grade-tcg-card
Über
Diese Fähigkeit bewertet Sammelkarten (Pokémon, MTG, etc.) nach PSA-, BGS- oder CGC-Standards durch eine strukturierte Beurteilung von Zentrierung, Oberfläche, Kanten und Ecken. Sie liefert eine Endnote mit einem Konfidenzintervall, nützlich für die Vorabprüfung von Einsendungen, die Beilegung von Zustandsstreitigkeiten oder die Werteinschätzung. Entwickler können sie für automatisierte Kartenbewertungs-Workflows integrieren.
Schnellinstallation
Claude Code
Empfohlennpx skills add pjt222/agent-almanac -a claude-code/plugin add https://github.com/pjt222/agent-almanacgit clone https://github.com/pjt222/agent-almanac.git ~/.claude/skills/grade-tcg-cardKopieren Sie diesen Befehl und fügen Sie ihn in Claude Code ein, um diese Fähigkeit zu installieren
Dokumentation
Grade TCG Card
Assess and grade a trading card following professional grading standards (PSA, BGS, CGC). Uses an observation-first protocol adapted from the meditate skill to prevent grade anchoring — the most common grading bias.
When to Use
- Evaluating a card before submission to a professional grading service
- Pre-screening a collection to identify high-grade candidates worth submitting
- Settling disputes about card condition between buyers and sellers
- Learning to grade consistently by following a structured assessment protocol
- Estimating the grade-dependent value spread for a specific card
Inputs
- Required: Card identification (set, number, name, variant/edition)
- Required: Card images or physical description (front and back)
- Required: Grading standard to apply (PSA 1-10, BGS 1-10 with subgrades, CGC 1-10)
- Optional: Known market value at different grades (for grade-value analysis)
- Optional: Card game (Pokemon, Magic: The Gathering, Flesh and Blood, Kayou)
Procedure
Step 1: Clear Bias — Observation Without Prejudgment
Adapted from meditate Step 2-3: observe the card without anchoring to expected grade or market value.
- Set aside any knowledge of the card's market value
- Do NOT look up recent sales or population reports before grading
- If you know the card is "valuable," acknowledge that bias explicitly:
- "I know this card is worth $X in PSA 10. I am setting that aside."
- Examine the card as a physical object first, not as a collectible
- Note your initial gut impression but do NOT let it anchor the assessment
- Label any premature grade thoughts as "anchoring" and return to observation
Got: A neutral starting state where the card is assessed purely on physical condition, not market expectations. Grade anchoring (knowing the value before grading) is the #1 source of grading inconsistency.
If fail: If bias feels sticky (a high-value card makes you want to see a 10), write down the bias explicitly. Externalizing it reduces its influence. Proceed only when you can examine the card as a physical object.
Step 2: Centering Assessment
Measure the card's print centering on both faces.
- Measure the border width on all four sides of the front face:
- Left vs. right border (horizontal centering)
- Top vs. bottom border (vertical centering)
- Express as ratio: e.g., 55/45 left-right, 60/40 top-bottom
- Repeat for the back face
- Apply the grading standard's centering thresholds:
PSA Centering Thresholds:
+-------+-------------------+-------------------+
| Grade | Front (max) | Back (max) |
+-------+-------------------+-------------------+
| 10 | 55/45 or better | 75/25 or better |
| 9 | 60/40 or better | 90/10 or better |
| 8 | 65/35 or better | 90/10 or better |
| 7 | 70/30 or better | 90/10 or better |
+-------+-------------------+-------------------+
BGS Centering Subgrade:
+------+-------------------+-------------------+
| Sub | Front (max) | Back (max) |
+------+-------------------+-------------------+
| 10 | 50/50 perfect | 50/50 perfect |
| 9.5 | 55/45 or better | 60/40 or better |
| 9 | 60/40 or better | 65/35 or better |
| 8.5 | 65/35 or better | 70/30 or better |
+------+-------------------+-------------------+
- Record the centering score for each axis and the applicable subgrade
Got: Numeric centering ratios for both faces with the corresponding grade/subgrade identified. This is the most objective measurement in the grading process.
If fail: If borders are too narrow to measure accurately (full-art cards, borderless prints), note "centering N/A — borderless" and skip to Step 3. Some grading services apply different standards for borderless cards.
Step 3: Surface Analysis
Examine the card's surface for defects.
- Examine the front surface under good lighting:
- Print defects: ink spots, missing ink, print lines, color inconsistency
- Surface scratches: visible under direct and angled light
- Whitening on surface: haze or clouding of the surface layer
- Indentations or impressions: dents visible under raking light
- Staining or discoloration: yellowing, water marks, chemical damage
- Examine the back surface with the same criteria
- Check for factory defects vs. handling damage:
- Factory: print lines, miscut, crimping — may be less penalized
- Handling: scratches, dents, stains — always penalized
- Rate surface condition:
- Pristine (10): flawless under magnification
- Near-pristine (9-9.5): minor imperfections visible only under magnification
- Excellent (8-8.5): minor wear visible to naked eye
- Good (6-7): moderate wear, multiple minor defects
- Fair or below (1-5): significant damage visible
Got: A detailed surface inventory with each defect located, described, and severity-rated. Factory vs. handling defects distinguished.
If fail: If images are too low-resolution for surface analysis, note the limitation and provide a grade range rather than a point grade. Recommend physical inspection.
Step 4: Edge and Corner Evaluation
Assess the card's edges and corners for wear.
