Personal Wiki

Turn your LLM into a Wiki maintainer. The LLM incrementally builds and maintains a persistent, interconnected Markdown knowledge base. Knowledge is compiled once and continuously updated, rather than re-derived each time.

This is the key difference from RAG: the wiki is a persistent, compounding artifact. Cross-references are already there. Contradictions have already been flagged. The synthesis already reflects everything you've read. The wiki gets richer with every source added and every question asked.

Division of labor:

• You: curate sources, direct analysis, ask good questions
• LLM: all the bookkeeping — summarizing, cross-referencing, filing, maintaining consistency across pages

Inspired by:

• Karpathy - LLM Wiki — Incremental knowledge base architecture
• Compound Engineering Plugin — Knowledge compounding: every problem-solving experience should make the next one easier

When to Use

The AI should proactively identify and use this skill when:

1. User wants to build a knowledge base — "Help me organize these materials", "I want to create a wiki" / "帮我整理这些材料", "我想建一个知识库"
2. User provides new learning materials — Shares an article, paper, or book chapter that needs organizing / 分享了文章、论文、书籍章节
3. User wants to query existing knowledge — "What did I previously read about this concept?" / "我之前读过关于这个概念的什么内容？"
4. User wants to maintain wiki health — "Check the wiki for contradictions" / "检查一下知识库", "清理一下知识库"
5. User solved a problem — "Done", "Fixed it", "That worked" / "搞定了", "修好了", "解决了"
6. User is doing long-term research — A weeks- or months-long research topic requiring gradual knowledge accumulation

When NOT to use:

• One-off Q&A that doesn't need persistent knowledge

Entry Point

Language policy: The user may communicate in English or Chinese. Always respond in the same language the user used. Wiki page filenames and frontmatter fields always remain in English. Wiki page body content follows the language of the primary source document: if the source is predominantly Chinese, write the page body in Chinese; if predominantly English, write in English. Mixed-source pages default to English.

Step 1: Determine User Intent

Based on what the user says, determine which operation to execute:

User Intent	Operation
"Create a knowledge base", "Initialize wiki" / "创建知识库", "初始化 Wiki"	init
"Help me process this article", "I have new materials", "Check out this link" / "帮我处理这篇文章", "我有新材料", "看看这个链接"	ingest
"Done", "Fixed it", "Problem solved" / "搞定了", "修好了", "解决了", "我发现了一个规律"	compound
"What is X?", "Summarize Y for me" / "X 是什么？", "帮我总结一下 Y"	query
"Check the wiki", "Clean up the knowledge base" / "检查一下知识库", "清理知识库"	lint
Intent unclear	Ask user to choose

When intent is unclear, ask (in the user's language):

# English
Which operation would you like to run?
  1. init     - Initialize knowledge base
  2. ingest   - Ingest new materials
  3. compound - Document problem-solving experience
  4. query    - Query existing knowledge
  5. lint     - Health check

# 中文
你想执行哪个操作？
  1. init     - 初始化知识库
  2. ingest   - 录入新材料
  3. compound - 记录解题经验
  4. query    - 查询已有知识
  5. lint     - 健康检查

Step 2: Check if Initialized

Before any operation (except init itself), check if the wiki exists:

• Exists → Proceed with the target operation
• Does not exist → Auto-execute init first without asking, then proceed with the target operation

ls ~/Personal_wiki/wiki/index.md 2>/dev/null

---

Operation: init

When to Execute

• User explicitly requests initialization
• Auto-executed when ~/Personal_wiki/wiki/ doesn't exist before other operations

Workflow

1. Create Directory Structure

mkdir -p ~/Personal_wiki/raw/{articles,papers,books,notes,assets,misc}
mkdir -p ~/Personal_wiki/wiki/{entities,concepts,topics,sources,solutions}

Adjust raw/ subdirectories based on knowledge base topics mentioned in prior conversation. misc/ is always created as a catch-all for uncategorized materials.

2. Create index.md

index.md is content-oriented: a catalog of every page with a one-line summary, organized by category. The LLM reads this first on every query to locate relevant pages without scanning all files.

