build-bookgen
Implement the next phase/milestone of the AI-Agent-Orchestration-HW3 "bookgen" CrewAI + LaTeX project, following the repo's guideline-aligned workflow (TODO…
Skill by AmrSafadi
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/amrsafadi-build-bookgen
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: documents, testing, productivity, agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/build-bookgen
What's inside
- Skill name
build-bookgen- Description
- Implement the next phase/milestone of the AI-Agent-Orchestration-HW3 "bookgen" CrewAI + LaTeX project, following the repo's guideline-aligned workflow (TODO phases, ruff/format, tests + 85% coverage, docs sync, commit on request). Use when the user asks to build, continue, or implement a phase, milestone, or task of this project.
- License
- MIT
- Instructions
- 43 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Build BookGen
Implements the next unit of work on the `bookgen` project while keeping it aligned
to the submission guidelines and the `docs/` always in sync.
## 1. Before coding
1. Read `materials/software_submission_guidelines-V3_Summary.md` (the grading rubric),
plus `docs/PLAN.md` and `docs/PRD.md`.
2. Open `docs/TODO.md`, locate the next unchecked phase/tasks (stable `T###` ids).
3. Read the real source files you will touch — never assume their contents.
## 2. While coding
- Every code file stays ≤ 150 non-blank/non-comment lines; split modules if needed.
- No hardcoded paths or secrets; configurable values live in `config/*.json`;
secrets come from environment variables only.
- Keep the **dry-run path the default**. Never call an LLM/API or compile a PDF
unless the user explicitly approves that milestone.
- Do not add agents beyond the approved five; keep deterministic components
(citations, graph, validators, renderer, compiler) deterministic.
## 3. Verify — all must pass before declaring done
```
uv run --no-project --with ruff ruff format .
uv run --no-project --with ruff ruff check . # 0 violations
PYTHONPATH=src uv run --no-project --with pydantic --with pytest --with pytest-cov --with matplotlib --with jinja2 python -m pytest tests --cov --cov-fail-under=85
```
## 4. After coding — ALWAYS
- Update every affected file under `docs/`:
- `TODO.md`: tick the relevant checkboxes and fix the `Total tasks` count line.
- `IMPLEMENTATION_STATUS.md`: reflect what is now complete / in progress.
- `PLAN.md` / `PRD.md` / per-mechanism PRDs: update if architecture or
requirements changed. `COSTS.md` / `USAGE.md` if relevant.
- Summarize changed files plus the test/coverage result.
- Commit only when the user asks, with a meaningful message and a
`Co-Authored-By: Claude` trailer; push to the `Sharbel` branch and offer a PR.
## 5. Reference map
- Phases & tasks: `docs/TODO.md`. Architecture & ADRs: `docs/PLAN.md`.
- Agent/task design: `AGENTS_DESIGN.md`, `TASK_FLOW.md`. Folder rules: `FOLDER_STRUCTURE.md`.
- Source layout: `src/bookgen/{shared,document,harness,orchestration,latex}/`.From AmrSafadi/AI-Agent-Orchestration-HW3, MIT.
More from AmrSafadi/AI-Agent-Orchestration-HW3
- 0.464score
citation-discipline
bookgen-team
Rules for trustworthy citations sourced only from the curated registry.
SkillCFreshness: CClaude Code +9 - 0.464score
course-alignment
bookgen-team
Keep content anchored to the course's agent-orchestration concepts.
SkillCFreshness: CClaude Code +9 - 0.464score
latex-style
bookgen-team
House style and Hebrew-English BiDi rules for professional, compilable LaTeX content.
SkillCFreshness: CClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Jun 4, 2026 (4 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
Cite this page
build-bookgen skill. Agent Mart. https://agentmart.dev/skills/amrsafadi-build-bookgen (last updated 2026-10-24)