Skip to content

agentsope/SkillAlchemy / skills/LEAP

LEAP builds skills through two pipelines: Branch A distills a skill from raw data, while Branch B combines multiple skills into one. It is called by the main SkillAlchemy workflow. Use when SkillAlchemy requires distillation or fusion.

domains/manufacturing/domain.md

View on GitHub
# Manufacturing Domain Pack

Purpose:
extract SOPs for CAD/CAM, 3D scanning, mesh inspection, process control,
equipment maintenance, quality assurance, and production optimization.

Common sources:
STL/DXF/CAD files, equipment logs, QC reports, maintenance records, process
data, material tables.

Candidate operation families:
inspect input, parse artifacts/data, parse geometry/process data, filter noise,
filter/select relevant entity, measure, lookup reference data, lookup
material/process constraints, calculate, validate, report.

Validation focus:
units, tolerances, material properties, largest component/noise filtering,
process constraints, no hardcoded benchmark answer.

Research dimensions (for subagent planning — source modality × evidence depth):
- geometry_parsing: CAD/STL interpretation, mesh analysis, feature extraction, binary format handling
- tolerance_analysis: precision requirements, quality gates, GD&T, measurement uncertainty
- material_handling: density/property lookup, process constraints, material selection logic
- process_planning: operation sequencing, tool selection, workflow optimization
- quality_assurance: inspection methods, statistical process control, defect classification
- output_schema: deliverable format conventions, report structure, validation rules

Cross-domain bridges (commonly intersecting domains, and what to borrow):
- robotics: borrow motion_planning (toolpath ≈ motion), sensor_fusion (multi-sensor QC), failure_diagnosis
- software-engineering: borrow ci_deployment (manufacturing pipeline), testing_strategy (QC ≈ testing)
- mathematics: borrow optimization_modeling (process optimization), generalization (from one part to family)

Dimension derivation hints (when source evidence suggests a dimension not on the menu):
- source involves additive/subtractive process choice → derive `process_selection` dimension
- source involves supply chain or vendor qualification → derive `supply_chain_quality` dimension
- source spans design-for-manufacturing feedback → derive `dfm_feedback` dimension
- new dimension rule: name = `<operation_the_source_exposes>`, mission = "extract how <target> performs <operation>"
writing-skillsobra/superpowersUse when creating new skills, editing existing skills, or verifying skills work before deploymentStars: 322kUpdated Claude CodeCodexVerifiedInstall
xlsxanthropics/skillsUse this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
shipping-and-launchaddyosmani/agent-skillsPrepares production launches. Use when preparing to deploy to production, or when asking what needs to be in place before shipping. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy.Stars: 119kUpdated Claude CodeCodexVerifiedInstall
childhoodthedotmack/claude-memBabysit a shipped release after merge, publication, or deployment. Verify published packages, production behavior, installed plugins, and late CI or user reports until the observation window is clean; use babysit for PR readiness before release.Stars: 118kUpdated Claude CodeCodexVerifiedInstall