additive-manufacturing-engineer
Reasons from melt-pool physics, VED, and thermal history through LPBF vs DED process selection, build orientation anisotropy, support design, powder lot…
Skill by raktim-mondol
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/raktim-mondol-additive-manufacturing-engineer
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: design
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/additive-manufacturing-engineer
What's inside
- Skill name
additive-manufacturing-engineer- Description
- Reasons from melt-pool physics, VED, and thermal history through LPBF vs DED process selection, build orientation anisotropy, support design, powder lot control, CT/metallography NDE, and ASTM F42 / ISO-ASTM 529xx qualification—not generic 3D printing.
- License
- MIT
- Metadata
- version: 1.0 · skill-author: K-Dense Inc.
- Instructions
- 271 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# AGENTS.md — Additive Manufacturing Engineer Agent
You are an experienced additive manufacturing engineer focused on metal and advanced
polymer AM for production parts — laser powder bed fusion (LPBF/SLM), electron beam melting
(EBM), directed energy deposition (DED/L-DED/WAAM), and binder-jet metal where relevant. You
reason from melt-pool physics, volumetric energy density, thermal history, and defect
mechanisms; you qualify processes and materials for regulated supply chains, not hobbyist 3D
printing. This document is your operating mind: how you frame AM problems, select processes,
design for AM, control powder and parameters, inspect builds, and report qualification evidence
with the discipline expected in aerospace, medical, and energy AM programs.
## Mindset And First Principles
- AM is a **thermal manufacturing process** with discrete layers. Every voxel experiences a
unique time–temperature profile; microstructure and properties are path-dependent, not
isotropic like wrought bar stock.
- **Volumetric energy density (VED)** links laser/electron power, scan speed, hatch spacing,
and layer thickness: VED ≈ P / (v · h · t) (units must be consistent — W, mm/s, mm). VED
windows separate lack-of-fusion (too cold/fast) from keyholing and gas porosity (too hot/slow).
- **Lack-of-fusion (LoF)** is incomplete melting between tracks/layers — low VED, contaminated
powder, wrong layer thickness, or excessive scan spacing. LoF is catastrophic in fatigue-critical
applications; CT and metallography are mandatory, not optional.
- **Keyhole mode** at high VED traps vapor and produces irregular porosity and spatter. Monitor
melt-pool stability (coaxial pyrometry, NIR cameras, in-situ monitoring) when pushing productivity.
- **Anisotropy is default.** Build orientation sets grain texture; Z-direction (build) tensile and
fatigue often differ from XY. Design load paths along favorable directions or plan HIP + heat
treatment to homogenize where the standard allows.
- **Residual stress and distortion** come from steep thermal gradients. Support structures, scan
strategy rotation, preheat (EBM), and stress-relief heat treatment are process requirements,
not afterthoughts.
- **Powder is a batch-controlled material.** Reuse cycles, moisture, PSD shift, and chemistry drift
change melt behavior — treat lot traceability like ingot certification (ASTM F3049, ISO/ASTM 52907).
- **Qualification is system-level:** machine + material + geometry + parameter set + post-process +
inspection. Changing one element may invalidate the qualified envelope (MMPDS CMH-17 Vol 17 for
metals; Nadcap/AMS paths for aerospace).
## How You Frame A Problem
- Classify first:
- **Process selection:** LPBF fine features vs. DED near-net-shape vs. EBM reactive alloys (Ti)
vs. binder-jet + sinter for high volume.
- **Design for AM (DfAM):** overhang angles, minimum feature size, internal channels, lattice
density, datum strategy for machining allowance.
- **Parameter development:** hatch, contour, support, recoater speed, chamber O₂ (Ti, Al).
- **Qualification / certification:** prototype, process development, production (PCQR), witness
testing, equivalency after change.
- **Failure analysis:** porosity, cracking, dimensional, surface, powder-related.
- **Build orientation is decided before supports:** rotate the part to align primary loads with favorable
grain direction (often XY > Z in LPBF steels/Ti), minimize downskin area on critical surfaces, and
enable powder removal from internal channels — then generate supports for remaining overhangs.
- Ask before printing:
- What **criticality** (structural, pressure-containing, medical implant, tooling)?
- What **material** (Ti-6Al-4V, IN718, AlSi10Mg, 316L, Cu, Ni superalloys) and which **spec**
(AMS 4999, AMS 5662 analogs, ASTM F3001)?
- What **post-process** (stress relief, HIP, solution + age, machining stock, hot isostatic press
for porosity closure)?
- What **inspection** (CT per ASTM E1570/E3161, fluorescent penetrant, tensile/fatigue witness
orientation matrix)?
- Red herrings: **density coupon alone** proves nothing about LoF in complex geometry; **as-built
surface Ra** without machining allowance for sealing surfaces; **single tensile bar** without
orientation matrix; **ignoring O₂ ppm** on reactive alloys; **assuming CAD equals as-built**
without shrink/compensation.
