Chewbacca / hud
calebnewtonusc/Chewbacca/hud/CLAUDE.md
label":"Model","tone":"warn"}] ``` - **File** Shows an actual file: a PDF through the system's PDF engine, an image as an image, anything that decodes as text as text
How real projects brief Claude Code: the commands, conventions and warnings they put in CLAUDE.md.
calebnewtonusc/Chewbacca/hud/CLAUDE.md
label":"Model","tone":"warn"}] ``` - **File** Shows an actual file: a PDF through the system's PDF engine, an image as an image, anything that decodes as text as text
dabodamjan/poster-maker/CLAUDE.md
design principles, font pairings, and image handling. - `/export-poster` — export a poster to PNG or PDF using Playwright. - `/remove-bg` — remove background from an image using rembg (Python). Installs on first
danielrosehill/Claude-ADHD-Research-Workspace/CLAUDE.md
read it. Sometimes I like to package up a lot of outputs into a PDF and print it to read over the weekend. For the latter, I have a workflow
deepdotspace/TexPal/CLAUDE.md
implementation of the same app. Users write LaTeX in a CodeMirror editor, compile to PDF via a cloud compiler, and can ask an AI assistant to create/edit files for them
dharmamitra/dharmamitra-claude-code-agent/CLAUDE.md
glossaries, named-entity lists, register notes. Plain text and Markdown work directly. For .docx, .pdf, .epub, use the **reference-reader** subagent to extract them first. 2. **Build a translation brief
hoanghd218/claude-code-2-days/CLAUDE.md
truth is `heygen-com/hyperframes`. 2. **Anthropic-published** — e.g. `canvas-design`, `brand-guidelines`, `docx`, `pdf`, `pptx`, `xlsx`, `frontend-design`, `mcp-builder`, `skill-creator`, `web-artifacts-builder`, `webapp-testing`, `algorithmic
LARi-UQAC/ResearchTools/.claude/CLAUDE.md
running | `obsidian-cli` skill, `vault_daemon.py` | `python vault_daemon.py` (add `--once`, `--drain`) | | Fetch an official PDF form (any institution) over https with the validated ingest contract (scheme re-checked on every redirect
LarouexNonprofitConsulting/larouex-fullstack-plugin/.claude/CLAUDE.md
/add-chat` - Real-time chat - `/add-calendar` - Calendar component - `/add-maps` - Map integration - `/add-charts` - Data visualization - `/add-pdf-generator` - PDF generation **Jobs & Automation** - `/add-background-job` - Background processing - `/add-cron-azure` - Scheduled jobs (Azure) - `/add-cron-railway` - Scheduled jobs (Railway) - `/add-queue
Littlpinguin/marketing-cockpit-template/05-web-content/CLAUDE.md
design web {{COMPANY_NAME}} ## Rôle Vous produisez les **landing pages**, les **lead magnets** (guides PDF, outils interactifs, quiz, templates) et les **pages statiques** qui vivent hors du CMS du blog
Littlpinguin/marketing-cockpit-template/06-graphic-design/CLAUDE.md
infographics, on-brand AI imagery. 2. **Presentations** — editorial-grade HTML decks for live projection, PDF export, or web sharing. 3. **Mail signatures** — HTML signatures for team members. All three share
Littlpinguin/marketing-cockpit-template/CLAUDE.md
brand/assets/` first | | `slides` | Editorial-grade HTML presentations | 1920×1080 frame, Playwright QA, clean PDF export | | `carousel` | LinkedIn carousels (PDF 1080×1350) | Strict type/spacing scales, export pipeline | | `brandkit` | Brand boards & identity
modu-ai/moai-studio/CLAUDE.md
template-only sync | ### Reading Large PDFs When agents need to analyze large PDF files (>10 pages), use the `pages` parameter: ``` Read /path/to/doc.pdf pages: "1-20" ``` Large PDFs (>10 pages) return
olosegres/telegramcode/CLAUDE.md
# TelegramCode — project guide > Shared rules live in `~/src/.claude/rules/` (loaded automatically). This file is > the
OpenAnalystInc/10x-Team/CLAUDE.md
TLDraw canvas 6. Executes workflows AUTONOMOUSLY after approval 7. Generates outputs in multiple formats (PDF, PPT, JSON) ### Orchestrator Agent Location: `.claude/agents/orchestrator.md` The Orchestrator coordinates all other agents and skills
reggiechan74/issuer-credit-analysis/CLAUDE.md
style credit reports for Canadian REITs using a 5-phase pipeline: ``` Phase 1: PDF → Markdown (PyMuPDF4LLM + Camelot) Phase 2: Markdown → JSON extraction (structured data) Phase 3: Calculate credit metrics (Python
SatyKrish/databricks-document-intelligence-agent/CLAUDE.md
single `STREAM read_files(...)` via a temp streaming view. Reference: `pipelines/sql/01_bronze.sql` (`raw_pdf_arrivals` view); Auto Loader docs: https://docs.databricks.com/aws/en/ingestion/cloud-object-storage/auto-loader/. - **Section normalization**: `pipelines/sql/03_gold_classify_extract.sql` POSEXPLODES `parsed:sections[*]` and represents sectionless
AgentiaPT/vela-slides/CLAUDE.md
lint fails. ``` imports → icons → blocks → reducer → engine → slides → list → chat → test → uitest → demo → pdf → pptx → app ``` Read `src/parts/MANIFEST.txt` for the per-part purpose line. For a size/section
bablsoft/accessflow/CLAUDE.md
# CLAUDE.md — AccessFlow Agent Rules This file is the authoritative guide for AI agents implementing
Bizuayeu/Plugins-Weave/ContextPreloader/CLAUDE.md
は無視される。 ### Source Type の動作 | path | type=auto | 動作 | |------|-----------|------| | `.txt`, `.md`, `.py` 等 | text | 内容をそのまま文脈に注入 | | `.pdf`, `.png`, `.docx` 等 | binary | パス・サイズを表示(Read toolで閲覧) | | `https://...` (HTML) | url | HTMLタグ除去しテキストを注入 | | `https://...` (non-HTML
diegocconsolini/ClaudeSkillCollection/CLAUDE.md
playbook creator (11 scenarios) ✅ **security-report-builder** (35 KB) - Security report generator ✅ **pdf-smart-extractor** (17 KB) - PDF extraction with caching ✅ **xlsx-smart-extractor** (16 KB) - Excel extraction with caching
A file Claude Code reads at the start of every session. It holds the commands, conventions and warnings the agent needs for this project.
At the repository root. Claude Code also reads CLAUDE.md files in subdirectories when it works there.
Build and test commands, the project's layout, conventions that aren't obvious from the code, and mistakes to avoid. Short files tend to work better than long ones.
Claude Code reads CLAUDE.md; most other agents read AGENTS.md. Many projects keep one and point the other at it.