Bottle
Bootstrap a new or existing project with a small, file-based documentation system so Claude Code keeps context, lessons, and decisions across session restarts instead of starting cold every time. Sets up a handful of markdown files under .claude/ (standing rules, a free-form note to your next session, a phased roadmap, a prioritized backlog, and searchable history/changelog archives) sized and split so the files read every session stay small while the archives grow without ever costing context. Use this whenever someone is starting a new project and asks how to structure it for long-running AI
Install
npx skills add Simooo45/bottle --skill bottlegit clone --depth 1 https://github.com/Simooo45/bottle.git /tmp/bottle
mkdir -p ~/.claude/skills
cp -r /tmp/bottle/. ~/.claude/skills/bottlePersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Bottle A message in a bottle: something you write for a future reader you'll never meet in person, because by the time they read it you'll have no memory of writing it. That's exactly the situation every new Claude Code session is in. This skill sets up a small, plain-markdown system so each session can read a short, cheap briefing and pick up real continuity, without either side needing to reread the whole project history. ## The problem this solves A coding session has two things in tension: it needs the context window to stay small (long context costs money and attention), and it needs to remember what past sessions learned (or it repeats the same mistakes and re-asks the same questions). Chat history alone doesn't survive a restart. A single giant NOTES.md doesn't survive success either, it just grows until reading it in full is too expensive to keep doing every session. The fix is a **two-tier split**: - A **small set of files, capped in size, read in full every session.** These carry only what a future session actually needs: standing rules, a short free-form note, the current roadmap. Because they're small and read every time, they can be trusted without re-deriving anything. - **Archive files that grow without bound and are never read in full.** Full history lives here, searchable by keyword/ID/date. Nobody pays the cost of that size except the rare session that actually needs to dig up one old detail.
Details
- Skill name
bottle- Repository
- Simooo45/bottle
- License
- MIT
- Repo updated
- 4 September 2026
FAQ
What does the Bottle skill do?
Bootstrap a new or existing project with a small, file-based documentation system so Claude Code keeps context, lessons, and decisions across session restarts instead of starting cold every time. Sets up a handful of markdown files under .claude/ (standing rules, a free-form note to your next session, a phased roadmap, a prioritized backlog, and searchable history/changelog archives) sized and split so the files read every session stay small while the archives grow without ever costing context. Use this whenever someone is starting a new project and asks how to structure it for long-running AI
How do I install the Bottle skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add Simooo45/bottle --skill bottle. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Bottle popular?
It lives in Simooo45/bottle, which has 8 GitHub stars and 0 forks.
Related skills
Changshu Arnold
8factnn/changshu-arnold-skill
当用户提到"常熟阿诺"、"诺神"、"诺言诺语"、"那我问你"、"三卡车"、"生米冲碳"、"申气"、"脑袋尖尖"、"无糖可乐"、健身抽象梗时自动触发。将 Claude 变成常熟阿诺风格，用诺言诺语系统回答。即使用户只是随口提到这些词，也应该触发此 skill。
Aivc
7Pengzhi-Gao/aivc-skill
面向单细胞和 bulk 转录组的虚拟基因敲除、虚拟基因过表达与虚拟药物筛选流程 skill。当用户希望用已有数据运行虚拟干预、预测药物转录响应、生成逐基因/网络/embedding 结果、绘图或整理运行产物时使用。开始新分析时必须先请用户指定分析数据、分析目录、运行环境、KO/OE/药筛任务、模型及目标基因或药物库，缺项先问；Skill 完成输入检查、后端执行、结果标准化和文件交付。
Genpark Autonomous Personal Delegator Skill
8Alpha-Park/genpark-autonomous-personal-delegator-skill
GenPark AI Agent Skill - Autonomous micro-action delegation with user guardrails, confidence thresholding, dry-run previews, and token budget gating.
Marinara Engine Expert
7cha1latte/marinara-engine-expert-skill
Expert for Marinara Engine (the local AI roleplay/chat frontend at github.com/Pasta-Devs/Marinara-Engine). Handles two kinds of work — IDEATION (designing characters, lorebooks, custom tools, agents, extensions for users building things in Marinara) and CONTRIBUTION (triaging PRs, reproducing bugs, and shipping focused changes to the Marinara codebase itself). Use this skill when the user mentions Marinara Engine, Professor Mari, SpicyMarinara, or describes a project involving AI characters, chatbots, roleplay assistants, or personas they want to build in a Marinara-Engine-style system. Also t
Genpark Claude Code Conversation Archiver Skill
8Alpha-Park/genpark-claude-code-conversation-archiver-skill
Deterministic conversation turn archiver and session ledger with automated Git indexing and clean Markdown export.
Global Think Tank Analyst
7vassiliylakhonin/global-think-tank-analyst
Strategic-risk analysis skill for AI agents producing decision-ready memos on geopolitics, sanctions, trade, regulation, and strategic risk with explicit evidence boundaries, uncertainty, scenarios, actor incentives, trade-offs, and watch-next indicators. Use for a country risk brief, policy memo, sanctions or export-control exposure assessment, trade or regulatory implications memo, geopolitical scenario brief, strategic implications note for leadership, stakeholder and incentives analysis, a red-team challenge to an existing policy or risk view, or a decision briefing pack for founders, oper
Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.