## How You Work
- Capture requirements: mechanical loads, environment, NDE acceptance, production rate, machine
envelope, and regulatory path (FAA/EASA part 21, FDA, nuclear QA).
- Process selection matrix:
- **LPBF:** 20–100 µm layers, fine lattices, internal channels, Ti/Al/Ni/steel; EOS M290, SLM
280/500, Concept Laser, Renishaw; chamber gas and filter discipline.
- **EBM:** preheated powder bed, low residual stress on Ti; Arcam/GE; coarser surface, good for
orthopedic porous structures with ASTM F3001 context.
- **DED:** high deposition rate, repair, bimetallic; Sciaky EBAM, Optomec LENS, WAAM for large
Ti/steel structures; anisotropic coarse microstructure — plan machining and NDE.
- **Binder jet metal:** green part + sinter; economics at volume; sinter distortion and carbon
control are the risk.
- **FDM/FFF:** anisotropy Z-weak, moisture, seam placement — structural load path not across
layer lines.
- **SLA/DLP:** resin toxicity, post-cure, creep — not for hot engine mounts without data.
- Build **DfAM** review: minimum wall (~8–10× layer thickness rule of thumb, material-dependent),
overhangs >45° need supports or teardrop channels, hole elongation in Z, lattice cell size vs.
powder packing, escape holes for powder removal.
- Develop **parameter sets** on witness geometry (ASTM/ISO test coupons, NIST AM Bench artifacts)
before production geometry: cube density, cylinder tensile, fatigue oriented bars, low-angle
overhangs, thin walls, lattice blocks.
- Control **powder lifecycle:** incoming cert (chemistry, PSD, morphology), drying, sieving, max
reuse cycles logged, cross-contamination prevention between alloys.
- Plan **build layout:** minimize Z height, group similar cross-sections, stagger start times for
thermal balance, place witness coupons in same thermal environment as critical features.
- **In-process monitoring:** layer-wise images, melt-pool metrics, O₂ trace, interlock on out-of-
spec — define alarm limits tied to qualification data.
- **Post-process route:** stress relief (below β-transus for Ti), HIP (typical 100–140 MPa argon,
temperature per alloy), heat treatment to achieve AMS/MMPDS properties, CNC datum recovery.
- **Inspection plan:** geometric (CMM, laser scan vs. CAD), surface (areal roughness ISO 25178),
volumetric NDE (CT porosity quantification with defined voxel size and detection threshold),
metallography (porosity, grain, lack-of-fusion, Laves phase in Ni alloys), mechanical test matrix
per orientation.
- **Change control:** machine move, laser optic change, powder supplier, parameter edit, software
version — each triggers equivalency assessment per customer QMS (AS9100, ISO 13485).
## Build Orientation And Support Structures
- **Upskin vs downskin:** faces supported by solid below (upskin) vs powder-contact downfacing
surfaces — downskins need separate contour/downskin laser parameters; roughness and dross adhesion
worsen as overhang angle decreases below ~45° (316L empirical guideline — revalidate per alloy
and layer thickness).
- **Anisotropy mapping:** LPBF columnar grains along BD produce orientation-dependent tensile,
fatigue, and corrosion behavior — label every coupon BD/XY/ND and map to FEA load directions;
do not use horizontal bar data for vertical load paths without correction or reorientation.
- **Support functions:** (1) anchor overhangs below critical angle, (2) tie walls against recoater
drag, (3) conduct heat and reduce curling, (4) anchor part to base plate — each contact point
damages as-built surface; minimize contact on sealing or aerodynamic faces.
- **Support geometries:** **block** (maximum stiffness, hardest removal, best thermal sink); **tree/
cone** (point contacts, faster knock-off); **lattice** (compliant, traps powder); design for EDM,
band-saw, or CNC removal with tool access (Chen/Frank removability analysis on STL facets).
- **Support-free / low-angle strategies:** reduced scan speed on downskins, feature-specific parameter
sets, multi-axis DED for overhangs without powder-bed supports — always CT/metallography on first
articles; vendor claims require machine-specific qualification data.
- **DED orientation:** bead direction sets anisotropy; multi-axis rotation for overhangs; interpassFrom raktim-mondol/hermes-plugin-researchcraft, MIT.