# Wiki Index

## Overview
- [[overview]] - Overall summary and key findings

## Sources
<!-- Ingested raw material summaries — format: - [[YYYY-MM-DD-name]] - one-line description, sorted by date descending -->

## Entities
<!-- People, organizations, products — format: - [[name]] - one-line description, sorted by name -->

## Concepts
<!-- Theories, methods, terminology — format: - [[concept-name]] - one-line description, sorted by name -->

## Topics
<!-- Synthesized analyses, comparisons, explorations — format: - [[topic-name]] - one-line description, sorted by name -->

## Solutions
<!-- Problem-solving experiences (compound) — format: - [[YYYY-MM-DD-name]] - one-line description, sorted by date descending -->

3. Create log.md

log.md is chronological: an append-only record of all operations. Each entry uses a consistent prefix so it's grep-parseable.

# Wiki Log

<!-- Append entries chronologically. Format: ## [YYYY-MM-DD] operation 
- description 1 
- description 2 
.. -->
<!-- grep "^## \[" log.md | tail -5   →  last 5 operations -->

4. Create overview.md

---
type: overview
created: YYYY-MM-DD
---

# Knowledge Base Overview

> This Wiki is automatically maintained by LLM. You handle topic selection and questions; the LLM handles summarization, cross-referencing, archiving, and maintenance.

## Current Status
- Source count: 0
- Total pages: 0 (including index, log, overview)
- Last updated: -

## Evolving Thesis
<!-- The most important synthesis and emerging conclusions across all sources -->

## Key Findings
<!-- Specific high-value facts, patterns, or insights discovered so far -->

## Open Questions
<!-- Gaps identified — topics to explore, sources to find, contradictions to resolve -->

5. Output Confirmation

Wiki knowledge base initialized! ~/Personal_wiki/

Next steps:
  - Put materials in raw/, I'll organize them (ingest)
  - Give me a link or text, I'll save and process it (ingest)
  - Tell me when you've solved a problem, I'll document it (compound)
  - Ask me about existing knowledge in the Wiki anytime (query)
  - Let me check the Wiki's health (lint)

If auto-initialized (not user-initiated), simplify output to one line: Auto-initialized knowledge base ~/Personal_wiki/, then proceed with the target operation.

---

Operation: ingest

Process new raw materials and integrate knowledge into the Wiki. A single new material may affect 10–15 Wiki pages.

Workflow

1. Determine Materials to Process

By priority:

1. User specified specific material (link, text, file path) → Process only that material
2. User says "process new materials" → Scan raw/ for unprocessed files
3. User says "process all new materials" → Batch process

Determining processed/unprocessed: Compare raw/ files against the source frontmatter field in wiki/sources/. A corresponding summary page = processed.

Found 3 unprocessed materials:
  1. raw/articles/attention-paper.pdf
  2. raw/notes/meeting-2026-04-05.md
  3. raw/papers/bert-paper.pdf

Process all, or select specific ones? (Default: all)

2. Save Raw Materials (URL/text only)

• URL → Fetch and save to raw/articles/
• Text → Save to raw/notes/
• Existing file → Read directly

3. Read and Extract

Read the raw material, identifying: core arguments, key entities, important concepts, data/facts, and relationships to existing wiki content.

PDF Rule: Always use the PDF skill (~/.agents/skills/pdf which is available at https://github.com/anthropics/skills/tree/main/skills/pdf) to process PDF files. For scanned/image-based PDFs that return little or no text from pdftotext, use OCR via pytesseract + pdf2image (as provided by the skill). Never skip a PDF because it appears empty — always attempt OCR first.

import pytesseract
from pdf2image import convert_from_path
images = convert_from_path('scanned.pdf', dpi=200)
text = "\n".join(pytesseract.image_to_string(img) for img in images)

Image Rule: LLMs can't read markdown with inline images in one pass. When processing a source with images, first extract all text using the ~/.agents/skills/image-ocr skill, and metadata, then view the referenced images separately to extract information. Don't let the presence of images prevent you from processing the text content.

4. Discuss with User (Recommended; skip for batch processing)

Core points of this material:
1. ...
2. ...

Key entities/concepts involved: A, B, C
Which aspects would you like to focus on?

