Rohit Ghumare

Design and test rules for activating skills through human requests, AI selection, applications, or other skills. Check eligibility before matching descriptions, then return a JSON decision showing the selected channel, score, and policy reason.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Separate explicit requests from automatic skill selection
• Test allowed callers and skill composition limits
• Check cases where no skill should activate

Learn to create, discover, invoke, secure, evaluate, package, and port Agent Skills through one interactive lesson at a time. Practical checkpoints and quizzes track demonstrated progress in a local file, so later sessions resume where you stopped.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Learn to build and invoke a minimal Agent Skill
• Understand discovery and automatic routing
• Check permission, sandbox, and trust boundaries

Publish an approved Orchard release while retaining source paths in the result. The skill requires work to stop when supporting evidence is missing, making evidence availability a condition for proceeding.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Publish an approved Orchard release
• Retain source paths in publication results
• Stop release work when supporting evidence is missing

Helps agents choose the right agentmemory tool through MCP, a protocol for connecting agents to tools. It explains tool roles and points to parameter references for saving, retrieving, organizing, and maintaining stored knowledge.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Choosing a tool to save or retrieve knowledge
• Checking tool names and required parameters
• Reviewing available memory management operations

Shows recent work sessions for the current project as a timeline, newest first. It includes session identifiers, start times, status, recorded observation counts, and available highlights or decisions, using only history returned by the memory tool.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking what happened in the previous session
• Reviewing recent work in one project
• Finding decisions recorded in past sessions

Summarize recent agent sessions for the current project, grouped by date with highlights from recorded observations. Review today, the last seven days, or a chosen number of sessions, with totals for sessions, days, and observations.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Review today's agent work
• Recap project activity from the last seven days
• Summarize a chosen number of recent sessions

Find and delete selected memories stored in agentmemory after showing the matches and receiving explicit confirmation. It checks deletion results and distinguishes stored memories from lessons, observations, and complete session records.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Removing outdated stored memories
• Deleting selected memories containing private information
• Reviewing matching memories before deletion

List Git commits linked to agent work sessions, with branch or repository filters. See each commit’s message, date, linked sessions, and observation counts to review recorded changes alongside their session context.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Review recent commits linked to agent sessions
• Filter linked commits by branch
• Review linked commits for a specific repository

Create, update, or review agentmemory skills using a shared format. It guides document structure, supporting files, and generated reference data so contributions follow consistent rules and stay aligned with the source code.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Creating a new agentmemory skill
• Restructuring an existing skill
• Reviewing skill contributions for consistency

Resume work using the latest recorded session matching the current project directory. The skill surfaces unanswered questions first, summarizes relevant decisions and files, and provides a concrete next step while checking that records belong to the selected project.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Resuming work interrupted in a previous session
• Checking an unanswered question before continuing
• Reviewing key decisions and related files

Guide an agent through searching past decisions before work, saving new decisions with their reasons, and treating corrections as lessons. The workflow helps distinguish useful long-term knowledge from temporary details, code facts, and routine activity already captured by hooks.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking earlier decisions before starting a task
• Saving a resolved issue with its underlying reason
• Preserving lessons from corrections

Turns user corrections and recurring mistakes into actionable rules with confidence scores. It records when each rule applies and why it matters, so relevant lessons can be retrieved before similar work begins.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Recording a rule after a user correction
• Saving a lesson from a recurring mistake
• Keeping rules specific to one project

Retrieve past work, decisions, and lessons from agentmemory using keyword, meaning, and relationship searches. It expands selected records, groups findings by session, and prioritizes important observations so earlier context can inform the current task.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Recalling an earlier decision and its context
• Finding how a similar issue was handled
• Reviewing one project's or agent's history

Save facts, decisions, and discoveries to agentmemory for future sessions. The skill preserves the user's wording, adds specific search tags and referenced file paths, and confirms which terms can retrieve the saved knowledge.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Preserving a decision for future sessions
• Saving a discovery with related file paths
• Updating a previously saved fact

Trace a file, function, or line through Git history to the agent session linked to its commit. It presents recorded commit details, session summaries, and important observations to help explain the change.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigating why a particular line changed
• Finding the agent session behind a function change
• Checking a file's latest commit and author

Connect agentmemory to coding agents such as Claude Code and Codex while preserving existing server settings. It guides configuration, host restarts, and checks that memory tools are available and can save and retrieve information.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Connecting agentmemory to a coding agent
• Checking supported agents and connection methods
• Investigating an incorrect configuration path

Set up and troubleshoot a local agentmemory server by checking MCP connections, authentication, ports, and environment settings. Understand which optional memory features require additional configuration, model downloads, or token usage before enabling them.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Set up a local agentmemory connection
• Diagnose MCP connection failures
• Review authentication and custom ports

Guides HTTP integration with the agentmemory server for saving and searching knowledge. It explains authentication, request conventions, and endpoint references, including how to connect systems that do not support MCP, the agent tool connection protocol.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Saving and searching knowledge over HTTP
• Connecting a host that does not support MCP
• Checking authentication and response conventions

Understand how agentmemory automatically records tool activity, prompts, and session boundaries through hooks, actions triggered by session events. Use it to check integration setup, investigate missing records, and distinguish capture from optional summaries and context injection.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Understanding automatic session recording
• Investigating missing observations
• Checking capture and summary settings

Explain how agentmemory stores and retrieves coding agents’ memories, including its engine, search methods, memory lifecycle, ports, and web viewer. Useful for understanding the system or planning extensions to its functions.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Understand how agent memories are stored and retrieved
• Plan extensions to agentmemory
• Check memory capture in the web viewer

SkillOpt-flavored offline training loop for any SKILL.md. Treats accumulated learn-rule corrections as training trajectories, proposes bounded patches via an optimizer LLM, gates each candidate against a held-out validation set built from the user's own past corrections, and ships only candidates that demonstrably improve the score. Inspired by Microsoft SkillOpt's ReflACT pipeline (rollout → reflect → aggregate → select → update → evaluate) adapted to pro-workflow's SQLite store. Use when a skill has accumulated 8+ learn-rule rows and the user wants the skill itself to get better, not just longer.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Coordinate multiple Claude Code sessions as a team — lead + teammates with shared task lists, mailbox messaging, and file-lock claiming. Patterns for team sizing, task decomposition, and when to use teams vs sub-agents vs worktrees.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Compile a structured literature survey on any AI/ML topic. Agent curates a research bundle (taxonomy + sections + bibliography of real papers) from a public anchor resource, then a chosen LLM generates the survey artifact. Output target is a wiki page (markdown), not a one-off HTML — survey lands in `<wiki>/derived/surveys/<slug>.md` with full bibliography rows in `sources.md`. Provider-agnostic (Anthropic/OpenAI/OpenRouter/Fireworks/custom OpenAI-compat). Use when the user asks for a "survey", "literature review", "lit review", or "deep dive" on a technical topic.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Wire Commands, Agents, and Skills together for complex features. Use when building features that need research, planning, and implementation phases.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.