent (or another tool) interprets the image and converts visual findings into symptom keywords before calling diagnose.py.

Install Mechanism

No install spec is provided (instruction-only + included Python scripts). All scripts declare they use only the Python stdlib. No external downloads, package installs, or archive extraction are present.

Credentials

The skill requests no environment variables, no credentials, and no config paths other than its own assets/failure-log.json. That local log file is the only persistent data it reads/writes — proportional to the logging/reporting purpose.

Persistence & Privilege

always is false and the skill does not require persistent platform-level privileges. It writes a local JSON log at assets/failure-log.json within the skill directory and does not modify other skills or system-wide settings.

Assessment

This skill appears to be what it claims: text-based diagnosis, slicer-setting recommendations, and a local failure log. Before installing/using it: (1) note that it will create and update assets/failure-log.json inside the skill directory — back up or review that file if you care about its contents; (2) it does not perform image analysis itself — if you expect automatic image-to-diagnosis, your agent must convert images into symptom keywords before invoking the scripts; (3) no network calls or secrets are requested, but review the included Python files if you want to confirm there's no unexpected behavior; (4) ensure you run the scripts in a trusted environment with Python available and that you are comfortable allowing the skill to write a local JSON file.

Diagnose failures, recommend slicer fixes, and track a personal failure log.

References

• references/failure-types.md — 18 failure types with keywords, causes, visual symptoms
• references/slicer-fixes.md — Specific values for PrusaSlicer, Cura, OrcaSlicer per failure type

Read these when formulating diagnoses or recommending fixes. Do not recite them wholesale — extract relevant sections.

Scripts

All scripts use Python stdlib only. Log stored at assets/failure-log.json.

diagnose.py — Identify failure mode from symptoms

python3 scripts/diagnose.py --symptoms "stringing,warping"
python3 scripts/diagnose.py --description "hair between parts and corners lifting"
python3 scripts/diagnose.py --symptoms "stringing" --description "worse at layer transitions" --json

Outputs: ranked failure types with confidence, causes, and slicer-specific fixes. Use --json when you need structured output to reason over.

log_failure.py — Record a print failure

python3 scripts/log_failure.py \
  --printer "Prusa MK4" \
  --material "PETG" \
  --failure-type "stringing" \
  --description "Heavy stringing between towers" \
  --slicer-settings '{"temperature": 235, "retraction_distance_mm": 1.0}' \
  --fixed-by "Reduced temp to 230C, enabled wipe" \
  --notes "Filament may be wet"

Valid --failure-type values: stringing, warping, layer_adhesion, under_extrusion, over_extrusion, elephant_foot, layer_shifting, bridging, overhang, clog, pillowing, ringing, z_banding, seam, supports, first_layer, wet_filament, spaghetti, other

history.py — View failure history and patterns

python3 scripts/history.py                          # All failures
python3 scripts/history.py --last 10               # Last 10
python3 scripts/history.py --material PETG         # Filter by material
python3 scripts/history.py --printer "Prusa MK4"  # Filter by printer
python3 scripts/history.py --failure-type stringing
python3 scripts/history.py --patterns              # Pattern analysis only

report.py — Generate markdown report

python3 scripts/report.py                  # Print to stdout
python3 scripts/report.py --output r.md   # Save to file
python3 scripts/report.py --days 30       # Last 30 days only

Workflow

User describes a failure

1. Run diagnose.py --symptoms or --description with the user's input
2. Read references/failure-types.md for the top match to get full context
3. Read references/slicer-fixes.md for that failure type to get specific values
4. Present: most likely failure type, top 2–3 causes, and slicer fixes (ask which slicer if unknown)
5. Offer to log the failure with log_failure.py

User provides an image

1. Analyze the image to identify visual symptoms (stringing, warping, layer gaps, etc.)
2. Map observed symptoms to failure type keywords from references/failure-types.md
3. Run diagnose.py --symptoms "<observed symptoms>" for structured output
4. Present diagnosis with causes and fixes

User asks to log a failure

• Collect: printer, material, failure type, description. Ask for missing required fields.
• Optional: slicer settings used, what fixed it, notes
• Run log_failure.py with collected info

User asks for history or patterns

• Run history.py with appropriate filters
• Highlight any patterns flagged (recurring type+material combos, worst printer/material)

User asks for a report

• Run report.py, optionally with --days if user wants a time-bounded view
• Present the markdown output or save it and tell user where it is