Guide for creating effective skills for fundamental physics research. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized scientific knowledge, research workflows, or physics tool integrations.
Provides guidance for creating physics research skills that extend Claude with specialized workflows, tool integrations, and domain expertise. Use when users request new skills for fundamental physics research or want to update existing ones.
/plugin marketplace add fundamental-physics/marketplace/plugin install core@fundamental-physicsThis skill inherits all available tools. When active, it can use any tool Claude has access to.
references/output-patterns.mdreferences/workflows.mdscripts/init_skill.pyscripts/package_skill.pyscripts/quick_validate.pyThis skill provides guidance for creating effective skills for fundamental physics research.
Skills are modular, self-contained packages that extend Claude's capabilities by providing specialized knowledge, workflows, and tools. Think of them as "onboarding guides" for specific domains or tasks—they transform Claude from a general-purpose agent into a specialized research assistant equipped with procedural knowledge that no model can fully possess.
Physics research skills typically provide one or more of these workflow components:
(1) Research/Brainstorm → (2) Science → (3) Inference → (4) Visualization
arxiv, inspire, ads)astrophysics, jax-bandflux)jax-nested-sampler)anesthetic-plotter)Skills may be monolithic (covering multiple components) or modular (single component, composable with others).
The context window is a public good. Skills share the context window with everything else Claude needs: system prompt, conversation history, other Skills' metadata, and the actual user request.
Default assumption: Claude is already very smart. Only add context Claude doesn't already have. Challenge each piece of information: "Does Claude really need this explanation?" and "Does this paragraph justify its token cost?"
Prefer concise examples over verbose explanations.
Match the level of specificity to the task's fragility and variability:
High freedom (text-based instructions): Use when multiple approaches are valid, decisions depend on context, or heuristics guide the approach.
Medium freedom (pseudocode or scripts with parameters): Use when a preferred pattern exists, some variation is acceptable, or configuration affects behavior.
Low freedom (specific scripts, few parameters): Use when operations are fragile and error-prone, consistency is critical, or a specific sequence must be followed.
Think of Claude as exploring a path: a narrow bridge with cliffs needs specific guardrails (low freedom), while an open field allows many routes (high freedom).
Every skill consists of a required SKILL.md file and optional bundled resources:
skill-name/
├── SKILL.md (required)
│ ├── YAML frontmatter metadata (required)
│ │ ├── name: (required)
│ │ └── description: (required)
│ └── Markdown instructions (required)
└── Bundled Resources (optional)
├── scripts/ - Executable code (Python/Bash/etc.)
├── references/ - Documentation intended to be loaded into context as needed
└── assets/ - Files used in output (templates, icons, fonts, etc.)
Every SKILL.md consists of:
name and description fields. These are the only fields that Claude reads to determine when the skill gets used, thus it is very important to be clear and comprehensive in describing what the skill is, and when it should be used.scripts/)Executable code (Python/Bash/etc.) for tasks that require deterministic reliability or are repeatedly rewritten.
scripts/arxiv.py for paper search and LaTeX extraction, scripts/run_nested.py for nested samplingreferences/)Documentation and reference material intended to be loaded as needed into context to inform Claude's process and thinking.
references/pdg_constants.md for particle physics parameters, references/coordinate_systems.md for astronomy conventions, references/filter_definitions.md for photometryassets/)Files not intended to be loaded into context, but rather used within the output Claude produces.
assets/physics_plots.mplstyle for publication-quality matplotlib styling, assets/paper_template.tex for LaTeX templates, assets/sed_templates/ for SED model filesA skill should only contain essential files that directly support its functionality. Do NOT create extraneous documentation or auxiliary files, including:
The skill should only contain the information needed for an AI agent to do the job at hand. It should not contain auxiliary context about the process that went into creating it, setup and testing procedures, user-facing documentation, etc. Creating additional documentation files just adds clutter and confusion.
Skills use a three-level loading system to manage context efficiently:
Keep SKILL.md body to the essentials and under 500 lines to minimize context bloat. Split content into separate files when approaching this limit. When splitting out content into other files, it is very important to reference them from SKILL.md and describe clearly when to read them, to ensure the reader of the skill knows they exist and when to use them.
Key principle: When a skill supports multiple variations, frameworks, or options, keep only the core workflow and selection guidance in SKILL.md. Move variant-specific details (patterns, examples, configuration) into separate reference files.
Pattern 1: High-level guide with references
# Cosmological Analysis
## Quick start
Compute distances with astropy:
[code example]
## Advanced features
- **Parameter estimation**: See references/mcmc_guide.md for sampling workflows
- **Power spectra**: See references/power_spectrum.md for Fourier methods
- **Data formats**: See references/fits_handling.md for FITS file operations
Claude loads the reference files only when needed.
Pattern 2: Domain-specific organization
For Skills with multiple physics domains, organize content by domain to avoid loading irrelevant context:
particle-physics/
├── SKILL.md (overview and navigation)
└── references/
├── colliders.md (LHC, detector data)
├── neutrinos.md (oscillation experiments)
├── dark_matter.md (direct/indirect detection)
└── beyond_sm.md (SUSY, extra dimensions)
When a user asks about LHC analysis, Claude only reads colliders.md.
