DiagForge Bootstrap

Bootstrap skill for DiagForge. Use this skill to onboard an agent into the DiagForge GitHub repository, understand the project structure, run the canonical c...

Security Scan

The skill's requirements and runtime instructions are internally consistent with a bootstrap that guides an agent into the DiagForge repository and runs its smoke test; there are no disproportionate installs or unrelated credential requests, though you should review the repository code before running the included Python scripts and confirm the VISIO_BRIDGE_TOKEN usage.

Purpose & Capability

Name/description say this skill bootstraps an agent into the DiagForge repo; it requires git and python which are exactly what you need to clone and run the repo's smoke-test scripts. Asking for a Visio bridge token is plausible given the Visio-based workflow described.

Instruction Scope

SKILL.md stays on-task (clone repo, read specific docs, run the canonical smoke-test commands). It does instruct running repository Python scripts (Setup/*). Those scripts will run arbitrary Python code from the cloned repo, so inspect them before execution. The instructions do not themselves instruct reading unrelated local files or exfiltrating data.

Install Mechanism

Instruction-only skill with no install spec and no code files included in the package—no downloads or archive extraction by the skill itself (lowest install risk).

Credentials

The only required env var is VISIO_BRIDGE_TOKEN which is plausible for a Visio bridge, but SKILL.md never documents how or when the token is used. This is not necessarily malicious, but you should confirm the token's scope and why it's required before providing it.

Persistence & Privilege

The skill does not request always-on presence and uses normal agent invocation. It does not modify other skills or system-wide settings as presented.

Assessment

This skill is an instruction-only bootstrap: it points the agent to the GitHub repo and tells it to run Python smoke-test scripts found there. Before installing or running it: (1) verify the VISIO_BRIDGE_TOKEN purpose and minimize its scope/privileges; (2) prefer cloning via HTTPS if you don't want to expose SSH keys; (3) inspect the repository's Setup/*.py scripts and any network calls they make before executing them, and run tests in a sandbox or isolated environment if you can. If you don't trust the repo or can't review the code, don't provide sensitive tokens or run the smoke-test commands on a production machine.

This is a lightweight onboarding skill for the DiagForge repository.

It is not the full DiagForge system. Its job is to guide an agent to the correct GitHub repository, documents, smoke test, and execution flow.

DiagForge itself is an agent-driven closed loop built on top of Microsoft Visio. Its goal is to turn reference figures into directly editable diagram assets by helping agents operate Visio more like a capable human user rather than as a blind API caller.

What this skill can do

This skill can help an agent:

• understand what DiagForge is trying to achieve
• find the correct GitHub repository and entry documents
• avoid random first-run behavior and jump into the intended workflow
• run the canonical cold-start smoke test
• start reproducing reference figures through the DiagForge Visio loop
• move toward a result that a human can continue editing directly in Visio

Typical outcomes

After using this skill, an agent should be able to:

• explain the DiagForge workflow clearly
• bootstrap itself into the repository with the correct read order
• validate that the Visio bridge and execution path are working
• begin work on figure reproduction with better layer awareness
• help produce editable .vsdx outputs instead of dead image copies

What this skill is for

Use this skill when an agent needs to:

• find the DiagForge source repository
• understand the top-level architecture quickly
• avoid free-form blind retries
• run the canonical cold-start smoke test
• begin work in the correct layer

When to use it

Use this skill when:

• an agent is entering DiagForge for the first time
• a new environment needs to be validated before real drawing work
• a user wants an agent to help reproduce a figure through Visio
• the goal is not only to look similar to the reference, but to obtain a directly editable diagram asset

What this skill is not

This skill does not bundle the whole repository. It does not include Visio bridge code, benchmark PNGs, or runtime artifacts.

The full project lives in the GitHub repository:

https://github.com/qweadzchn/DiagForge

Recommended workflow

1. Clone the GitHub repository locally.
2. Read the cold-start entry documents.
3. Run the canonical smoke test before doing open-ended drawing work.
4. Only then move on to real jobs or system improvements.

Clone the repository

git clone [e-mail]:qweadzchn/DiagForge.git
cd DiagForge

If SSH is not available, use HTTPS instead.

Read order

Read these files first:

1. AGENT_START_HERE.md
2. AGENT_GUIDE.md
3. GET_STARTED.md
4. docs/human/setup/AGENT_COLD_START_SMOKE_TEST.md
5. MODE_POLICY.md

Canonical smoke test

From the repo root:

python Setup\prepare_smoke_test.py --config Setup\examples\smoke-test-inputpng-1.json
python Setup\run_draw_job.py --config Setup\examples\smoke-test-inputpng-1.json
python Setup\execute_drawdsl.py --config Setup\examples\smoke-test-inputpng-1.json --round 1 --save-final

Expected outputs:

• OutputPreview/smoke-inputpng-1/round-01.png
• OutputEditable/1_smoke_test_final.vsdx

Routing rule

When working inside DiagForge:

• if the issue is round-specific, keep it in review artifacts
• if it looks structural but still needs validation, write a proposal
• if it is already reusable experience, promote it into a lesson
• if the shared fix is clear, patch the owning layer directly

Where to go next

See:

• README.md
• CONTRIBUTING.md
• docs/architecture/FEEDBACK_PROMOTION_LOOP.md