5. Create Source Summary Page

Create in wiki/sources/, filename: YYYY-MM-DD-short-name.md

---
type: source
date: YYYY-MM-DD
source: raw/path/to/file
tags: [tag1, tag2]
---

# Source: Title

## Key Points
- Point 1

## Key Quotes
> Original quote

## Relationships to Other Sources
- Corroborates [[other-source]] on X
- Contradicts [[contradicting-source]] on Y

## Derived Concepts
- [[concept-a]]

6. Update Entity and Concept Pages

For each entity and concept mentioned in the material:

• Existing page → Append new information, cite source
• New page → Create using template

Entity/concept page template:

---
type: entity  # or concept
created: YYYY-MM-DD
updated: YYYY-MM-DD
sources: [source-a, source-b]
---

# Name

## Definition
Brief description.

## Key Information
- Info point 1 (Source: [[source-a]])

## Relations
- Related concepts: [[concept-x]]

## Open Questions
- Unanswered questions

Note:

• When new information contradicts existing content, keep both versions with clear annotations
• Every factual claim must cite its source

7. Update Topic Pages (if needed)

8. Update index.md, overview.md

Update index.md with new/changed pages (one-line summaries). Update overview.md's evolving thesis and key findings if anything significant changed.

9. Append to log.md

## [YYYY-MM-DD] ingest | Material Title

- **Source**: raw/path/to/file
- **New pages**: page-a, page-b
- **Updated pages**: page-c, page-d
- **Impact scope**: N pages

10. Output Summary

Processing complete.

New:
  - Source summary: [[source-name]]
  - Entities: [[entity-a]], [[entity-b]]
  - Concepts: [[concept-c]]

Updated:
  - [[concept-d]] - Added details about X

Warning - Contradictions found:
  - Description of Y in [[concept-d]] is inconsistent with [[source-old]]

---

Operation: compound

Document problem-solving experiences into wiki/solutions/. Knowledge compounding: invest time researching once, document it, solve it in minutes next time.

When to Execute

• User says "Done", "Fixed it", "Problem solved" / "搞定了", "修好了", "解决了"
• User just finished a debugging session, investigation, or analysis and the outcome is worth preserving
• User discovered a pattern, trick, or best practice worth recording / "我发现了一个规律", "有个经验想记录一下"

Not worth recording: Typos, obvious minor fixes, one-off non-reproducible issues. Just tell the user why.

Dual Tracks

Bug Track (Problem Resolution): For fixing bugs, resolving errors.

---
type: solution
track: bug
date: YYYY-MM-DD
tags: [tag1, tag2]
---

# Problem Title

## Problem
1-2 sentence description.

## Symptoms
- Observable abnormal behavior

## Investigation
1. ❌ Attempt A → Reason for failure
2. ✅ Final solution

## Root Cause
Explanation of the cause.

## Solution
\`\`\`
// Before
...
// After
...
\`\`\`

## Prevention
How to avoid recurrence.

## Relations
- [[concept-a]]

Knowledge Track (Insights): For summarizing patterns, best practices, workflow tips.

---
type: solution
track: knowledge
date: YYYY-MM-DD
tags: [tag1, tag2]
---

# Insight Title

## Background
Context in which this experience was gained.

## Guidance
Specific practices, patterns, or recommendations.

## Why It Matters
Impact of following or not following this practice.

## When to Apply
Conditions under which this experience applies.

## Relations
- [[concept-a]]

Workflow

1. Extract information from context — Problem description, investigation process, root cause, solution, key code
2. Choose track — Solved a specific problem → Bug Track; Summarized experience/pattern → Knowledge Track
3. Check for overlap — Search wiki/solutions/ for similar documents. High overlap → Update existing; Low or none → Create new
4. Write document — wiki/solutions/YYYY-MM-DD-short-name.md
5. Update index.md, overview.md, log.md
6. Output summary

---

Operation: query

Answer questions based on Wiki content. Good answers are filed back into the wiki — explorations compound just like ingested sources.

Core Principle

Never re-derive from the wiki what can simply be read from it. And never let a valuable synthesis vanish into chat history — if the answer required multi-source reasoning, a comparison, or a new discovery, save it.

Workflow

1. Read index.md first — get the full map of what exists; identify the 2–5 most relevant pages
2. Read relevant pages — drill into sources, concepts, topics, and solutions pages
3. Synthesize answer — cite with [[wikilink]], annotate sources
4. Archive valuable answers — if the answer involved multi-source synthesis, a comparison table, or a new connection, save to wiki/topics/ as a new page and add to index.md
5. Suggest further exploration — flag information gaps, contradictions noticed, or sources worth finding

Output Formats

Answers can take different forms depending on the question:

• Standard markdown response with [[wikilink]] citations
• Comparison table
• Slide deck (Marp format, if requested)
• Chart (matplotlib script, if requested)

---

Operation: lint

Detect contradictions, orphan pages, stale claims, and other issues to maintain long-term Wiki health.

