From wize-doc
Explore the Workwize codebase to find files relevant to a feature. Returns a structured analysis of business logic, endpoints, models, and key rules found. Used internally by the wize-doc agent.
npx claudepluginhub goworkwize/wize-docThis skill uses the workspace's default tool permissions.
Explore the Workwize codebase to find and analyze files relevant to a feature.
Creates new Angular apps using Angular CLI with flags for routing, SSR, SCSS, prefixes, and AI config. Follows best practices for modern TypeScript/Angular development. Use when starting Angular projects.
Executes ctx7 CLI to fetch up-to-date library documentation, manage AI coding skills (install/search/generate/remove/suggest), and configure Context7 MCP. Useful for current API refs, skill handling, or agent setup.
Share bugs, ideas, or general feedback.
Explore the Workwize codebase to find and analyze files relevant to a feature.
Feature name from the orchestrator (e.g. auto-restock, budget approval).
From the feature name, extract 1–2 short tokens for glob matching:
auto-restock → try both restock and autorestock)Run these searches in parallel using the primary token:
**/*<token>*.php — backend (Laravel)**/*<token>*.ts — TypeScript**/*<token>*.tsx — React componentsExclude: vendor/, node_modules/, dist/, .next/, storage/, bootstrap/cache/.
If results are sparse (< 5 files), also try the secondary token or broaden with related terms.
In addition to token-based matches, scan these directories for contextually related files:
Backend (PHP):
wize-back/project/app/Http/Controllers/**/*<token>*wize-back/project/app/Services/**/*<token>*wize-back/project/app/Models/**/*<token>*wize-back/project/app/Jobs/**/*<token>*Frontend (TS/TSX):
wize-front/src/components/**/*<token>*wize-front/src/hooks/**/*<token>*wize-front/src/services/**/*<token>*wize-front/src/pages/**/*<token>*Show the combined file list to the user. Select the 10–15 most relevant files based on:
Ask the user to confirm, remove irrelevant files, or add paths you may have missed.
Read each confirmed file in full. For very large files (> 300 lines), read the most relevant sections first (class definition, key methods, validation rules).
Summarize findings for the doc-writer. Cover:
Keep the summary factual — extract what is in the code, don't invent behavior.