summarize-session
Summarize the current session and generate reusable Claude rules, skills, or commands.
Best use case
summarize-session is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Summarize the current session and generate reusable Claude rules, skills, or commands.
Teams using summarize-session should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/summarize-session/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How summarize-session Compares
| Feature / Agent | summarize-session | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Summarize the current session and generate reusable Claude rules, skills, or commands.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Summarize Session ## Purpose At the end of a productive coding session, analyze the conversation to extract reusable patterns and generate Claude Code artifacts (rules, skills, commands) that can accelerate future work. ## Instructions 1. **Review Session Activity** - What problems were solved? - What code was written or modified? - What workflows were performed? - What decisions were made and why? 2. **Identify Patterns** **Rules Candidates** (coding standards, project conventions): - Repeated code style corrections - Error patterns that were fixed - Best practices established - Project-specific conventions **Skills Candidates** (multi-step workflows): - Complex operations performed multiple times - Sequences of commands that go together - Integration or deployment workflows - Testing or validation procedures **Commands Candidates** (single-action shortcuts): - Frequently used command combinations - Build/test/deploy shortcuts - Common git operations - Project-specific utilities 3. **Generate Artifacts** For each identified pattern, create the appropriate artifact: **Rules** → `.claude/rules/<name>/RULE.md` ```markdown --- name: rule-name description: Brief description --- # Rule Name ## When to Apply ... ## Guidelines ... ``` **Skills** → `.claude/skills/<name>/SKILL.md` ```markdown --- name: skill-name description: Brief description --- # Skill Name ## Instructions 1. Step 1 2. Step 2 ... ``` **Commands** → `.claude/commands/<name>.md` ```markdown # Command Name Description of what this command does. ## Steps 1. ... 2. ... ``` 4. **Validate Artifacts** - Ensure artifacts are general enough to be reusable - Remove session-specific details - Test that instructions are complete and actionable 5. **Document Session Summary** - What was accomplished - What artifacts were generated - Recommendations for next session ## Output Format ```markdown ## Session Summary ### Accomplished - [List of completed tasks] ### Generated Artifacts #### Rules - `<rule-name>`: <description> #### Skills - `<skill-name>`: <description> #### Commands - `<command-name>`: <description> ### Next Steps - [Recommendations for future work] ``` ## Examples ### Example: After Adding a New Adapter **Identified Pattern**: Multi-step process for adding adapters **Generated**: Skill `new-adapter` ### Example: After Fixing Multiple Type Errors **Identified Pattern**: TypeScript strict mode conventions **Generated**: Rule `typescript-conventions` ### Example: After Repeated Test Commands **Identified Pattern**: Test-then-commit workflow **Generated**: Command `test-and-commit`
Related Skills
sessions
Agent Sessions window architecture — covers the sessions-first app, layering, folder structure, chat widget, menus, contributions, entry points, and development guidelines. Use when implementing features or fixing issues in the Agent Sessions window.
session-start
Initialize a new mission with role selection and persona naming
session-start-routine
Execute work session initialization routine at conversation start. Identifies new skills, researches improvements for existing skills, and updates skill library. Triggers automatically at session start.
session-retrospective
Review the current session to extract learnings and propose improvements to CLAUDE.md files and skills. Run at the end of a session or when asked to reflect on what was learned. Routes project-specific learnings to the project CLAUDE.md, universal patterns to the global ~/.claude/CLAUDE.md, and repeated workflows to skill creation/modification proposals. Triggers include "retrospective", "session retro", "振り返って", "何を学んだ?", "セッションの学び", "what did we learn?", "improve from this session".
session-memory
Internal skill. Use cc10x-router for all development tasks.
session-log
Create structured session logs for AI coding/chat sessions. Use when starting a new development session, tracking decisions and context, documenting troubleshooting, or preserving conversation history for future reference.
72-close-session-150
[72] CLOSE. Save and restore session context between conversations. Use when ending a session to preserve progress, or starting a new session to restore context. Triggers on "save session", "end session", "preserve context", "handoff", "continue from last time", or when context window is running low.
cc-get-session-id
Get the current Claude Code session ID. Use when you need to reference or display the session ID.
agent-sessions-layout
Agent Sessions workbench layout — covers the fixed layout structure, grid configuration, part visibility, editor modal, titlebar, sidebar footer, and implementation requirements. Use when implementing features or fixing issues in the Agent Sessions workbench layout.
74-mid-session-save-150
[74] CLOSE. Quick checkpoint during active work when context is running low. Use multiple times per development cycle to preserve progress and lessons. Lighter than close-session — no full handoff needed. Triggers on 'save progress', 'checkpoint', 'context low', or automatically when nearing token limits.
summarize
Summarize or extract text/transcripts from URLs, podcasts, and local files.
session-logs
Search and analyze your own session logs (older/parent conversations) using jq.