BeakrGo to website
Docs/Overview/Skills

Skills

Skills are atomic units of domain expertise that agents load on demand. They teach the agent how to use a Python package, query a database API, or apply a scientific methodology -- without being tied to a specific workflow. A skill is stored as a Markdown file, usually with optional bundled scripts, examples, or package references alongside it.

How skills work

Rather than packing every possible piece of domain knowledge into the agent's system prompt, Beakr uses a just-in-time loading model:

  1. Catalog. The agent sees a compact catalog of available skills -- name, description, and trigger keywords -- in its system prompt.
  2. Match. When the user's request matches a skill's trigger keywords or domain, the agent identifies which skill to load. Users can also ask for a specific skill by name when they want to force a known workflow.
  3. Load. The agent calls load_skills to pull the full expertise into context -- package documentation, code patterns, API conventions, and bundled scripts.
  4. Execute. The agent applies the loaded knowledge to the user's task, using the correct packages, APIs, and methodologies.

This keeps the agent's context focused. A skill for single-cell RNA-seq analysis doesn't consume context when the user is asking about project management.

What a skill contains

ComponentPurpose
Name and descriptionShown in the skill catalog. The agent uses these to decide when to load the skill.
Markdown instructionsThe core skill content. Markdown keeps procedures portable, reviewable, and easy to share across Beakr-supported agent surfaces.
DomainKnowledge domain (e.g., bioinformatics, cheminformatics, data science). Used for categorization.
Trigger keywordsComma-separated keywords that trigger automatic matching (e.g., "scRNA-seq, h5ad, UMAP, Scanpy").
KnowledgeThe full expertise content: how to use the package, API conventions, best practices, common pitfalls.
PackagesPython packages to install in the sandbox when this skill is active (e.g., ["scanpy", "anndata"]).
Tool patternsGuidance on how to use Beakr's built-in tools for this domain.
Bundled scriptsPre-built code scripts the agent can reference or execute directly.

Skill ownership

Skills can come from three sources:

SourceOwned byVisible to
SystemBeakrAll users
OrganizationYour orgAll members of the org
UserIndividual userOnly that user

Organizations can create custom skills that encode their specific methodologies, internal tools, or proprietary workflows. These skills are available to all members of the organization but not visible to other organizations. Because the source format is portable Markdown, approved skills can be shared across teams and reused anywhere Beakr agents run.

Skill library

Each user has a personal skill library -- a set of installed skills that are automatically available in their agent sessions. Users can:

Skills vs. workflows

Skills are capabilities, not orchestration.

A skill teaches the agent how to do something (use Scanpy, query PubMed, apply a statistical method). A workflow tells the agent what to do (run this analysis pipeline on this data). Workflows reference skills -- the workflow provides the steps, the skill provides the expertise for each step.