Build Overview

Generates an experiment-overview snapshot of all research questions under research/reports/. Invoke when a new point-in-time report across all RQs should be produced.

49 stars 1 forksResearch & Science

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add marcoemrich/agentic_coding_lab --skill build-overview
Manual install
git clone --depth 1 https://github.com/marcoemrich/agentic_coding_lab.git /tmp/agentic_coding_lab
mkdir -p ~/.claude/skills
cp -r /tmp/agentic_coding_lab/.claude/skills/build-overview ~/.claude/skills/build-overview

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# /build-overview — produce an experiment-overview snapshot

You produce a frozen, publishable research report from the current state of every `findings.md` under `research/questions-claude/`, `research/questions-opencode/`, `research/questions-cross/`, and `research/workflow-dev/`. The snapshot lands as a new file under `research/reports/experiment-overview-YYYY-MM-DD.md`.

## Core principle

`findings.md` = living document, growing list of status-tagged findings.
Snapshot = frozen, table-heavy report at a point in time.

Both exist in parallel. The snapshot is **not written from memory** — it is filled in from an auto-generated skeleton.

## Prerequisites

Required on `$PATH` for the Markdown snapshot (steps 1–5):

- `python3` — runs `experiments/generate-snapshot-skeleton.py`

Only needed when the user asks for a PDF (step 6):

- `pandoc` — Markdown → HTML (any version ≥ 2.9 works)
- `google-chrome` (or `chromium` — adjust the binary name in step 6) — headless `--print-to-pdf`
- `pdfinfo` (Poppler utils) — optional, used for the PDF verification check

If a PDF was requested and one of its tools is missing, finish the Markdown snapshot and report which tool is unavailable so the user can install it — do not treat it as a failure of the whole run.

## Lifecycle (6 steps)

### Step 1 — generate the skeleton

Bash:

```bash
./experiments/generate-snapshot-skeleton.py
```
Read the full skill on GitHub

Details

Skill name
build-overview
Path
.claude/skills/build-overview/SKILL.md
License
MIT
Repo updated
13 November 2026

FAQ

What does the Build Overview skill do?

Generates an experiment-overview snapshot of all research questions under research/reports/. Invoke when a new point-in-time report across all RQs should be produced.

How do I install the Build Overview skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add marcoemrich/agentic_coding_lab --skill build-overview. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Build Overview popular?

It lives in marcoemrich/agentic_coding_lab, which has 49 GitHub stars and 1 forks.

Related skills

Exact Coding Baseline Export

49

marcoemrich/agentic_coding_lab

Mint a new YYYY-MM-DD-exact-coding-baseline snapshot under research/workflow-dev/export/. Detects the current best correctness- oriented workflow from research/workflow-dev/workflow-construction.md (or takes an explicit source-workflow argument) and transforms it from a lab workflow into a consumer-ready one on three axes: strips lab-only measurement content, re-enables human-in-the-loop checkpoints, and converts auto-loading config into an explicitly-invoked skill. Supports both promoted EXACT Coding lines: Opus/Hybrid and SOL/Predictive TDD. Exports Claude Code, pi, OpenCode, cursor-agent an

Software Development

Green

49

marcoemrich/agentic_coding_lab

TDD Green Phase - Implement minimal code to make the failing test pass

Testing & QA

Publish Site

49

marcoemrich/agentic_coding_lab

Build the results site and publish it to GitHub Pages. Checks every precondition deploy-site.py enforces before spending a build on them, presents the research/ diff the build produces for a commit, and deploys only on explicit confirmation. Trigger when the user says "publish", "deploy", "site deployen", "gh-pages", "auf die Seite bringen", or asks how to get results online.

DevOps & Cloud

Run Rq

49

marcoemrich/agentic_coding_lab

Use this skill to drive a research question (RQ) end-to-end: validate the RQ README, generate a fill batch-plan, start the Docker batch in the background, monitor progress, run aggregation, and propose findings updates. Trigger when the user says "RQ-N voranbringen", "run-rq", "fill RQ-N", "run RQ-N", "Forschungsfrage N starten", or names a specific RQ-N directory in research/.

Research & Science

Unreal

45

j4flmao/agent-skills

Use when the user asks about Unreal Engine 5, UE5 C++, Blueprints, UObject and Actor lifecycle, Gameplay Ability System, Nanite, Lumen, Chaos physics or Unreal replication. Produces Unreal project architecture and C++/Blueprint guidance. Not for Unity (use unity) or custom engine rendering (use render-graph).

Research & Science

Fxbaogao Deep Research

10

fxbaogao/fxbaogao-deep-research

围绕行业、公司或主题做深度研究。采用"先想后搜"方法:先明确研究边界,用 MECE 原则拆解关键子问题,再基于发现报告接口定向搜索、筛选核心研报、精读后沉淀事实、对比推导,最终形成结构化结论。

Research & Science

Browse the most popular Claude skills, all research & science skills, or write your own with the skills generator.