Self-Hosted Docs-to-AI-Skills Workbench

Engineering & Development

A web workbench that turns documentation and code repositories into AI skill packages; runs on your own machine with Docker Compose, bound to 127.0.0.1, and needs no key to start. Derived from a frozen snapshot of an MIT-licensed open-source project.

Subscribe & download See how to start

SubscriptionUS$49 per month

Last run2026-11-12

In practice

Readiness3 / 5

What you need

Few changes needed4 / 5

Who it is for

Developers and small teams who want to turn documentation sites or code repositories into skills and reference material for AI assistants, operated on their own machine.

How to start

$ cp .env.example .env
$ docker compose up -d --build

Browse the files

Files in the product repository at the pinned commit. A few house files are left out of the zip.

File overview2,000+ paths

▸api199

.gitignore
README.md
__init__.py
config_analyzer.py
configs_repo/
main.py
requirements.txt

▸configs12

astrovalley_unified.json
blender-unified.json
claude-code-unified.json
claude-code.json
godot.json
godot_unified.json
httpx_comprehensive.json
medusa-mercurjs.json
react.json
unity-addressables.json
…

▸distribution10

claude-plugin/
github-action/
smithery/

▸docs969

ARCHITECTURE.md
BEST_PRACTICES.md
BUG_AUDIT.md
DOCKER_DEPLOYMENT.md
FAQ.md
KUBERNETES_DEPLOYMENT.md
PRODUCTION_DEPLOYMENT.md
README.md
TROUBLESHOOTING.md
UML/
…

▸examples54

chroma-example/
cline-django-assistant/
continue-dev-universal/
cursor-react-skill/
faiss-example/
haystack-pipeline/
http_transport_examples.sh
langchain-rag-pipeline/
llama-index-query-engine/
pinecone-upsert/
…

▸helm15

skill-seekers/

▸scripts9

bootstrap_skill.sh
check_translation_sync.sh
render_sponsors.py
run_benchmarks.sh
run_integration_tests.sh
run_tests_fast.sh
run_tests_safe.py
skill_header.md
translate_doc.py

▸skills1

skill-seekers/

▸src348

skill_seekers/

▸templates1

github-actions/

▸tests228

__init__.py
conftest.py
docker-compose.test.yml
fixtures/
golden/
mcp_integration_test.md
phase2_golden_utils.py
subprocess_helpers.py
test_adaptor_benchmarks.py
test_adaptors/
…

▸ui98

.gitignore
components.json
eslint.config.js
index.html
package-lock.json
package.json
playwright.config.ts
postcss.config.js
src/
tailwind.config.js
…

▫AGENTS.md

▫ATTRIBUTION.md

▫CHANGELOG.md

▫CLAUDE.md

▫CONTRIBUTING.md

▫Dockerfile

▫Dockerfile.mcp

▫Dockerfile.ui

▫LICENSE

▫PRODUCT.md

▫QUICKSTART.md

▫QWEN.md

▫README.ar.md

▫README.de.md

▫README.es.md

▫README.fr.md

▫README.hi.md

▫README.ja.md

▫README.ko.md

▫README.md

▫README.pt-BR.md

▫README.ru.md

▫README.tr.md

▫README.zh-CN.md

▫ROADMAP.md

▫SECURITY.md

▫SPONSORS.md

▫SPONSORSHIP.md

▫codecov.yml

▫delivery-manifest.txt

▫docker-compose.yml

▫example-mcp-config.json

▫mypy.ini

▫pyproject.toml

▫pytest.ci.ini

▫render-mcp.yaml

▫render.yaml

▫requirements.txt

▫setup.sh

▫setup_mcp.sh

▫sponsors.json

▫uv.lock

▫Config and hidden files 14

Latest passing run

Clone → Checkout → Toolchain → Run hud

Pre-purchase Disclosure

What you are buying

A workbench that turns documentation, code repositories and other sources into AI skill packages from a web interface: brought up with Docker Compose on your own machine, and opening the interface needs no key.

Derived from an open-source project under the MIT licence, and not the original project itself.

Delivery is a frozen snapshot: one zip, taken from the product repository at revision 3abf11a.

Known limitations

The service speaks plain HTTP and is bound to the local machine only (port 8770); TLS and a reverse proxy are yours to bring for any wider access
The AI enhancement features need your own model provider key, entered on the interface’s Settings page
Settings and output are kept in Docker volumes, and down -v deletes them
The first build needs internet access to compile the web frontend and install Python packages
Pinned to the delivered snapshot; it does not follow upstream.

The liability cap, the scope of what is promised and the statutory floor are governed by the Terms of Service.

Vetting record

Everything below was checked against the pinned commit 5b5d8df. Every verdict carries its full reasoning, an evidence link and the checker; failures are published, not hidden — do not take our word for it, verify it yourself.

2 PASS3 WARN0 FAIL

Source ReviewWARN

Read: docker-compose.yml, Dockerfile.ui, .env.example and QUICKSTART.md. The upstream Python and frontend source was not read file by file.

Script SafetyPASS

The Dockerfile and the compose file were read; no download-and-pipe-to-shell pattern was seen there. Other upstream scripts were not read.

RecencyWARN

This is a frozen snapshot that does not follow upstream. The date of the pinned upstream commit was not checked.

LicensePASS

SPDX:MIT

The LICENSE file in the repository is MIT text. The upstream copy was not compared against it.

Dependency LicensesWARN

Dependencies are declared in the project files and fetched at build time. They were not scanned for licenses.