identify-gemstone
About
This Claude Skill identifies gemstones by analyzing their optical properties, physical tests, and inclusions. It helps verify species, distinguish natural stones from simulants, and ensure safe handling of rough material. Key capabilities include testing refractive index, specific gravity, and spectroscopy indicators.
Quick Install
Claude Code
Recommendednpx 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/identify-gemstoneCopy and paste this command in Claude Code to install this skill
Documentation
Identify Gemstone
ID gemstones using systematic physical + optical property testing, inclusion analysis, elimination vs known species profiles.
When Use
- Unknown gemstone or suspect gemstone, want to ID species
- Verify seller's claim about gemstone identity
- Tell natural gemstone from common simulant or synthetic
- Build gemological literacy through structured observation + testing
- ID rough material before cutting for safe handling
Inputs
- Required: Gemstone specimen (loose stone preferred; mounted limit testing)
- Optional: Refractometer with contact liquid (RI fluid, 1.81 standard)
- Optional: Dichroscope (pleochroism testing)
- Optional: Chelsea colour filter
- Optional: Specific gravity balance or heavy liquids
- Optional: 10x loupe or gemological microscope
- Optional: UV lamp (long-wave 365nm + short-wave 254nm)
- Optional: Polariscope (optic character determination)
Steps
Step 1: Visual Inspection
Examine specimen with unaided eye then under 10x magnification.
Visual Inspection Checklist:
+--------------------+------------------------------------------+
| Observation | Record |
+--------------------+------------------------------------------+
| Colour | Hue (red, blue, green...), saturation |
| | (vivid, moderate, weak), tone |
| | (light, medium, dark) |
+--------------------+------------------------------------------+
| Transparency | Transparent, translucent, opaque |
+--------------------+------------------------------------------+
| Luster | Adamantine, vitreous, waxy, pearly, |
| | silky, resinous |
+--------------------+------------------------------------------+
| Cut style | Faceted, cabochon, carved, rough |
+--------------------+------------------------------------------+
| Estimated size | Approximate dimensions (mm) and weight |
+--------------------+------------------------------------------+
| Surface condition | Scratches, chips, abrasion, wear pattern |
+--------------------+------------------------------------------+
| Phenomena | Star (asterism), cat's eye |
| | (chatoyancy), play of colour, colour |
| | change, adularescence |
+--------------------+------------------------------------------+
- Note body colour under daylight-equivalent lighting (5500-6500K)
- Check colour zoning by viewing through stone from different angles
- Assess transparency + luster — narrows candidates immediate
- Look for optical phenomena (star, cat's eye, play of colour)
- Record any visible inclusions without magnification
Got: Complete visual profile — colour, transparency, luster, phenomena. Alone narrows candidates to manageable shortlist.
If fail: Lighting poor (yellowish indoor)? Note limitation. Daylight or daylight-equivalent bulbs strongly preferred. Incandescent shifts colour perception → misidentification of colour-change stones.
Step 2: Physical Property Testing
Test measurable physical properties to narrow ID.
Key Physical Properties:
+--------------------+------------------------------------------+
| Property | Method |
+--------------------+------------------------------------------+
| Hardness (Mohs) | Scratch test against reference minerals |
| | or hardness pencils. CAUTION: Do NOT |
| | scratch faceted gemstones — use other |
| | tests instead for cut stones |
+--------------------+------------------------------------------+
| Specific gravity | Hydrostatic weighing: |
| (SG) | SG = weight in air / (weight in air - |
| | weight in water) |
| | |
| | Common SG values: |
| | Quartz: 2.65 |
| | Beryl: 2.68-2.74 |
| | Tourmaline: 3.02-3.26 |
| | Topaz: 3.53 |
| | Corundum: 3.99-4.01 |
| | Zircon: 4.60-4.73 |
| | CZ: 5.65-5.95 |
+--------------------+------------------------------------------+
| Heft | Does the stone feel heavier or lighter |
| | than expected for its size? |
| | CZ and zircon feel noticeably heavy |
| | Quartz and glass feel average |
+--------------------+------------------------------------------+
- Rough material: test hardness using Mohs scale reference points
- Cut stones: measure specific gravity using hydrostatic method
- Assess heft — experienced handlers can tell CZ from diamond by weight alone
- Note any cleavage planes visible on surface
Got: Hardness range (rough) or SG value (cut stones) differentiates between candidate species. SG often most powerful single diagnostic for cut stones.
