Loading...
Loading...
Found 75 Skills
Documents TypeScript code with JSDoc comments, generates API documentation, and creates type-safe documentation. Use when users request "JSDoc", "code documentation", "API docs", "TypeDoc", or "inline documentation".
Generate JSDoc/docstrings for functions
Maintains persistent codebase knowledge across sessions through a structured knowledge graph stored in a local Obsidian vault (.doctrack/). Use this skill whenever you have just made meaningful code changes (new features, modified components, refactoring, bug fixes) to update the project's documentation. Also use it when the user asks to document code, update docs, sync documentation, initialize documentation for an existing project, or when you want to understand the existing codebase structure at the start of a session. This skill should be used proactively after any significant code modification — don't wait for the user to ask. If you changed code, update the docs. Think of it as your long-term memory system: read before working, write after changing. Also use this when a user says "doctrack init", "doctrack refresh", "refresh docs", "update docs", "sync docs", "initialize docs", "document this project", or wants to bootstrap documentation for a codebase that has no .doctrack/ vault yet.
Use when checking for drift between docs/ and source code — reports discrepancies with file:line evidence.
Persistent decision log that creates a read-write feedback loop: read previous decisions before starting work, respect or supersede them, and write new Y-statement records as you go. Activates during any task involving architectural, structural, or design decisions - choosing libraries, designing schemas, creating modules, making tradeoffs, selecting patterns. Also activates when DECISIONS.md already exists in the project. Do NOT activate for trivial changes like typos, renames, or formatting.
Meta-skill for internal codebase exploration at varying depths (quick/deep/architecture)
Write technical reports — experiment reports, system design documents, code documentation, and internal research memos. Use when documenting technical work that doesn't fit paper format.
Turns a codebase into EventCatalog documentation through an evidence-based interview. Scans the code first, proposes an architectural model (domains, services, messages, channels), grills the user on the structural decisions, produces a reviewable plan file, then hands off to catalog-documentation-creator. Use when user says "document my codebase in EventCatalog", "turn this repo into a catalog", "model my code as a catalog", "grill me on my architecture", "update my catalog from the code", "reconcile my catalog with my code", or "I don't know where to start documenting this codebase". Works for brand-new catalogs AND for updating existing catalogs that have drifted from the code.
Writing technical articles and blog posts. Use when creating articles in docs/articles/ or blog content explaining patterns, techniques, or lessons learned.
Automatically generate standardized comments for Vue 2 Single-File Components (.vue). Parse the three blocks of template, script, and style, add structured comments according to the agreed format, without modifying any code logic. Trigger scenarios: Users request to add comments, supplement document comments for components, and interpret Vue 2 component structure.
Use when the user wants to generate technical documentation for ADVPL/TLPP code on TOTVS Protheus -- Protheus.doc header blocks (@type, @param, @return, @author, @since, @history), complete routine documentation (tables read/written, MV_* parameters, entry points, execution flow, dependencies), or REST API endpoint documentation (path/query parameters, request/response JSON, status codes). Also triggers on Portuguese phrasing like "documentar rotina", "gerar cabecalho Protheus.doc", "documentar endpoint", "documentar API REST", or requests to add documentation to legacy/undocumented code.
Ingest a codebase into memory as code pages connected by wiki links. Walks the tree, classifies each code file by role, applies a role template, and writes a code page per meaningful unit under <wiki root>/code/. Resumable: skips files already ingested and current. Not for prose documents; use /loam::adding-to-memory for those.