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 flight-plan-parsergit 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/flight-plan-parser)<a href="https://agentmods.dev/skills/benchflow-ai/skillsbench/flight-plan-parser"><img src="https://agentmods.dev/badge/skills/benchflow-ai/skillsbench/flight-plan-parser/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/flight-plan-parser"><img src="https://agentmods.dev/badge/skills/benchflow-ai/skillsbench/flight-plan-parser.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 | $0.00093 | $0.00805 |
| Opus 5 | $0.00046 | $0.00402 |
| Sonnet 5 | $0.00019 | $0.00161 |
| Haiku 4.5 | $0.00009 | $0.00081 |
Grade A, and why
flight-plan-parser 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 7d 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Flight Plan Parser
Overview
Converts human-readable flight commands into structured waypoints compatible with the drone simulator's trajectory planner. Each command maps to one flight segment with a mode tag (takeoff, hover, fly, land).
Output Format
waypoints : (4 x n) numpy array — rows are [x, y, z, yaw]
waypoint_times : (n,) numpy array — arrival time for each waypoint [seconds]
modes : list of (n-1) strings — one mode per segment between waypoints
Supported Commands
| Command pattern | Mode |
|---|---|
Take off to <h> m height in <t> seconds |
'takeoff' |
Hover at <h> m height for <t> seconds |
'hover' |
Fly from (<x>,<y>,<z>) to (<x'>,<y'>,<z'>) in <t> seconds |
'fly' |
Land from <h> m height in <t> seconds |
'land' |
Implementation Logic
Use a stateful parser class that accumulates waypoints, times, and modes as it processes each command line:
- Maintain internal state: current position, current time, list of waypoints, list of arrival times, and list of mode strings.
- On the first command, auto-insert a starting waypoint at the current position and
t=0if the list is empty. - Each command handler extracts numeric values via regex, advances the time accumulator, updates the current position, appends the end waypoint, and appends the mode string.
- After all commands are processed, convert the lists to a
(4 × n)numpy array (rows: x, y, z, yaw) and a(n,)time array. - Expose a top-level
parse_flight_plan(text)function that instantiates the class, feeds it each line, and returns(waypoints, waypoint_times, modes).
Regex Strategy
Write one case-insensitive pattern per command type. Each pattern captures only the numeric fields:
- Takeoff / Hover / Land: capture height and duration (2 groups).
- Fly: capture start coordinates
(x, y, z)and end coordinates(x', y', z')plus duration (7 groups). Thefrom (...)andto (...)parts must handle optional whitespace around commas.
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.
- 7d ago First seen · 66 lines · 93 tokens per session scan A 74acf1d6c9d8
flight-plan-parser is a skill published in the GitHub repository benchflow-ai/skillsbench (1,760 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 93 tokens to every session and 805 once invoked, about $0.0005 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 2026-09-03.
Other skills, from other repositories
exploded-view-illustration
Techniques for drawing isometric or orthographic exploded-view hardware diagrams programmatically using Pillow, with annotation leader lines and layer separation.
membrowse-integrate
Integrate MemBrowse memory tracking into a project that produces ELF binaries. Use when the user wants to set up MemBrowse, add memory analysis GitHub workflows, create membrowse-targets.json for tracking memory usage, or add a MemBrowse badge to the README. Works with embedded firmware (STM32, ESP32, nRF, RISC-V) and…
pcbway
PCBWay PCB fabrication and assembly — turnkey/consigned assembly, design rules, ordering workflow. Alternative to JLCPCB for manufacturing. Use with KiCad. Use this skill when the user mentions PCBWay, needs turnkey assembly (PCBWay sources parts by MPN), has parts not available on LCSC, needs assembled boards with…
unifi-protect
How to manage UniFi Protect cameras and NVR — view cameras, smart detections, Find Anything detection search, recordings, snapshots, lights, sensors, Known Faces, license plates, and the Alarm Manager. Use this skill when the user mentions UniFi cameras, security cameras, NVR, recordings, motion detection, person…
akg-agents
An agent workflow for developing, generating, testing, and tuning AKG operators. AKG is a toolkit for generating optimized computational kernels.
fpga
FPGA development guidelines covering Vivado, SystemVerilog, timing closure, AXI interfaces, and hardware optimization.