SkillsBench is a benchmark for measuring how effectively AI agents use modular skills—folders containing instructions, scripts, and resources—to complete specialized tasks. It helps researchers and developers evaluate both skill quality and agent behavior, including tasks that require combining multiple skills. The catalogue’s skills and instructions are evaluated as part of this workflow.
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 benchflow-ai/skillsbench --skill architectural-dxf-extractiongit clone --depth 1 https://github.com/benchflow-ai/skillsbenchWrote 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/benchflow-ai/skillsbench/architectural-dxf-extraction)<a href="https://agentmods.dev/skills/benchflow-ai/skillsbench/architectural-dxf-extraction"><img src="https://agentmods.dev/badge/skills/benchflow-ai/skillsbench/architectural-dxf-extraction/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/benchflow-ai/skillsbench/architectural-dxf-extraction"><img src="https://agentmods.dev/badge/skills/benchflow-ai/skillsbench/architectural-dxf-extraction.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 | $0.00046 | $0.01122 |
| Opus 5 | $0.00023 | $0.00561 |
| Sonnet 5 | $0.00009 | $0.00224 |
| Haiku 4.5 | $0.00005 | $0.00112 |
Grade A, and why
architectural-dxf-extraction 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 12d 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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Use this skill for 2D architectural DXF plans where the CAD file is the authoritative source. Treat screenshots as orientation only.
Workflow
- Open the DXF with
ezdxf.readfile(...)and inspect modelspace entities grouped byentity.dxf.layer. - Build a layer inventory before extracting geometry. Include entity counts and entity types per layer.
- Normalize layer aliases through the provided layer schema. Keep both the original layer name and the canonical meaning in your working notes.
- Extract plan-view geometry in drawing units. If the task declares inches, do not convert unless the DXF header proves a different unit.
- Prefer geometric primitives over image interpretation:
LINEand lightweight/polyline vertices for wall, door, fixture, clearance, and grab-bar outlines.CIRCLEcenter/radius for turning circles or circular fixture details.ARCandSPLINEextents only after checking whether they are visible fixture geometry or control geometry.
- When no closed room/space layer exists, derive the room polygon as the rectangular interior usable extent of the room. Use the inside face of the
WALLlines for the left, right, and top edges and the lower door-wall plane for the door side, not a short raised wall return above the threshold. If multiple horizontal wall bands appear above the fixtures, choose the lower continuous interior wall line that bounds the main fixture zone shared by the toilet, lavatory, and tub, not an upper service or wall band above that usable floor area. Document the derivation in the inventory notes. Do not use the outer wall envelope, a wall-centerline shell, the clearance polyline, or the fixture envelope as the reported room polygon. - Keep output coordinates numeric and stable. Round only at the final JSON boundary, consistently to 3 decimals for coordinates and dimensions unless the task explicitly requires another precision. Do not mix 2-decimal room polygons with 3-decimal fixture bboxes.
Common Architectural Entities
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.
- 12d ago First seen · 48 lines · 46 tokens per session scan A 843682ecc8b8
architectural-dxf-extraction is a skill published in the GitHub repository benchflow-ai/skillsbench (1,764 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 46 tokens to every session and 1,122 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 2026-08-30.
Other skills, from other repositories
hotpath_init
Configure hotpath profiling in a Rust project. Adds the hotpath dependency with feature-gated setup, instruments main with hotpath::main, functions with measure/measureall, and wraps channels, mutexes, rwlocks, streams, futures, reqwest clients, axum routers and byte-level I/O with hotpath macros. Use when the user…
portfolio
Cross-chain DeFi portfolio discovery, rebalancing suggestions, and NEAR Intent construction. Activates when the user pastes a wallet address or asks about yield/positions/rebalancing. Bootstraps a per-user "portfolio" project, aggregates positions across all the user's addresses inside one project, and offers a…
llm-council
Query multiple LLM models in parallel from CodeAct and cross-reference their responses.
environment-discovery
Systematic exploration of unknown environments before starting work.
performant-code
Writing efficient code that handles large data and tight constraints.
rag-eval
NVIDIA RAG Blueprint evaluation guidance for measuring retrieval and answer quality with stable datasets, baselines, and reproducible scoring workflows.