session-analysis
Skill1 starsChanged 2 months agoNo licenceView on GitHub
Mine this Claude Code project's own session transcripts (~/.claude/projects/<slug>/*.jsonl) for a specific analysis job, selected by a mode argument, e.g. `/session-analysis dream`. Currently implements one mode, `dream`, which extracts durable learnings worth promoting to long-term memory (repeated mistakes, user corrections, stated preferences, decisions that stuck) from the 10 most recent transcripts. Use when the user asks to review past sessions for lessons, patterns, recurring mistakes, or things that should be remembered, or types `/session-analysis`. Not for reading a single named transcript for its task content (just open the file), not for anything that needs a session older than the 10 most recent (raise that with the user first: the cap is deliberate, see §2.1), and not for writing the extracted candidates into MEMORY.md yourself; this skill stops at a reviewable list.
In this repository17 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- agent-styleSkill
- benchmark-code-graphsSkill
- bug-reportSkill
- claims-and-scope-disciplineSkill
- context7-mcpSkill
- dreamSkill
- dual-scoped-review-plansSkill
- git-worktree-topologySkill
- improve-memorySkill
- plan-and-reviewSkill
- plan-docsSkill
- plan-rolloutSkill
- reviewSkill
- root-cause-fixSkill
- send-resultsSkill
The file
We split this skill into the rules it gives an agent
10 rules. About 0 are common, 6 are distinctive, and 4 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈6
Distinctive · estimate
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
No licence file, so all rights are reserved — read it at the source. We count its rules but don't quote them. Read them on GitHub.
≈ “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.
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.