Session Debug Agent Skill

Diagnose issues in the current Amplifier session — misconfigured tools, failing operations, unexpected behavior. Use when something isn't working right.

515 tokens

context cost

the whole folder, loaded on every use

files

instructions only

copies elsewhere

how many repositories repackaged it

stars on the repo

on the repository, not the skill itself

Install

one command, takes just this skill from the repository

npx skills add https://github.com/microsoft/amplifier-bundle-skills --skill session-debug

The instruction itself

3 sections, as written by the author

Debug: Session Diagnostics

Help the user diagnose an issue they're encountering in their current Amplifier session.

Issue Description

$ARGUMENTS

If no issue was described, read the session logs and summarize any errors, warnings, or notable issues.

Instructions

Delegate to the session-analyst agent to investigate the current session. The session-analyst has specialized knowledge for safely analyzing large event logs (events.jsonl files can contain lines with 100k+ tokens that will crash other tools). Use the delegate tool to dispatch it with the issue description and any relevant context.

Check session configuration. Review the current session's configuration for common issues:
Bundle composition problems (missing modules, failed loads)
Provider configuration (missing API keys, wrong endpoints)
Tool availability (tools expected but not mounted)
Hook failures (hooks that errored during lifecycle events)

Session and project settings are typically at:

Project: .amplifier/settings.yaml
User: ~/.amplifier/settings.yaml
Keys: ~/.amplifier/keys.env

Check for common patterns:
Tool calls returning errors repeatedly
Provider rejections (rate limits, auth failures, model not found)
Module mount failures at startup
Context overflow or compaction issues

Explain what you found in plain language. Avoid jargon. Tell the user:
What went wrong
Why it likely happened
Concrete steps to fix it

If the issue can't be diagnosed from logs alone, suggest the user:
Run amplifier doctor for a system health check
Check amplifier module list to verify module availability
Try amplifier --verbose to see detailed startup output

Other skills for the same job

different authors, same section of the catalogue

Hook Development

by anthropics

vendor ×2

This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.

Build agentic applications with GitHub Copilot SDK. Use when embedding AI agents in apps, creating custom tools, implementing streaming responses, managing sessions, connecting to MCP servers, or creating custom agents. Triggers on Copilot SDK, GitHub SDK, agentic app, embed Copilot, programmable agent, MCP server, custom agent.

Coding Agent Session Search - unified CLI/TUI to index and search local coding agent history from Claude Code, Codex, Gemini, Cursor, Aider, ChatGPT, Pi-Agent, Factory, and more. Purpose-built for AI agent consumption with robot mode.

Destructive Command Guard - High-performance Rust hook for Claude Code that blocks dangerous commands before execution. SIMD-accelerated, modular pack system, whitelist-first architecture. Essential safety layer for agent workflows.

Makepad UI development skills for Rust apps: setup, patterns, shaders, packaging, and troubleshooting.

Secure environment variable management ensuring secrets are never exposed in Claude sessions, terminals, logs, or git commits

Prompt for generating an AGENTS.md file for a repository

2k tokens

How to use it

Copy the folder

Take microsoft/session-debug from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.