Individual skill
iros-reproducibility
Use when strengthening IROS reproducibility evidence — splitting rerunnable claims from auditable-only real-robot claims, the hardware specification ledger, calibration and parameter disclosure, log capture discipline, honest code/data availability statements, and sim-to-real accounting, all inside a page budget with no supplementary PDF.
IROS-Skills/skills/iros-reproducibility/SKILL.md
Source commit 932eb23331721b16e967c59f093781be1928b498
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- No
- Repository scan complete
- No
- Skill scan complete
- Yes
- Observed behavior
- Not checked yet
- Last checked
- Nov 9, 2026
These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.
Install this skill
Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.
An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.
Repository context
- Repository stars (not skill ratings)
- 1,409
- Repository last updated
- Sep 27, 2026
- License
- MIT
Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.
- academic-writing Repository topic
- agent-skills Repository topic
- journal Repository topic
- academic-research Repository topic
- ai-agents Repository topic
- anthropic Repository topic
- awesome-list Repository topic
- claude Repository topic
- claude-code Repository topic
- economics Repository topic
- finance Derived category
Files and excerpt
File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.
Browse files
SKILL.mdcore · 3,721 bytes
Read excerpt
# IROS Reproducibility
Use this before submission and again before camera-ready. Robotics reproducibility is not the same as ML
reproducibility: a reader usually cannot rerun your robot, so the goal is to make every claim either
**rerunnable** (code/sim someone can execute) or **auditable** (logs and specs detailed enough to check),
and to be honest about which is which.
## Evidence map
- Split each claim into rerunnable or auditable. A simulation result should be rerunnable; a real-robot
reliability number is auditable through logs and a stated protocol, not rerunnable by a reader.
- For the **rerunnable** part: pin dependencies, seeds, configs, and an entry point; state the hardware
it assumes.
- For the **auditable** part: give the hardware ledger, calibration, parameters, trial protocol, resets,