Unsupervisedcom

Unsupervisedcom/deepwork

Plugin Claude Code

Plugins for the DeepWork framework.

Unsupervisedcom/deepwork

Agent Claude Code

Reviews PRs and code changes for consistency with DeepWork's architectural patterns, naming conventions, and process standards. Understands both the framework codebase and how changes impact downstream user installations. Invoke for PR reviews or when checking that changes align with established conventions.

Unsupervisedcom/deepwork

Agent Claude Code

Reviews that all end-user functionality is covered by RFC 2119 requirements and that all requirements have traceable automated tests or DeepWork review rules.

Unsupervisedcom/deepwork

Settings file Claude Code

Agent settings declaring 111 allowed tools.

Unsupervisedcom/deepwork

Skill Claude CodeCodex

Merge the current PR, wait for merge queue/checks to complete, then switch to main and pull.

Unsupervisedcom/deepwork

Instructions file GitHub Copilot

Copilot instructions for Unsupervisedcom/deepwork, covering github copilot development environment, environment setup, available tools, running tests and all tests.

Unsupervisedcom/deepwork

MCP server Claude CodeCodexCursor +2

Framework for enabling AI agents to perform complex, multi-step work tasks. Runs locally from the deepwork Python package.

Unsupervisedcom/deepwork

Instructions file CodexOpenCode

AGENTS.md instructions for Unsupervisedcom/deepwork, covering deepwork - agent instructions, project overview, core concepts, jobs and steps.

Unsupervisedcom/deepwork

Instructions file

Claude Code instructions for Unsupervisedcom/deepwork.

Unsupervisedcom/deepwork

Plugin Claude Code

Auto-improving AI sub-agents that learn from their mistakes across sessions.

Unsupervisedcom/deepwork

Agent

Expert on the LearningAgent system. Operates on LearningAgent files: identifies issues in transcripts, investigates root causes, and incorporates learnings into agent definitions.

Unsupervisedcom/deepwork

Hook

Runs after a tool call finishes for Task tool calls, executing post_task.sh. From Unsupervisedcom/deepwork.

Unsupervisedcom/deepwork

Hook

Runs when the agent finishes a response, executing session_stop.sh. From Unsupervisedcom/deepwork.

Unsupervisedcom/deepwork

Skill Claude CodeCodex

Creates a new LearningAgent with directory structure, core-knowledge.md, and Claude Code agent file. Guides the user through initial configuration.

Unsupervisedcom/deepwork

Skill Claude CodeCodex

Reads a session transcript and identifies issues where a LearningAgent made mistakes, had knowledge gaps, or underperformed. Creates issue files for each problem found.

Unsupervisedcom/deepwork

Skill Claude CodeCodex

Takes investigated issues and incorporates the learnings into the LearningAgent's knowledge base by updating core-knowledge.md, topics, or learnings files.

Unsupervisedcom/deepwork

Skill Claude CodeCodex

Investigates identified issues in a LearningAgent session by reading the transcript, determining root causes, and updating issue files with investigation reports.

Unsupervisedcom/deepwork

Skill Claude CodeCodex

Runs the learning cycle on all LearningAgent sessions with pending transcripts. Identifies issues, investigates root causes, and incorporates learnings into agent definitions.

Unsupervisedcom/deepwork

Skill Claude CodeCodex

Dispatch entry point for the LearningAgents plugin. Routes to sub-commands for creating agents, running learning cycles, and reporting issues.

Unsupervisedcom/deepwork

Skill Claude CodeCodex

Reviews a prompt/instruction file against Anthropic prompt engineering best practices. Use when evaluating skill files, agent definitions, or instruction chunks for quality.

Unsupervisedcom/deepwork

Skill Claude CodeCodex

Creates an issue file tracking a problem observed in a LearningAgent session. Used by the identify skill and can be invoked directly to report issues in real-time.

Unsupervisedcom/deepwork

Skill Claude CodeCodex

Configures project permissions for the LearningAgents plugin. Adds required Bash and file access rules to .claude/settings.json.

Unsupervisedcom/deepwork

Plugin Claude Code

Framework for AI-powered multi-step workflows with quality gates.

Unsupervisedcom/deepwork

Agent

Minimal review subagent for DeepWork review tasks. Reads a supplied instruction file, performs the review against the criteria in that file, and reports results via the DeepWork MCP markreviewaspassed tool. Use when dispatching parallel review tasks from .deepreview rules or workflow quality gates.