NPC-Worldwide

Create a bar chart using chroptiks.bar.plot and save it to a file. Accepts x positions and heights as JSON.

Create a 1D histogram using chroptiks.hist1d.plot and save it to a file. Accepts data as a JSON array and plotting kwargs as a JSON object.

Create a 2D histogram using chroptiks.hist2d.plot and save it to a file. Accepts x and y arrays plus optional color-code array as JSON.

Create a 3D scatter plot using chroptiks.p3d.plot and save it to a file. Accepts x, y, z arrays as JSON. Note that p3d.plot normally calls plt.show(); this jinx suppresses display and saves instead.

Given data columns, automatically pick a sensible chroptiks plot (1D histogram, 2D histogram, or scatter) and save it. Useful when the user just says "plot this data".

Save the current matplotlib figure to a file path with chroptiks defaults (png, 250 dpi, tight bounding box). Returns the absolute path.

Create a scatter plot using chroptiks.scat.plot and save it to a file. Accepts x and y arrays plus optional color-code array as JSON.

Apply the bundled chroptiks matplotlib style and return a summary of active rc settings. Useful when an agent wants to reset or inspect the plotting style.

Skill for searching and evolving the SQLite-backed Knowledge Graph. Use this when you need structured fact/concept/link search across one or more teams, NPCs, or directory scopes. The Knowledge Graph (KG) is stored in the application's database (not YAML). It…

Skill for using the KnowledgeIndex registry to discover which directories contain `.knowledge.yaml` files without walking the filesystem. KnowledgeIndex is a lightweight SQLite cache. It maps directory paths to file metadata (mtime, memory_count, link_count).…

Skill for population-based Knowledge Graph evolution via Sememolution. Use this when the user wants creative cross-domain synthesis, speculative reasoning, or when a single KG search might be too narrow. Sememolution maintains a population of KG…

Skill for working with local .knowledge.yaml files via KnowledgeStore. Use this when you need to recall, search, or manage directory-local memories and knowledge links stored in plain YAML alongside the user's project files. KnowledgeStore is…

Write a new .jinx file from inputs (name, description, inputs spec as JSON list of strings, python body). Agents use this mid-task to crystallize a repeated block of code into a reusable jinx. The jinx is written to the team's jinxes/lib dir by default and…

Execute a jinx by name (already loaded on the team) or by filesystem path (e.g. a freshly created_jinx that isn't yet registered), passing input values as a JSON object. Returns the jinx's output field or the full context dict. Use this to run a jinx you just…

Git workflow best practices. Use when asked about git branching, commits, or merge strategy. [Sections: branching, commits, merging, hotfix]

npcpy LLM prompting and JSON formatting patterns.

Patterns for clear technical writing in documentation, READMEs, API references, and design documents.

Generate paired weak/strong technical writing examples for training and preference optimization. Stores examples for reuse in GRPO/DPO fine-tuning.