If fail: Hydrostatic balance unavailable? Use heft test as rough guide. Stones "too heavy for size" likely have high SG (>3.5). Hardness testing would damage cut stone? Skip to optical tests.
Step 3: Optical Tests
Apply gemological optical instruments for definitive properties.
Optical Property Tests:
+--------------------+------------------------------------------+
| Test | What It Reveals |
+--------------------+------------------------------------------+
| Refractive Index | Measured on refractometer with RI fluid |
| (RI) | Diagnostic for most species: |
| | Quartz: 1.544-1.553 |
| | Beryl: 1.577-1.583 |
| | Tourmaline: 1.624-1.644 |
| | Topaz: 1.609-1.617 |
| | Corundum: 1.762-1.770 |
| | Spinel: 1.718 |
| | Diamond: 2.417 (OTL on refractometer) |
| | CZ: 2.15 (OTL on refractometer) |
+--------------------+------------------------------------------+
| Birefringence | Difference between high and low RI |
| (BR) | Quartz: 0.009 |
| | Corundum: 0.008 |
| | Tourmaline: 0.018-0.020 |
| | Singly refractive: 0 (spinel, garnet, |
| | diamond) |
+--------------------+------------------------------------------+
| Pleochroism | Colour variation with crystal direction |
| (dichroscope) | Strong: tourmaline, tanzanite, iolite |
| | Moderate: corundum, topaz |
| | None: singly refractive stones |
+--------------------+------------------------------------------+
| Optic character | Singly refractive (SR), doubly |
| (polariscope) | refractive (DR), aggregate (AGG) |
+--------------------+------------------------------------------+
| UV fluorescence | Long-wave and short-wave UV response |
| | Diamond: often blue (LWUV) |
| | Ruby: strong red (LWUV) |
| | Emerald: usually inert |
+--------------------+------------------------------------------+
| Chelsea filter | Transmits deep red and yellow-green |
| | Emerald (Cr): appears red/pink |
| | Aquamarine: appears green |
| | Blue synthetic spinel: appears red |
+--------------------+------------------------------------------+
- Measure RI on refractometer — take both high + low readings for birefringence
- Test pleochroism with dichroscope — rotate slow + note colour changes
- Check optic character on polariscope (SR vs DR vs AGG)
- Test UV fluorescence under both long-wave + short-wave
- Use Chelsea filter if chromium-coloured stones suspected
Got: RI value (to 0.001), birefringence, optic character, pleochroism description, UV response. Combined with Step 2, IDs most gemstone species definitive.
If fail: RI over-the-limit (OTL, >1.81)? Stone likely diamond, CZ, zircon (high-type), or high-RI synthetic. Use SG + thermal conductivity to differentiate. No refractometer? Rely on SG + visual properties + inclusions.
Step 4: Inclusion Analysis
Examine internal features under magnification for species confirmation + natural vs synthetic determination.
Diagnostic Inclusions by Species:
+------------------+------------------------------------------+
| Species | Characteristic Inclusions |
+------------------+------------------------------------------+
| Diamond | Crystals (garnet, diopside), feathers, |
| | cloud, graining, pinpoints |
+------------------+------------------------------------------+
| Ruby/Sapphire | Silk (rutile needles), fingerprints, |
| | colour zoning (straight angular), |
| | crystal inclusions |
+------------------+------------------------------------------+
| Emerald | Three-phase inclusions (solid + liquid + |
| | gas), jardin (garden-like fractures), |
| | pyrite crystals |
+------------------+------------------------------------------+
| Tourmaline | Growth tubes, liquid-filled fractures |
+------------------+------------------------------------------+
| Quartz/Amethyst | Tiger stripes, phantoms, two-phase |
| | inclusions, negative crystals |
+------------------+------------------------------------------+
Synthetic Indicators:
+------------------+------------------------------------------+
| Synthetic Type | Telltale Inclusions |
+------------------+------------------------------------------+
| Flame fusion | Curved growth lines (striae), |
| (Verneuil) | gas bubbles (spherical) |
+------------------+------------------------------------------+
| Flux grown | Flux fingerprints (wispy veils), |
| | platinum platelets |
+------------------+------------------------------------------+
| Hydrothermal | Chevron or zigzag growth patterns, |
| | seed plate remnant |
+------------------+------------------------------------------+
| Glass simulants | Round gas bubbles, swirl marks, |
| | conchoidal fracture chips |
+------------------+------------------------------------------+
- Examine stone under darkfield illumination (gemological microscope) or oblique lighting through 10x loupe
- Look for species-diagnostic inclusions first
- Check synthetic indicators — curved striae + gas bubbles definitive for flame-fusion synthetics
- Note inclusion type, location, frequency
- Photograph inclusions if possible for records
Got: Species-confirming inclusion pattern + natural/synthetic determination. Some species IDed more by inclusions than optical properties (emerald's jardin).