- Examine all four edges:
- Whitening: white spots or lines along colored edges (the most common defect)
- Chipping: small pieces of the edge layer missing
- Roughness: edge feels uneven or has micro-tears
- Foil separation: on holofoil cards, check for delamination at edges
- Examine all four corners:
- Sharpness: corner tip is crisp and pointed
- Rounding: corner tip is worn to a curve (slight, moderate, heavy)
- Splitting: layer separation visible at corner (dings)
- Bending: corner turned or creased
- Rate edge and corner condition using the same scale as surface
- Note which specific corners/edges have the worst condition
Got: Per-edge and per-corner condition assessment. The worst individual corner/edge typically limits the overall grade.
If fail: If the card is in a sleeve or toploader that obscures edges, note which areas couldn't be fully assessed.
Step 5: Assign Final Grade
Combine sub-assessments into the final grade.
- For PSA grading (single number 1-10):
- The final grade is limited by the weakest sub-assessment
- A card with perfect surface but 65/35 centering caps at PSA 8
- Apply the "lowest limits" principle, then adjust up if other areas are exceptional
- For BGS grading (four subgrades → overall):
- Assign subgrades: Centering, Edges, Corners, Surface (each 1-10 in 0.5 steps)
- Overall = weighted average, but the lowest subgrade limits the overall
- BGS 10 Pristine requires all four subgrades at 10
- BGS 9.5 Gem Mint requires average of 9.5+ with no subgrade below 9
- For CGC grading (similar to PSA with subgrades on label):
- Assign Centering, Surface, Edges, Corners
- Overall follows CGC's proprietary weighting
- State the final grade with confidence:
- "PSA 8 (confident)" — clear grade, unlikely to be higher or lower
- "PSA 8-9 (borderline)" — could go either way at the grading service
- "PSA 7-8 (uncertain)" — limited assessment data
Got: A final grade with confidence level. For BGS, all four subgrades reported. The grade is supported by evidence from Steps 2-4.
If fail: If the assessment is inconclusive (e.g., can't tell if a surface mark is a scratch or dirt), provide a grade range and recommend professional grading. Never assign a confident grade with insufficient data.
Validation
- Bias check completed before grading (no grade anchoring)
- Centering measured on both faces with ratios recorded
- Surface examined for scratches, print defects, staining, indentations
- All four edges and corners individually assessed
- Factory vs. handling defects distinguished
- Final grade supported by evidence from each sub-assessment
- Confidence level stated (confident, borderline, uncertain)
- Grading standard correctly applied (PSA/BGS/CGC thresholds)
Pitfalls
- Grade anchoring: Knowing a card's value before grading biases the assessment toward the "hoped-for" grade. Assess physically first
- Ignoring the back: The back surface and back centering count. Many graders over-focus on the front
- Confusing factory with handling defects: A factory print line is different from a scratch, but both affect the grade
- Over-grading holofoils: Holographic and foil cards hide surface scratches until viewed at the right angle. Use multiple light angles
- Centering optical illusions: Art placement can make centering appear better or worse than it is. Measure the borders, not the art
Related Skills
build-tcg-deck— Deck building where card condition affects tournament legalitymanage-tcg-collection— Collection management with grade-based valuationmeditate— Source of the observation-without-prejudgment technique adapted for grading bias prevention
GitHub Repository
Verwandte Skills
llamaguard
AndereLlamaGuard ist Metas 7-8B-Parameter-Modell zur Moderation von LLM-Eingaben und -Ausgaben in sechs Sicherheitskategorien wie Gewalt und Hassrede. Es bietet eine Genauigkeit von 94-95 % und kann mit vLLM, Hugging Face oder Amazon SageMaker eingesetzt werden. Nutzen Sie diese Skill, um Inhaltsfilterung und Sicherheitsguardrails einfach in Ihre KI-Anwendungen zu integrieren.
cost-optimization
AndereDiese Claude Skill unterstützt Entwickler bei der Optimierung von Cloud-Kosten durch Ressourcen-Dimensionierung, Tagging-Strategien und Ausgabenanalysen. Sie bietet einen Rahmen zur Senkung von Cloud-Ausgaben und zur Implementierung von Kosten-Governance für AWS, Azure und GCP. Nutzen Sie sie, wenn Sie Infrastrukturkosten analysieren, Ressourcen richtig dimensionieren oder Budgetvorgaben einhalten müssen.
quantizing-models-bitsandbytes
AndereDiese Fähigkeit quantisiert LLMs auf 8-Bit- oder 4-Bit-Präzision mittels bitsandbytes und erreicht dabei eine Speicherreduzierung von 50–75 % bei minimalem Genauigkeitsverlust. Sie ist ideal für den Betrieb größerer Modelle mit begrenztem GPU-Speicher oder zur Beschleunigung von Inferenzvorgängen und unterstützt Formate wie INT8, NF4 und FP4. Die Fähigkeit integriert sich in HuggingFace Transformers und ermöglicht QLoRA-Training sowie 8-Bit-Optimierer.
dispatching-parallel-agents
AndereDiese Claude-Fähigkeit verteilt mehrere Agenten, um drei oder mehr unabhängige Probleme gleichzeitig zu untersuchen und zu beheben. Sie ist für Szenarien konzipiert, die unabhängige Fehler umfassen, die ohne gemeinsamen Zustand oder Abhängigkeiten gelöst werden können. Die Kernfähigkeit ist die parallele Problemlösung, bei der pro unabhängigem Problembereich ein Agent zugewiesen wird, um die Effizienz zu maximieren.
