drawio-reconstruction

Reconstructs reference images into high-fidelity, editable Draw.io files with rendered previews: native Draw.io elements carry text and structure, SVG covers simple icons that match the reference, and cropped or transparent PNGs preserve complex visuals. Use when the user wants a diagram image, research figure, architecture diagram, slide, UI screenshot, or image folder turned into `.drawio` XML; batch requests use a manifest with bounded parallelism when available and a full-fidelity serial fallback otherwise.

Quality

87%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

73%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is highly actionable and workflow-clear, with executable commands and strong validation feedback loops for batch/destructive operations. Its main weakness is conciseness (repeated medium rules) and progressive disclosure: it is a monolithic single file with no reference split despite its length.

Suggestions

Extract the icon-discipline, screenshot-crop, and typography sections into separate reference files (e.g. references/crops.md, references/icons.md) and link to them from a concise overview, reducing the inlined wall of text.

De-duplicate the crop-vs-SVG medium guidance: state the decision rules once and have the later sections reference them instead of restating them.

Reference the bundled assets/cases example images from the body (or move them under a documented examples path) so the provided bundle assets are discoverable and tied to the guidance.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and assumes Claude's competence, but the crop-vs-SVG medium guidance is restated across several sections ('Reconstruction Strategy', 'Medium Decision Rules', 'Screenshot Crop Rules', 'Icon Reconstruction Discipline'), adding noticeable padding that could be tightened. Not a 4 because the repetition is substantive enough to bloat the context budget.	3 / 5
Actionability	Fully executable, copy-paste-ready commands for every bundled helper with real flags — e.g. `python "$SKILL_DIR/scripts/crop_assist.py" reference.png --roi x,y,w,h --anchor x,y --exclude x,y,w,h --output-dir crops --name icon_name` — covering the common single and batch cases.	5 / 5
Workflow Clarity	The 'Default Workflow' is an explicit 11-step sequence with validation checkpoints (run checker, treat layout failures as blocking, full visual audit) and feedback loops (iterate until checks and audit pass), and the batch workflow mirrors these with explicit verification. This is exactly the validate→fix→retry pattern the rubric rewards.	5 / 5
Progressive Disclosure	All ~350 lines of guidance are inlined in a single SKILL.md with no references/ files; substantial material that clearly belongs in separate reference files (icon discipline, crop rules, typography) is inlined, and the bundled assets/cases PNGs are not referenced from the body. Not a 1 because sections are headed and the bundled scripts are real and clearly linked.	2 / 5
	Total	15 / 20 Passed

Description

95%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is concrete, comprehensive, and clearly states both what the skill does and when to use it, with natural trigger terms and a distinct niche. It is among the strongest reference examples; the only minor weakness is that it consolidates actions into one reconstruction flow rather than a longer enumerated action list.

Dimension	Reasoning	Score
Specificity	Lists several specific actions — 'Reconstructs reference images into high-fidelity, editable Draw.io files with rendered previews' plus a three-way medium breakdown (native/SVG/crop) — with only minor gaps in coverage. Not a 5 because it bundles actions into one reconstructed-output flow rather than enumerating many distinct concrete operations.	4 / 5
Completeness	Explicitly answers both: 'what' (reconstructs images into editable .drawio with rendered previews across three media) and 'when' via 'Use when the user wants ... turned into `.drawio` XML' with concrete trigger phrases and a batch case.	5 / 5
Trigger Term Quality	Comprehensive natural trigger terms — 'diagram image, research figure, architecture diagram, slide, UI screenshot, or image folder' — plus the file extension '.drawio', covering synonyms and the batch variant. Users would naturally say these when they need the skill.	5 / 5
Distinctiveness Conflict Risk	Clear niche — converting images into Draw.io .drawio XML — with distinct triggers and minimal overlap risk versus other skills.	5 / 5
	Total	19 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: HKUSTDial/Supervisor-Skills
Path: skills/drawio-reconstruction/SKILL.md
Commit: 207bc6f

Reviewed: 9 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.