If fail: Stone eye-clean + no inclusions visible at 10x? May be very clean natural stone or synthetic. Lack of inclusions raises synthetic probability — refer to optical + physical tests for confirmation. Laboratory analysis (FTIR, Raman) may be needed.
Step 5: ID by Elimination
Cross-reference all collected data to reach final ID.
- Compile property profile:
- Colour + transparency + luster
- Hardness or SG
- RI + birefringence + optic character
- Pleochroism + UV fluorescence
- Inclusion pattern
- Compare vs reference tables for candidate species
- Eliminate species that conflict with any measured property
- Two or more candidates remain? ID distinguishing test:
- Blue topaz vs aquamarine — SG definitive (3.53 vs 2.70)
- State ID with confidence level:
- Definitive: Multiple properties confirm single species
- Probable: Properties consistent with one species, one test missing
- Uncertain: Conflicting data or insufficient testing — lab referral recommended
Got: Final species ID ("Natural sapphire, blue, heat-treated") with supporting evidence from each test category. Or clear recommendation for lab analysis if field tests insufficient.
If fail: Stone can't be IDed with available equipment? Document all measured properties + refer to gemological laboratory. Provide measured data to lab — accelerates analysis.
Checks
- Visual inspection done under daylight-equivalent lighting
- At least two physical properties measured (hardness/SG + one other)
- RI measured + birefringence computed (if refractometer available)
- Pleochroism tested (if dichroscope available)
- Inclusions examined under at least 10x magnification
- ID reached by systematic elimination, not assumption
- Common simulants explicit considered + ruled out
- Natural vs synthetic determination made (or flagged as uncertain)
Pitfalls
- Trusting colour alone: Colour least reliable ID property. Blue stones include sapphire, topaz, aquamarine, tanzanite, iolite, spinel, glass, CZ. Always confirm with measurable properties
- Skipping SG on mounted stones: Mounted stones limit testing, but can still check RI, pleochroism, inclusions, UV. Document limitation not guess
- Confusing high-RI synthetics with naturals: Flame-fusion rubies + sapphires have identical RI + SG to natural stones. Only inclusions (curved striae vs straight growth) differentiate
- Assuming expensive = natural: Commercial jewellery frequently has treated, synthetic, simulant stones. Test every stone regardless of provenance claims
- Damaging specimen: Never hardness-test faceted gemstone — leaves visible scratches. Use non-destructive tests (RI, SG, inclusions) for cut stones
See Also
cut-gemstone— ID determines safe cutting parameters + orientation requirements for speciesappraise-gemstone— Positive ID prerequisite for meaningful valuationmineral-identification— Field mineral ID methodology using physical properties (prospecting domain) shares systematic elimination approach
GitHub Repository
Related Skills
content-collections
MetaThis skill provides a production-tested setup for Content Collections, a TypeScript-first tool that transforms Markdown/MDX files into type-safe data collections with Zod validation. Use it when building blogs, documentation sites, or content-heavy Vite + React applications to ensure type safety and automatic content validation. It covers everything from Vite plugin configuration and MDX compilation to deployment optimization and schema validation.
polymarket
MetaThis skill enables developers to build applications with the Polymarket prediction markets platform, including API integration for trading and market data. It also provides real-time data streaming via WebSocket to monitor live trades and market activity. Use it for implementing trading strategies or creating tools that process live market updates.
creating-opencode-plugins
MetaThis skill helps developers create OpenCode plugins that hook into 25+ event types like commands, files, and LSP operations. It provides the plugin structure, event API specifications, and implementation patterns for JavaScript/TypeScript modules. Use it when you need to intercept, monitor, or extend the OpenCode AI assistant's lifecycle with custom event-driven logic.
sglang
MetaSGLang is a high-performance LLM serving framework that specializes in fast, structured generation for JSON, regex, and agentic workflows using its RadixAttention prefix caching. It delivers significantly faster inference, especially for tasks with repeated prefixes, making it ideal for complex, structured outputs and multi-turn conversations. Choose SGLang over alternatives like vLLM when you need constrained decoding or are building applications with extensive prefix sharing.
