server automatically) |
| Exported case state | `./exports/case_state.json` | Full `CaseState` snapshot on session end |
| PDF report (optional) | `./reports/report.pdf` | Generated by `python3 generate_pdf_report.py` |
All timestamps in output files must
blog cover, social card or banner image from HTML; render HTML to a PDF → `web run --session ... (read text: web get-text; one-time login: web save-session)`
- **xlsx** — Read
list actions, connect /
disconnect via OAuth, and universal `execute`.
- `artifacts` — list / get / export (PNG, PDF) / save-to-file for
artifacts produced by the Ask-AI agent. Each artifact is also
GitHub Actions workflow / pipeline PR for security and team standards | `revisor-pipeline` |
| Turn a PDF or slide deck into a standalone HTML webpage | `productivity` (routes to `references/webpage-from-slides.md`) |
| Transform DevOps Mentoria
equivalent direct form
```
A test project needs a business plan at `plancasting/businessplan/*.md` (or `.pdf`). Stage 0 (`tech-stack`) must run before Stage 1, since the prerequisite hook and most
rules.
## Output Language — mirror the user (mandatory) 🌐
Write every response and **generated report (incl. PDF)** in the **language the user
writes to you in** — user writes Turkish → reply + reports
como um analista. Os únicos artefatos executáveis são scripts Python utilitários de pós-processamento (PDF). Para "rodar" o sistema, leia e siga `orchestrator.md`.
## Fluxo de execução
`SKILL.md` (entry point
copyrighted and not redistributed. To build
the dictionary-backed checker from your own free PDF copy:
```
pdftotext -layout -enc UTF-8 your_ste100.pdf ste.txt
python3 tools/ste-dictionary/parse_dict.py ste.txt
python3 tools/ste-dictionary/emit.py
python3 tools/ste-dictionary/ste_dict_lint.py
fixes/tweaks, minor for new features/styles, major for breaking changes to the skill interface.
## PDF export
```bash
python3 scripts/export-pdf.py magazine.html
# Optional flags: --output filename.pdf --width 210 --height 297
# Requires: pip install
rules + bracket-placeholder scan on the ACTUAL outgoing .pdf/.docx
python scripts/lint-submission-file.py final/docx/ .docx final/pdf/ .pdf
```
`lint-submission-file.py` extracts text from the file that will actually be uploaded and applies the prose
service itself (`src/convert/`, pure Rust: HTML, DOCX, XLSX/XLSM (read
cell by cell), CSV, PPTX, PDF; decided 2026-10-10, replacing "the service never parses Word, PDF or HTML itself").
Every
call remember(kind="document-note", title, key_points, summary, source_hint, category).
2. Only PDF and Word (.docx/.docm) accepted for file ingest. Images are described, not uploaded.
3. For image
step — the project is a pure-Python CLI. `pandoc` is an
optional system dep (PDF rendering only); `claude -p` is an optional binary
(enricher LLM path; falls back to rule
identity), plus a human-authored taste primer at `magic_trick.md`
and a `human/` directory for PDF materials the MCP intentionally ignores.
The goal: when an LLM helps build a website
A file Claude Code reads at the start of every session. It holds the commands, conventions and warnings the agent needs for this project.
Where does it go?
At the repository root. Claude Code also reads CLAUDE.md files in subdirectories when it works there.
What should it contain?
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.md or AGENTS.md?
Claude Code reads CLAUDE.md; most other agents read AGENTS.md. Many projects keep one and point the other at it.