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/mathematics/domain.md

View on GitHub
# Mathematics Domain Pack

Purpose:
extract SOPs for proofs, formal methods, problem solving, symbolic reasoning,
optimization, and numerical verification.

Common sources:
problem statements, LaTeX, Lean files, lecture notes, proof sketches, solver
models.

Candidate operation families:
inspect input, parse artifacts/data, formalize problem, formalize problem
model, introduce definitions, choose strategy, solve or prove, prove lemmas,
split cases, calculate, optimize, verify, validate, report, generalize.

Validation focus:
logical completeness, symbol consistency, proof checking, no hidden assumption,
no theorem statement modification.

Research dimensions (for subagent planning — source modality × evidence depth):
- problem_formalization: definition crafting, assumption articulation, notation standardization
- proof_strategy: induction, contradiction, construction, case analysis, diagonalization
- symbolic_manipulation: algebraic transformation, inequality handling, pattern recognition
- optimization_modeling: objective formulation, constraint encoding, solver selection
- generalization: from specific case to general theorem, boundary identification
- verification: proof checking, counterexample search, edge case enumeration

Cross-domain bridges (commonly intersecting domains, and what to borrow):
- software-engineering: borrow debugging_patterns (proof debugging), code_architecture (proof structure ≈ code structure)
- natural-science: borrow model_building (mathematical modeling), limitation_articulation (axiom boundary)
- finance: borrow risk_assessment (probabilistic reasoning), portfolio_construction (constrained optimization)

Dimension derivation hints (when source evidence suggests a dimension not on the menu):
- source involves computational / algorithmic methods → derive `algorithm_design` dimension
- source involves teaching or exposition of mathematics → derive `mathematical_exposition` dimension
- source spans multiple subfields or analogical transfer → derive `cross_domain_transfer` 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