summarize-session
Skill37 starsChanged 9 months agoUnlicenseView on GitHub
Summarize the current session and generate reusable Claude rules, skills, or commands.
In this repository8 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .claude/CLAUDE.mdCLAUDE.md
- .cursor/rules/knowledge-base/RULE.mdCursor rule
- .cursor/rules/project/RULE.mdCursor rule
- new-adapterSkill
- sync-readmeSkill
- update-docsSkill
- update-knowledge-baseSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 87
Ensure artifacts are general enough to be reusable
- Distinctive: line 89
Test that instructions are complete and actionable
- Distinctive: line 133
Identified Pattern: Test-then-commit workflow
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
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
- Review Session Activity
- What problems were solved?
- What code was written or modified?
- What workflows were performed?
- What decisions were made and why?
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
Generate Artifacts
For each identified pattern, create the appropriate artifact:
Rules →
.claude/rules/<name>/RULE.md--- name: rule-name description: Brief description --- # Rule Name ## When to Apply ... ## Guidelines ...Skills →
.claude/skills/<name>/SKILL.md--- name: skill-name description: Brief description --- # Skill Name ## Instructions 1. Step 1 2. Step 2 ...Commands →
.claude/commands/<name>.md# Command Name Description of what this command does. ## Steps 1. ... 2. ...- Validate Artifacts
- Ensure artifacts are general enough to be reusable
- Remove session-specific details
- Test that instructions are complete and actionable
- Document Session Summary
- What was accomplished
- What artifacts were generated
- Recommendations for next session
Output Format
## 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
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

