Help us improve
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
Share bugs, ideas, or general feedback.
By sametbrr
Save conversation checkpoints as markdown files and resume them later with full context
npx claudepluginhub sametbrr/skill-hub --plugin look-againA 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.
Share bugs, ideas, or general feedback.
Based on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Plugin-safe Claude Code distribution of Antigravity Awesome Skills with 1,495 supported skills.
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
Harness-native ECC plugin for engineering teams - 64 agents, 262 skills, 84 legacy command shims, reusable hooks, rules, MCP conventions, and operator workflows for Claude Code plus adjacent 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
Personal 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
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge.
Sign in to claim