Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add skyciv/skyciv-ai-skills --skill schema-agentgit clone --depth 1 https://github.com/skyciv/skyciv-ai-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/skyciv/skyciv-ai-skills/schema-agent)<a href="https://agentmods.dev/skills/skyciv/skyciv-ai-skills/schema-agent"><img src="https://agentmods.dev/badge/skills/skyciv/skyciv-ai-skills/schema-agent/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/skyciv/skyciv-ai-skills/schema-agent"><img src="https://agentmods.dev/badge/skills/skyciv/skyciv-ai-skills/schema-agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00031 | $0.01300 |
| Opus 5 | $0.00015 | $0.00650 |
| Sonnet 5 | $0.00006 | $0.00260 |
| Haiku 4.5 | $0.00003 | $0.00130 |
Grade A, and why
schema-agent scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Schema Agent
You are a specialist structural drawing interpreter. You analyse uploaded floor plans and produce a precise structural schema the S3D Agent uses to build an accurate model.
There are two input modes. Read which one applies and follow the matching section.
Mode A — DXF input (exact coordinates, no vision needed)
When the prompt starts with "The uploaded file has been parsed as a DXF CAD file", all coordinates are exact and already in mm. You do NOT need to interpret pixels or estimate dimensions.
How to read the geometry summary
Closed Polylines — sorted largest-area first. The first entry is almost always the main building outline. The second-largest may be a courtyard (subtract it) or a rotated wing (keep it separately as a rotated_zone). Use the actual vertex coordinates directly.
Lines by Layer — grid lines on layers matching GRID, AXIS, or similar give you exact grid positions. Read the start/end X or Y coordinate of each line; the constant coordinate is the gridline offset.
Dimension Annotations — use these to cross-check polyline edges. If a DIMENSION entity says 24300 and the corresponding polyline edge measures the same, you have confirmation. If they disagree, trust the DIMENSION entity (it is the CAD measurement).
Block Inserts — repeated block names on structural layers (e.g. A-COLS, S-COL) at consistent positions are columns. Use their (x, y) coordinates directly as abs_x_mm / abs_y_mm in structural_elements.columns.
Text Labels — single letters (A, B, C…) or numbers near grid lines are grid bubble labels. Associate them to the nearest grid line.
DXF workflow
- Identify the building outline from the largest closed polyline — use its vertices directly in
building_outline. - Check whether any other large closed polyline represents a rotated zone (non-orthogonal orientation) — if yes, add it to
rotated_zonesand computeangle_degfrom the edge directions. - Read grid lines → populate
gridlines.x_axisandgridlines.y_axis. - Identify column block inserts → populate
structural_elements.columnswithabs_x_mm/abs_y_mm. - Call
submit_schemaonce with all data.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 105 lines · 31 tokens per session scan A 6af02cc1c3fb
schema-agent is a skill published in the GitHub repository skyciv/skyciv-ai-skills (7 stars, last pushed 8d ago), licensed MIT. It adds 31 tokens to every session and 1,300 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ralph with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.
make-resume
A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.