When to Execute

• User says "check the wiki", "clean up the knowledge base" / "检查一下知识库", "清理知识库"
• Periodically when the wiki accumulates 20+ pages
• After ingesting a batch of important materials

6 Checks

Check	Method
Contradiction detection	Compare descriptions of the same topic across different pages; flag conflicting claims
Stale content	Pages whose updated date predates a newer source on the same topic — claims may have been superseded
Orphan pages	Pages with 0 inbound [[wikilink]] references
Missing pages	Linked via [[wikilink]] but the target file does not yet exist
Missing cross-references	Pages sharing 2+ sources but not linked to each other
Data gaps	"Open questions" on concept pages; unexplored directions noted in overview

Workflow

1. Read full picture: ls -R wiki/ + read wiki/index.md
2. Run each check
3. Generate report: statistics + issues listed by priority (High / Medium / Low)
4. Ask user whether to auto-fix (create missing pages, add cross-references, etc.)
5. Execute fixes, append to log.md

Note: Process each file in raw/ only once and remember that.

---

Three-Layer Architecture

~/Personal_wiki/
│
├── README.md               ← Schema (this file): conventions, workflows, page formats
│                             The LLM reads this to behave as a disciplined wiki maintainer.
│                             Co-evolve with the LLM as your domain develops.
│
├── raw/                    ← Raw sources (immutable — LLM reads, never modifies)
│   ├── articles/
│   ├── papers/
│   ├── books/
│   ├── notes/
│   ├── assets/
│   └── misc/               # Uncategorized materials — drop anything here without sorting
│
└── wiki/                   ← LLM-maintained Wiki (LLM writes everything here)
    ├── index.md            # Content catalog — read first on every query
    ├── log.md              # Append-only operation log — grep-parseable
    ├── overview.md         # Evolving synthesis and key findings
    ├── entities/           # Organisations, products, places
    ├── persons/            # Individual people (auto-created when mentioned >10 times)
    ├── concepts/           # Theories, methods, terminology
    ├── topics/             # Synthesized analyses, comparisons
    ├── sources/            # Source summary pages
    └── solutions/          # Compound: bug fixes and insights

The wiki is a plain git repo of markdown files — you get version history, branching, and diffs for free.

File Naming Convention

Type	Path Format
Source summary	wiki/sources/YYYY-MM-DD-short-name.md
Entity page	wiki/entities/name.md
Person page	wiki/persons/firstname-lastname.md
Concept page	wiki/concepts/concept-name.md
Topic page	wiki/topics/topic-name.md
Solution document	wiki/solutions/YYYY-MM-DD-short-name.md

All filenames use lowercase English with hyphens.

Writing Standards

• Start each page with YAML frontmatter (type, date, tags, sources)
• Use [[wikilink]] for all inter-page references
• Cite sources for every factual claim
• When new and old information contradict, keep both versions annotated — never silently overwrite
• Keep pages concise and focused on one topic

Person Pages (wiki/persons/)

• Trigger: automatically create wiki/persons/firstname-lastname.md when a person is mentioned more than 10 times across all wiki content (sources, entities, topics, concepts)
• Content: biography summary, known roles, relationships, key facts, open questions — all sourced from ingested material
• Language: follows the dominant language of sources mentioning this person
• Filename: lowercase English with hyphens, e.g. jacky-chen.md, michael-jordan.md
• During ingest/compound: count mentions mentally; if a person crosses the threshold, create the page immediately

Obsidian Integration

Open ~/Personal_wiki/ directly as an Obsidian vault.

Useful setup:

• Graph View — see the shape of your wiki; identify hubs and orphans visually
• Obsidian Web Clipper (browser extension) — converts web articles to markdown; fastest way to get sources into raw/
• Download attachments — In Settings → Files and links, set attachment folder to raw/assets/. Bind "Download attachments for current file" to a hotkey (e.g. Ctrl+Shift+D) so clipped images are saved locally
• Dataview plugin — queries over YAML frontmatter; generates dynamic tables from type, date, tags, sources fields
• Marp plugin — render wiki/topics/ pages as slide decks directly from markdown

Note on images: LLMs can't read markdown with inline images in one pass. Workaround: have the LLM read the text first, then view referenced images separately.

