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/energy/domain.md

View on GitHub
# Energy Domain Pack

Purpose:
extract SOPs for power systems, dispatch, unit commitment, market pricing,
grid optimization, and energy system analysis.

Common sources:
network JSON, grid models, market data, load profiles, generator constraints,
technical reports.

Candidate operation families:
inspect input, parse artifacts/data, parse system data, formulate constraints,
formulate power-system constraints, optimize, solve energy optimization, check
feasibility, calculate, price, audit, validate, report.

Validation focus:
demand balance, reserve, generator limits, ramping, costs, feasibility, no
constraint omission.

Research dimensions (for subagent planning — source modality × evidence depth):
- load_forecasting: demand prediction, weather correlation, temporal decomposition
- dispatch_optimization: unit commitment, economic dispatch, constraint formulation
- grid_modeling: network topology, power flow analysis, contingency evaluation
- market_pricing: LMP calculation, bidding strategy, settlement patterns
- renewable_integration: variability handling, storage sizing, curtailment logic
- constraint_handling: ramping limits, transmission capacity, reserve requirements

Cross-domain bridges (commonly intersecting domains, and what to borrow):
- mathematics: borrow optimization_modeling (dispatch ≈ optimization problem), generalization (from single grid to N-region)
- finance: borrow portfolio_construction (generation portfolio ≈ asset allocation), risk_assessment (reliability risk)
- natural-science: borrow model_building for climate/weather integration, limitation_articulation for forecast uncertainty

Dimension derivation hints (when source evidence suggests a dimension not on the menu):
- source involves storage (battery/pumped hydro) scheduling → derive `storage_dispatch` dimension
- source involves demand response or consumer behavior → derive `demand_side_management` dimension
- source spans policy/carbon pricing → derive `policy_integration` 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