Skylit / Research in the making
Turn a market question
into an experiment.
Run a workflow. Inspect its evidence. Change one thing and share what you learn. A place to build trading research with the agent you choose.
Internal pilot · GitHub repository access is currently required. Ask about access. A Skylit API key alone does not grant repository access.
A watchlist, a journal, a source feed.
Known inputs. Visible sources. Local reports.
A reproducible example, ready for review.
Question → experiment → evidence → review
Three starting points
All three seeds start with fictional inputs. The default runs need no account, API key, model or installed Python packages.
Watchlist Investigator
Read GEX, VEX and flow observations together, with source times and missing data kept visible.
Fictional defaults. Requires a separate, pinned Agent Kit checkout.
Workflow guide (GitHub, repository access required, opens in a new tab)Journal Reviewer
Review closed paper-trade rows and the notes you entered. Start with the sample, then bring a supported CSV.
Closed USD cash-equity paper trades. No inferred strategy or tax analysis.
Workflow guide (GitHub, repository access required, opens in a new tab)Market Brief
Turn dated entries from one press-release feed into a compact brief. Start offline, then use saved RSS or an explicit public-feed fetch.
Selects 1–20 entries from a single feed. Not a market-wide scan.
Workflow guide (GitHub, repository access required, opens in a new tab)Internal pilot · GitHub repository access is currently required. Ask about access. A Skylit API key alone does not grant repository access.
Your first run
With repository access, Git and Python 3.11+, clone the Lab and run Market Brief. This first run uses fictional data, makes no network requests and spends no API credits.
Read the getting-started guide (GitHub, repository access required, opens in a new tab)git clone https://github.com/SkylitAI/skylit-agent-lab.git
cd skylit-agent-lab
python3 -X utf8 -I -B experiments/market-brief/run.pyThe command prints paths to a Markdown report and a run record. Open both to inspect the result and its inputs. On Windows, use py -3 if python3 is unavailable.
Build with others
Contribute a workflow, data adapter, visualization, documentation improvement or reproduction. Make it possible for someone else to run your work and understand its limits.
Contribution guide (GitHub, repository access required, opens in a new tab)Give the experiment a clear question, owner, inputs and expected output.
Include a reproducible example, sources, known gaps and resource costs. Keep credentials and private reports local.
Submit the experiment for review. Useful, reusable work can graduate into Agent Kit through a reviewed contribution.
Before you start
Lab is the home for experiments and community contributions. Agent Kits provides maintained helpers, starter workflows and setup guides. Lab experiments can use Kit components and later contribute improvements back.
The Lab has guidance for Codex, Claude Code, OpenClaw, other skill-capable hosts, MCP-only hosts and standalone Python, with provisional Muse Code guidance. Python examples are tested; host-driven runs remain unverified. See the agent guide (GitHub, repository access required, opens in a new tab)
The repositories are currently internal pilots. Ask about access using the link on this page. Repository access, Skylit data access and your agent subscription are separate.
No. These seeds produce research reports from explicit inputs. They do not submit orders, manage a brokerage account or promise investment returns. Live-service and agent-host certification remain pending.
Your next experiment starts here
Research and education. These workflows do not place trades.