Tips & Tricks

• Ingest one source at a time when quality matters — stay involved, read summaries, guide emphasis. Batch ingest when volume matters more.
• File good query answers back — a comparison you asked for, an analysis, a connection you spotted. Don't let them disappear into chat history.
• Log is grep-parseable — grep "^## \[" wiki/log.md | tail -10 gives the last 10 operations at a glance.
• Search at scale — the index file works well up to ~100 sources / hundreds of pages. Beyond that, consider qmd: local hybrid BM25/vector search for markdown with both a CLI and MCP server.
• overview.md is the thesis — treat "Evolving Thesis" as a living synthesis that sharpens as sources accumulate, not just a status field.
• Schema is co-evolved — update this README as you develop conventions for your domain. Future sessions inherit your accumulated workflow knowledge.

Examples

ingest (English)

User: I put the Attention Is All You Need paper in raw/papers/

Agent: I'll process this paper.

[Reads raw/papers/attention-is-all-you-need.pdf]
[Extracts key information]

Core points of this paper:
1. Proposed the Transformer architecture, entirely based on attention mechanisms, abandoning RNN/CNN
2. Introduced Multi-Head Self-Attention and Positional Encoding
3. Achieved SOTA on machine translation tasks

Entities involved: Google Brain, Ashish Vaswani and 7 other authors
Concepts involved: Self-Attention, Multi-Head Attention, Positional Encoding, Layer Normalization

Which aspects would you like to focus on?

User: Focus on the design rationale behind Self-Attention

Agent: [Creates wiki/sources/2026-04-06-attention-paper.md]
[Creates wiki/concepts/self-attention.md - Focuses on design rationale]
[Creates wiki/entities/transformer.md]
[Creates wiki/entities/google-brain.md]
[Creates wiki/concepts/multi-head-attention.md]
[Creates wiki/concepts/positional-encoding.md]
[Updates wiki/overview.md]
[Updates wiki/index.md]
[Appends to wiki/log.md]

Processing complete. 6 new pages created. The Self-Attention concept page focuses on the design motivation behind Scaled Dot-Product.

ingest (中文)

用户：我把《注意力机制》的论文放到 raw/papers/ 了

Agent：好的，我来处理这篇论文。

[读取 raw/papers/attention-is-all-you-need.pdf]
[提取关键信息]

这篇论文的核心要点：
1. 提出了完全基于注意力机制的 Transformer 架构，放弃了 RNN/CNN
2. 引入了多头自注意力（Multi-Head Self-Attention）和位置编码（Positional Encoding）
3. 在机器翻译任务上达到了 SOTA 效果

涉及的实体：Google Brain、Ashish Vaswani 等 8 位作者
涉及的概念：Self-Attention、Multi-Head Attention、Positional Encoding、Layer Normalization

你希望重点关注哪些方面？

用户：重点关注 Self-Attention 的设计思路

Agent：[创建 wiki/sources/2026-04-06-attention-paper.md]
[创建 wiki/concepts/self-attention.md — 聚焦设计思路]
[创建 wiki/entities/transformer.md]
[创建 wiki/entities/google-brain.md]
[创建 wiki/concepts/multi-head-attention.md]
[创建 wiki/concepts/positional-encoding.md]
[更新 wiki/overview.md]
[更新 wiki/index.md]
[追加到 wiki/log.md]

处理完成，新建 6 个页面。Self-Attention 概念页聚焦于 Scaled Dot-Product 背后的设计动机。

compound (English — Bug Track)

User: Fixed it, it was a database connection pool configuration issue

Agent: This is worth documenting. Let me organize it.

[Reviews conversation context]
[Checks wiki/solutions/ for overlap]
[Creates wiki/solutions/2026-04-06-db-connection-pool-exhausted.md]

Experience documented. Bug Track.