Similarly, for skills supporting multiple methods or frameworks:
bayesian-inference/
├── SKILL.md (workflow + method selection)
└── references/
├── mcmc.md (Metropolis-Hastings, HMC, emcee)
├── nested_sampling.md (dynesty, MultiNest)
└── variational.md (ADVI, normalizing flows)
When the user chooses nested sampling, Claude only reads nested_sampling.md.
Pattern 3: Conditional details
Show basic content, link to advanced content:
# Spectral Analysis
## Basic fitting
Use scipy.optimize for simple fits.
## Advanced methods
**For MCMC sampling**: See references/mcmc.md
**For nested sampling**: See references/nested.md
**For JAX acceleration**: See references/jax_fitting.md
Claude reads the specific reference only when the user needs those features.
Important guidelines:
Skill creation involves these steps:
Follow these steps in order, skipping only if there is a clear reason why they are not applicable.
Skip this step only when the skill's usage patterns are already clearly understood. It remains valuable even when working with an existing skill.
To create an effective skill, clearly understand concrete examples of how the skill will be used. This understanding can come from either direct user examples or generated examples that are validated with user feedback.
For example, when building a nested-sampling skill, relevant questions include:
To avoid overwhelming users, avoid asking too many questions in a single message. Start with the most important questions and follow up as needed for better effectiveness.
Conclude this step when there is a clear sense of the functionality the skill should support.
To turn concrete examples into an effective skill, analyze each example by:
Example: When building a jax-nested-sampler skill to handle queries like "Run nested sampling on this likelihood," the analysis shows:
scripts/run_nested.py script would be helpful to store in the skillExample: When designing a jax-bandflux skill for queries like "Compute the expected flux in these bands," the analysis shows:
references/filter_definitions.md file and assets/sed_templates/ directory would be helpfulExample: When building an anesthetic-plotter skill to handle queries like "Create a corner plot from these samples," the analysis shows:
assets/anesthetic_style.mplstyle file would be helpful to store in the skillTo establish the skill's contents, analyze each concrete example to create a list of the reusable resources to include: scripts, references, and assets.
At this point, it is time to actually create the skill.
Skip this step only if the skill being developed already exists, and iteration is needed. In this case, continue to the next step.
When creating a new skill from scratch, run the init_skill.py script. The script generates a new template skill directory that automatically includes everything a skill requires.
Usage:
scripts/init_skill.py <skill-name> --path <output-directory>
Examples:
scripts/init_skill.py jax-nested-sampler --path plugins/core/skills
scripts/init_skill.py anesthetic-plotter --path plugins/core/skills
scripts/init_skill.py jax-bandflux --path plugins/astro-ph.CO/skills
The script:
scripts/, references/, and assets/After initialization, customize or remove the generated SKILL.md and example files as needed.
When editing the (newly-generated or existing) skill, remember that the skill is being created for another instance of Claude to use. Include information that would be beneficial and non-obvious to Claude. Consider what procedural knowledge, domain-specific details, or reusable assets would help another Claude instance execute these tasks more effectively.
Consult these helpful guides based on your skill's needs:
These files contain established best practices for effective skill design.
To begin implementation, start with the reusable resources identified above: scripts/, references/, and assets/ files. Note that this step may require user input. For example, when implementing a cosmology skill, the user may need to provide specific parameter conventions or institutional data formats.
Added scripts must be tested by actually running them to ensure there are no bugs and that the output matches what is expected. If there are many similar scripts, only a representative sample needs to be tested to ensure confidence that they all work while balancing time to completion.
Any example files and directories not needed for the skill should be deleted.
Writing Guidelines: Always use imperative/infinitive form.
Write the YAML frontmatter with name and description:
name: The skill namedescription: This is the primary triggering mechanism for your skill, and helps Claude understand when to use the skill.
cosmology skill: "Cosmological calculations and analysis including distance measures, power spectra, parameter estimation, and CMB analysis. Use when working with: (1) Cosmological distances and redshifts, (2) Matter/CMB power spectra, (3) Cosmological parameter fitting, (4) CAMB/CLASS computations."Do not include any other fields in YAML frontmatter.
Write instructions for using the skill and its bundled resources.
Once development of the skill is complete, it can be packaged into a distributable .skill file. The packaging process automatically validates the skill first:
scripts/package_skill.py <path/to/skill-folder>
Optional output directory specification:
scripts/package_skill.py <path/to/skill-folder> ./dist
The packaging script will:
Validate the skill automatically, checking:
Package the skill if validation passes, creating a .skill file named after the skill (e.g., my-skill.skill).
If validation fails, fix the errors and run the packaging command again.
After testing the skill, users may request improvements. Often this happens right after using the skill, with fresh context of how the skill performed.
Iteration workflow:
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.
Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.
Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.