By sametbrr
Save conversation checkpoints as markdown files and resume them later with full context
A Claude Code skill that saves conversation checkpoints as markdown files and resumes them later with full context — decisions, rejected alternatives, and the final plan preserved verbatim.
🇹🇷 Türkçe için README.tr.md
git clone https://github.com/sametbrr/look-again ~/.claude/skills/look-again
> "look again" # save the current state as a checkpoint
> "look again list" # list saved checkpoints, pick one to continue
That's it — entries land in ~/.claude/look-again/ and survive between sessions.
.md files (no persistent disk)git clone https://github.com/sametbrr/look-again ~/.claude/skills/look-again
Start a new Claude Code session. The skill loads automatically when you mention saving or resuming a checkpoint.
The skill detects the mode from natural language — Turkish or English:
| Mode | Trigger examples | What happens |
|---|---|---|
| SAVE | "look again", "tekrar bak", "save this for later", "bunu kaydet" | Writes a checkpoint file: context snapshot + final plan + last exchange verbatim |
| RECALL | "look again list", "tekrar bakacaklarım nelerdi", "continue where we left off" | Lists entries newest-first; pick one to switch into continuation mode |
Entries are named YYYY-MM-DD-HHmm-<topic-slug>.md and follow assets/entry-template.md. In continuation mode the assistant adopts the saved context, never re-proposes rejected alternatives, and continues from the saved next steps.
On Claude.ai the sandbox filesystem resets between conversations, so checkpoints cannot persist server-side.
Workaround: SAVE presents the entry as a downloadable file — keep it locally (e.g. in ~/.claude/look-again/) and upload it back to a future chat to RECALL.
MIT — see LICENSE.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub sametbrr/skill-hub --plugin look-againPersonal LLM-managed wiki: ingest sources, cross-reference pages, query with citations, and lint your markdown knowledge base
Turns any rough request into a structured, domain-aware expert prompt with an 8-gate quality review
Full programmatic access to Google NotebookLM: notebooks, sources, podcasts, videos, quizzes, flashcards and more
Daily Turkish HTML radar report of trending and talked-about projects, with a persistent watchlist
Enforces a consistent README.md + README.tr.md structure: create, audit, fix and TR-sync modes
Plugin-safe Claude Code distribution of Antigravity Awesome Skills with 1,561 supported skills.
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
Harness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current.
Reliable automation, in-depth debugging, and performance analysis in Chrome using Chrome DevTools and Puppeteer