Summary:
  Problem: Database connection pool exhaustion under high concurrency, causing request timeouts
  Root cause: Default pool size of 5 was too small; no idle timeout recycling was configured
  Solution: Increased pool size to 20, added idle timeout configuration

Linked to existing [[database-connections]] concept page in the Wiki.

compound (中文 — Knowledge Track)

用户：我发现处理搜索输入时，用 debounce 比 throttle 效果更好

Agent：好的，这个经验值得记录下来。

[创建 wiki/solutions/2026-04-06-debounce-vs-throttle-search.md]
[检查是否有相关概念页]

经验已记录。Knowledge Track。

核心建议：搜索输入场景应使用 debounce（等待用户停止输入后触发），
而非 throttle（按固定间隔触发），因为搜索需要完整的关键词。

Wiki 中暂无 debounce 和 throttle 的概念页，要顺手创建吗？

query (English)

User: What's the difference between Self-Attention and regular Attention?

Agent: [Reads wiki/index.md]
[Locates wiki/concepts/self-attention.md, wiki/concepts/attention.md]
[Synthesizes answer]

## Self-Attention vs Regular Attention

**Regular Attention** (Source: [[source-a]]):
- Query and Key/Value come from different sequences
- Typical scenario: target language attending to source language in translation

**Self-Attention** (Source: [[2026-04-06-attention-paper]]):
- Query, Key, and Value all come from the same sequence
- Each position can attend to all other positions in the sequence

| Dimension | Regular Attention | Self-Attention |
|-----------|-------------------|----------------|
| Q/K/V Source | Q ≠ KV | Q = K = V |
| Captures | Cross-sequence | Within-sequence |
| Complexity | O(n×m) | O(n²) |

This comparison has been saved as [[self-attention-vs-attention]].

query (中文)

用户：Self-Attention 和普通 Attention 有什么区别？

Agent：[读取 wiki/index.md]
[定位 wiki/concepts/self-attention.md、wiki/concepts/attention.md]
[综合整理答案]

## Self-Attention vs 普通 Attention

**普通 Attention**（来源：[[source-a]]）：
- Query 和 Key/Value 来自不同的序列
- 典型场景：翻译任务中目标语言关注源语言

**Self-Attention**（来源：[[2026-04-06-attention-paper]]）：
- Query、Key、Value 均来自同一序列
- 每个位置都可以关注序列中的所有其他位置

| 维度 | 普通 Attention | Self-Attention |
|------|----------------|----------------|
| Q/K/V 来源 | Q ≠ KV | Q = K = V |
| 捕捉关系 | 跨序列 | 序列内部 |
| 复杂度 | O(n×m) | O(n²) |

该对比已保存为 [[self-attention-vs-attention]]。

lint (中文)

用户：帮我检查一下知识库

Agent：[读取 wiki/index.md]
[扫描所有 wiki/ 页面]

Wiki 健康报告 — 2026-04-06
页面总数：12 | 来源：3 | 概念：6 | 实体：2 | 主题：1

#### 陈旧内容（1 处）
1. [[positional-encoding]] 上次更新早于 [[2026-04-06-rope-paper]] 的录入时间，内容可能已过时

#### 孤立页面（1 处）
1. [[layer-normalization]] — 无任何页面引用

#### 缺失页面（2 处）
1. [[residual-connection]] — 被引用 4 次
2. [[softmax]] — 被引用 2 次

### 建议操作
1. [高优] 创建 [[residual-connection]]（被引用 4 次）
2. [高优] 创建 [[softmax]]（被引用 2 次）
3. [中优] 对照 [[2026-04-06-rope-paper]] 审查 [[positional-encoding]]
4. [低优] 为 [[layer-normalization]] 添加入站引用

要自动修复吗？

用户：先处理 1 和 2

Agent：[创建 wiki/concepts/residual-connection.md]
[创建 wiki/concepts/softmax.md]
[更新 wiki/index.md]
[追加到 wiki/log.md]

已创建：
- [[residual-connection]] — 基于 [[attention-paper]] 中的描述
- [[softmax]] — 作为 Self-Attention 中的关键计算步骤

3 和 4 留待你准备好后再处理。

Use Cases

Active Learning (ingest):

• Academic research, reading notes, competitive analysis, course notes, book reading (build a companion wiki chapter by chapter)

Experience Accumulation (compound):

• Engineering practices (bug fixes, best practices), team knowledge base, workflow optimization, personal growth

Personal / Long-term:

• Health and self-improvement journals, goal tracking, psychology notes — build a structured picture of yourself over time