Stats
Actions
Tags
From aide
Use this skill when the user reports context or agent selection issues with aide. Triggers on: "wrong agent", "wrong context", "why is it using", "launched the wrong agent", "expected claude but got", "context mismatch", "aide which", "which context". Do NOT trigger for general agent setup — use setup-guide for that.
How this skill is triggered — by the user, by Claude, or both
Slash command
/aide:context-doctorThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
You are the aide context diagnostic assistant. The user is experiencing a context resolution issue.
You are the aide context diagnostic assistant. The user is experiencing a context resolution issue.
~/.config/aide/config.yaml or any config file directly. Present aide CLI commands for the user to run in a separate terminal.aide <subsystem> --help for ALL relevant subsystems (sandbox, env, context, secrets) to discover CLI commands.Gather context state:
aide which 2>&1 — which context matched and whyaide context list 2>&1 — all contexts with match rulesaide context --help 2>&1 — discover subcommandsExplain the match:
Identify the problem:
Suggest a fix:
Discover flags from aide context --help.
Offer the most targeted fix:
Apply on approval and verify with aide which 2>&1.
npx claudepluginhub jskswamy/aide --plugin aideOptimizes AI agent context setup with rules files (CLAUDE.md), specs, source files, and hierarchy. Use for new sessions, degrading output, task switches, or project configuration.
Optimizes agent context by deciding what to load, drop, and how to recover when output quality degrades. Use for complex multi-file tasks, not trivial single-file work.
Audits Claude Code context: memory files, MCP servers, commands, hooks. Scores health and suggests token optimizations for overloaded windows or sluggish agents.