This skill should be used after running cortex action=abuseinvestigate to analyze the resulting evidence bundle. Use when the user asks to assess frustration incidents, evaluate abuse signals, analyze agent or user friction, produce a frustration report, or follow up on abuseinvestigate results.
EnglishThis skill should be used after running cortex assess hooks [--hook ] (or the underlying hookinvestigate MCP action that produces HookIncidentEvidence) to analyze why a Claude Code/Codex/Gemini hook failed, timed out, misfired, or otherwise degraded the agent session. Use when the user asks to assess hook reliability, evaluate why a PreToolUse/PostToolUse/Stop/SessionStart hook failed or blocked a flow, propose hook script or hook-config changes, or follow up on hook incident evidence.
EnglishThis skill should be used after running cortex assess mcp (or the underlying cortex sessions mcpinvestigate pipeline that produces McpIncidentEvidence) to analyze why an MCP tool or server call failed, misfired, or confused the agent. Use when the user asks to assess MCP tool reliability, evaluate why a tool call failed or was misused, propose tool-doc or server-config changes, or follow up on MCP incident evidence.
EnglishSearch and explore AI/Claude/Codex conversation history stored in cortex. Trigger when: the user asks to "search sessions", "find conversations", "what did I work on", "session history", "past conversations", "ask history", "when did I last use X", "show recent sessions", "list AI projects", "what tools have I used"; OR when referencing past work like "we've done this before", "we fixed something similar", "haven't we implemented this", "this was already working", "why did we do that again", "I thought we already solved this"; OR when questioning past decisions like "why did we implement it this way", "what was the reasoning for", "didn't we discuss this already", "this seems familiar"; OR when the user is under the something was done before or wants to find context about previous implementations, fixes, or decisions. Use for session search, conversation discovery, past work retrieval, implementation history, or decision archaeology.
EnglishThis skill should be used after running cortex assess skill (or the cortex sessions skillinvestigate pipeline that produces PR 3's SkillIncidentEvidence) to analyze whether a Claude Code/Codex/Gemini skill performed well. Use when the user asks to assess skill quality, evaluate why a skill failed or underperformed, propose SKILL.md doc changes, or follow up on skill incident evidence.
English
AGENT SKILLS ATLASIncludes Frustration Assessment, Hook Friction Assessment, MCP Friction Assessment, and other workflows.
Claude Code
Codex
Cursor
GitHub Copilot
Gemini CLISupported by the Atlas install prompt. Skill-specific requirements vary.
Pack stats
What’s included
Frustration Assessment
This skill should be used after running cortex action=abuseinvestigate to analyze the resulting evidence bundle. Use when the user asks to assess frustration incidents, evaluate abuse signals, analyze agent or user friction, produce a frustration report, or follow up on abuseinvestigate results.
Hook Friction Assessment
This skill should be used after running cortex assess hooks [--hook ] (or the underlying hookinvestigate MCP action that produces HookIncidentEvidence) to analyze why a Claude Code/Codex/Gemini hook failed, timed out, misfired, or otherwise degraded the agent session. Use when the user asks to assess hook reliability, evaluate why a PreToolUse/PostToolUse/Stop/SessionStart hook failed or blocked a flow, propose hook script or hook-config changes, or follow up on hook incident evidence.
MCP Friction Assessment
This skill should be used after running cortex assess mcp (or the underlying cortex sessions mcpinvestigate pipeline that produces McpIncidentEvidence) to analyze why an MCP tool or server call failed, misfired, or confused the agent. Use when the user asks to assess MCP tool reliability, evaluate why a tool call failed or was misused, propose tool-doc or server-config changes, or follow up on MCP incident evidence.
Searching Sessions
Search and explore AI/Claude/Codex conversation history stored in cortex. Trigger when: the user asks to "search sessions", "find conversations", "what did I work on", "session history", "past conversations", "ask history", "when did I last use X", "show recent sessions", "list AI projects", "what tools have I used"; OR when referencing past work like "we've done this before", "we fixed something similar", "haven't we implemented this", "this was already working", "why did we do that again", "I thought we already solved this"; OR when questioning past decisions like "why did we implement it this way", "what was the reasoning for", "didn't we discuss this already", "this seems familiar"; OR when the user is under the something was done before or wants to find context about previous implementations, fixes, or decisions. Use for session search, conversation discovery, past work retrieval, implementation history, or decision archaeology.
Skill Improvement Assessment
This skill should be used after running cortex assess skill (or the cortex sessions skillinvestigate pipeline that produces PR 3's SkillIncidentEvidence) to analyze whether a Claude Code/Codex/Gemini skill performed well. Use when the user asks to assess skill quality, evaluate why a skill failed or underperformed, propose SKILL.md doc changes, or follow up on skill incident evidence.
Quick start
- Choose your skills. Select individual skills above, or choose the entire pack.
- Copy the install prompt. Use Copy install prompt above the list.
- Send it to your agent. Paste into your coding agent’s chat. Your agent reviews the source and guides the setup.
Try it with your agent
After installation, start with a request like:
Use the Frustration Assessment skill to help with my task.
Ask me for the context you need before getting started.Requirements & license
- A coding agent that can access your project files and install skills.
- Your agent checks each skill’s instructions, dependencies, and permissions during setup.
- Reported license for the skills shown: MIT. The author’s terms apply.