Agent
Designs implementation blueprints for features using exploration findings and architectural best practices.
Agent Alchemy is a curated collection of plugins, apps, and extensions designed to elevate your agentic engineering workflows. Built for Claude Code and other AI coding agents, these tools help developers work smarter and ship faster.
Agent
Designs implementation blueprints for features using exploration findings and architectural best practices.
Agent
Explores codebases to find relevant files, trace execution paths, and map architecture with team communication capabilities for collaborative analysis.
Agent
Synthesizes exploration findings into unified analysis with deep investigation capabilities (Bash, git history, dependency analysis) and completeness evaluation.
Agent
Researches technical documentation, domain knowledge, compliance requirements, best practices, and competitive landscape to support an adaptive interview. Use when the interview-me skill dispatches a research task for a topic surfaced during the conversation. user: (via interview-me) "What are good remote-first retro…
Agent
Solves competitive programming and LeetCode-style problems with educational explanations. Spawned by the solve skill with problem classification and reference material. Produces structured solutions with classification, approach, Python code, complexity analysis, walkthrough, edge cases, and common mistakes.
Agent
Verifies competitive programming solutions through static analysis, test case generation, and execution. Spawned by the verify skill with problem statement and solution code. Reports correctness verdict, failing cases, bug analysis, and improvement suggestions.
Agent
Executes diagnostic investigation tasks to test debugging hypotheses. Runs tests, traces execution, checks git history, and reports evidence.
Agent
Reviews git history and updates CHANGELOG.md with entries for [Unreleased] section.
Agent
Reviews code implementations for correctness, security, maintainability with confidence-scored findings.
Agent
Generates MkDocs-flavored or standard GitHub-flavored Markdown documentation from codebase analysis findings including API references, architecture guides, standalone markdown files, and change summaries.
Agent
Generates OpenCode skill, agent, and command files based on interview results. Spawned by oc-create-skill, oc-create-agent, and oc-create-command.
Agent
Fetches latest OpenCode documentation and changelog to verify compatibility. Spawned by oc-update skills to check if existing artifacts match current OpenCode best practices.
Agent
Validates generated or updated OpenCode skills, agents, and commands against the platform specification. Spawned by all 6 oc- skills post-generation or update.
Agent
Converts a single plugin component (skill, agent, hooks, reference, or MCP config) to a target platform format. Spawned by port-plugin as part of a wave-based conversion team. Reads session files for shared knowledge, loads type-specific converter references on demand, and writes structured results to per-component…
Agent
Researches target platform plugin architectures by fetching official documentation, community examples, and existing plugins to produce a structured platform profile for the conversion engine.
Agent
Explores codebases to discover architecture, patterns, and feature-relevant code for spec creation context. Spawned in parallel with specific focus areas.
Agent
Manages execution context lifecycle within a single wave of the run-tasks engine. Reads and summarizes prior wave learnings from executioncontext.md, distributes context to all task executors via SendMessage, collects context contributions during execution, provides enriched context for Tier 2 retries, and finalizes…