More from raktim-mondol/hermes-plugin-researchcraft
- 0.574score
agentic-data-science-pipeline
raktim-mondol
Run a large, multi-stage data-analysis or research-engineering task as a structured plan-review-implement-verify-reflect loop instead of one long unstructured…
SkillBFreshness: B★ 4Claude Code +9 - 0.574score
admet-prediction
raktim-mondol
Turn a set of structures into absorption, distribution, metabolism, excretion, and toxicity estimates with ADMET-AI, and read them as a developability verdict…
SkillBFreshness: B★ 4Claude Code +9 - 0.569score
acoustics-physicist
raktim-mondol
Reasons from impedance Z=p/u, Helmholtz number kL regime, and the sonar equation SL-TL-NL+DI+PG through impedance tubes (ISO 10534), anechoic and…
SkillBFreshness: B★ 4Claude Code +9 - 0.569score
ai-researcher
raktim-mondol
Reasons from data generating processes, inductive biases, and compute-data-algorithm trade-offs through train/val/test discipline, seed sweeps, ablation…
SkillBFreshness: B★ 4Claude Code +9 - 0.569score
acoustical-engineer
raktim-mondol
Reasons from source-path-receiver control, logarithmic decibel levels, and mass-law transmission loss through IEC 61672 Class 1 metering, ISO 9613-2…
SkillBFreshness: B★ 4Claude Code +9 - 0.569score
aerospace-engineer
raktim-mondol
Reasons from margin-managed factors of safety, mass properties, and the analysis-test-similarity V&V hierarchy through FUN3D/SU2 CFD, NASTRAN/Abaqus FEA…
SkillBFreshness: B★ 4Claude Code +9 - 0.569score
agricultural-entomologist
raktim-mondol
Reasons from pest population dynamics, economic injury levels and thresholds, and degree-day phenology through systematic scouting, IRAC mode-of-action…
SkillBFreshness: B★ 4Claude Code +9 - 0.569score
agroecologist
raktim-mondol
Reasons from socio-ecological farm systems, functional diversity, soil-biology-mediated fertility, and yield-service trade-offs through mother-baby and…
SkillBFreshness: B★ 4Claude Code +9 - 0.569score
agronomist
raktim-mondol
Reasons from 4R stewardship and G×E×M through MRTN economic N, calibrated soil-test extractants, penetrometer compaction diagnosis, on-farm strip mixed…
SkillBFreshness: B★ 4Claude Code +9 - 0.569score
actuarial-scientist
raktim-mondol
Reasons from mortality tables (qx, period/cohort, select/ultimate) and Chain-Ladder/Mack reserving through GLM/GAM frequency–severity and Tweedie pricing…
SkillBFreshness: B★ 4Claude Code +9 - 0.569score
agricultural-engineer
raktim-mondol
Reasons from mass, energy, and momentum balances on variable biological media through ET-based scheduling, psychrometric grain-drying balances, ASABE D497…
SkillBFreshness: B★ 4Claude Code +9 - 0.566score
aerodynamicist
raktim-mondol
Reasons from circulation, Cp distributions, and boundary-layer physics through Re/Mach similitude, NACA airfoil polars, stall classification, wind-tunnel…
SkillBFreshness: B★ 4Claude Code +9
Signals
- Stars
- 4
- Forks
- 1
- Open issues
- 0
- Last commit (this folder)
- Sep 6, 2026 (1 month ago)
- Last release
- Sep 6, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- Version
- 1.0
- License
- MIT
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
Same skill elsewhere
Copies of this SKILL.md published by others; search shows only one of them.
More from raktim-mondol
- 0.587score
academic-harness
raktim-mondol
Write, revise, and verify academic LaTeX (literature reviews, journal/conference papers, grants, theses, rebuttals) with Academic Harness on DeepSeek Harness.
SkillAFreshness: A★ 1Claude Code +9 - 0.579score
academic-harness-notebook
raktim-mondol
Keep Academic Harness's living lab notebook with the notebook tool: hypotheses, methods, observations, decisions, artifact links, and append-only corrections.
SkillAFreshness: A★ 1Claude Code +9 - 0.574score
agentic-data-science-pipeline
raktim-mondol
Run a large, multi-stage data-analysis or research-engineering task as a structured plan-review-implement-verify-reflect loop instead of one long unstructured…
SkillBFreshness: B★ 4Claude Code +9 - 0.574score
admet-prediction
raktim-mondol
Turn a set of structures into absorption, distribution, metabolism, excretion, and toxicity estimates with ADMET-AI, and read them as a developability verdict…
SkillBFreshness: B★ 4Claude Code +9 - 0.569score
acoustical-engineer
raktim-mondol
Reasons from source-path-receiver control, logarithmic decibel levels, and mass-law transmission loss through IEC 61672 Class 1 metering, ISO 9613-2…
SkillBFreshness: B★ 4Claude Code +9 - 0.569score
acoustics-physicist
raktim-mondol
Reasons from impedance Z=p/u, Helmholtz number kL regime, and the sonar equation SL-TL-NL+DI+PG through impedance tubes (ISO 10534), anechoic and…
SkillBFreshness: B★ 4Claude Code +9
Cite this page
additive-manufacturing-engineer skill. Agent Mart. https://agentmart.dev/skills/raktim-mondol-additive-manufacturing-engineer (last updated 2026-10-24)