librarian
Multi-repository codebase exploration. Research library internals, find code patterns, understand architecture, compare implementations across GitHub/npm/PyPI/crates. Use when needing deep understanding of how...
Discover Content & media skills, compare source repositories and read the instructions for each workflow.
Multi-repository codebase exploration. Research library internals, find code patterns, understand architecture, compare implementations across GitHub/npm/PyPI/crates. Use when needing deep understanding of how...
Expert workflow for refactoring large Rust codebases, modularizing monolithic files, and establishing a robust quality gate using Clippy, formatting, and a comprehensive test suite (unit + integration). Use whe...
Fetch claude-code-plugins repo and convert plugins to OpenCode format. Usage: /sync-from-claude-plugins [plugin-names...] (default: all available plugins)
PRのコードレビューをCodexサブエージェントに依頼する。ユーザーがレビュー依頼/コード確認/「review」と言及したときに使う。
Create or update AgnosticV catalog files (common.yaml, dev.yaml, description.adoc, info-message-template.adoc)
Comprehensive codebase audit for release readiness. Parallel exploration of docs, code, config, tests, and specs to identify cruft, then interactive triage with clear action options.
Apply consistent coding style patterns when writing or reviewing code. Use when generating new code that should follow your established preferences. Works with any language. Complements linters (which handle fo...
Use find-slot-impls if you are looking for the implementations of a slot with a given name. Do it instead of grepping or exploring with text based tools.
Execute work session initialization routine at conversation start. Identifies new skills, researches improvements for existing skills, and updates skill library. Triggers automatically at session start.
Use this skill when analyzing how the system narrows down 500 million daily tweets to a candidate pool of ~1,500. This is the "top-of-funnel" engineering that determines what is even eligible to be ranked.
Use when configuring MCP servers in Claude Code, optimizing MCP token usage, troubleshooting MCP connections, understanding Tool Search thresholds, or deciding between MCP tools vs skills for token efficiency
Helps manage context window efficiently by summarizing, focusing, and pruning context to stay within token limits.
This skill should be used when searching, discovering, or installing skills from the skills.sh marketplace (Vercel's open agent skills ecosystem). It applies when the user wants to find skills for AI agents, br...
This skill routes /aida commands to appropriate handlers - configuration, diagnostics, feedback, extension management, session persistence (memento operations), and CLAUDE.md management.
Activates when the user asks about AI prompts, needs prompt templates, wants to search for prompts, or mentions prompts.chat. Use for discovering, retrieving, and improving prompts.
Generate research agent prompts from INQ QUESTION.md files for Phase 1 deliberation
Orchestrate multi-agent deliberation for INQ work items through all 4 phases
This skill should be used when the user asks to "requirements framework status", "show requirements project context", "what's the state of requirements framework", "requirements framework overview", or wants a...
Conducts retrospectives, archives items, and reprioritizes backlog
Scans repository and builds priority queue
Scans infrastructure task repositories for active and backlog tasks, builds priority queue based on criticality and dependencies
Provides current project state, architecture overview, and structured metadata
Reflect on a session to identify learnings, friction points, and improvements. Captures valuable insights for future sessions and system evolution.
Creates Jira tasks following Prowler's standard format. Trigger: When user asks to create a Jira task, ticket, or issue.
The default order uses GitHub repository stars from our indexed data. Stars belong to the source repository and may be shared by multiple skills. They indicate repository interest, not skill installs or an independent quality score.