Explore skills
65,097 skills found
compiling-entities
Compiles a comprehensive entry for a named entity by scanning ALL files, gathering every mention, and assembling a structured profile. Use when building out a full entry for any character, species, location, or concept, or when user says "compile", "flesh out", "full entry for", or "everything about [entity]". Does NOT extract multiple entities from one source — use /extracting-entities.
extracting-entities
Extracts individual entities from a large source document and creates separate .md files for each one. Use when a source contains multiple distinct entities that should each have their own file, or when user says "extract", "pull out entities", "split this file", or "create files from this source". Does NOT compile scattered info about one entity — use /compiling-entities for that.
contexts-dictionaries
Draft, refine, prune, split, or rewrite Contexts and Dictionaries for the Context-Anchored Specifications framework. Use this skill whenever the user is asked to define a Context, draft a Dictionary from a Spec File, refine or prune terms, document Relationships between Contexts, or split a Context — even if they don't explicitly mention "Context" or "Dictionary". Applies anywhere project vocabula
evaluating-dependencies
Evaluates Node.js packages before installation by checking bundle size impact, comparing alternatives, verifying latest stable versions, and assessing maintenance status. Use when adding dependencies, installing packages, choosing between libraries, optimizing bundle size, or when user mentions npm install, yarn add, pnpm add, package selection, or asks about package recommendations.
make-pr
Creates pull requests on GitHub or Azure DevOps by analyzing commits and generating descriptions. Detects platform from git remote and uses gh CLI or az CLI. Use when asked to create PR, open PR, make pull request, submit PR, create pull request, new PR, raise PR, push PR, open pull request, submit changes, PR workflow, or when user mentions PR creation. Generates casual, context-aware PR descript
pr-review
Performs comprehensive code reviews checking for bugs, security issues, performance problems, testing gaps, and code quality. Accepts branch names or PR URLs (GitHub/Azure DevOps) to automatically checkout and review. Use when reviewing PRs, pull requests, code changes, commits, diffs, or when asked to review code, check code, audit changes, review my changes, check PR, review branch, or perform c
migrate-to-plugin-framework
This skill should be used when migrating Terraform provider data sources or resources from hashicorp/terraform-plugin-sdk/v2 to hashicorp/terraform-plugin-framework. Trigger phrases include "migrate to plugin framework", "SDK v2 to plugin framework", "convert to plugin framework", "migrate data source", "migrate resource", "plugin framework migration", "move to framework", or "upgrade from SDK v2"
auditing-canon
Verifies canon status, naming compliance, frontmatter completeness, writing standards, and cross-reference validity across worldbuilding files. Use when checking naming consistency, verifying frontmatter, auditing prose standards, or when user says "canon audit", "check names", "verify frontmatter", "writing standards check", or "naming audit". Does NOT check physics equations — use /auditing-phys
cross-checking
Cross-references a specific topic, concept, or rule across all files to verify it is used consistently. Use when checking if a term or claim matches its authoritative definition everywhere, or when user says "cross-check", "is this consistent", "verify this term", or "does this match everywhere". Does NOT audit entire directories — use /auditing-physics or /auditing-canon for that.
office-docx
Create, edit, fill, validate, or format native Word DOCX files. Use only when the requested input or final deliverable is a .docx/.doc Word file, or when the user explicitly asks for Word document formatting, placeholders, template application, tracked changes, comments, headers, footers, tables, or DOCX validation. Do not use for plain text drafting, general reports, Markdown, PDF, or knowledge e
auditing-human-assumptions
Scans worldbuilding files for unexamined assumptions — descriptions, vocabulary, and social structures that were imported rather than derived from the civilization's biology, cognition, and environment. Applies to ALL civilizations: alien species get checked for anthropomorphism; human civilizations in novel contexts get checked for assumptions imported from familiar Earth cultures. Use after writ
deep-reading
Reads an entire file and produces a structured content map showing sections, entities, claims, and gaps. Use when needing to understand a file before editing, checking conversion completeness, or when user says "what is in this file", "content map", "deep read", "read the whole thing", or "check completeness". Does NOT modify files — read-only analysis only.