Scan reports · K-Dense-AI/scientific-agent-skills
experimental-design: scan report
Designs experiments and studies BEFORE data is collected — choosing a design, randomizing, blocking, and laying out treatment combinations so results are interpretable. Use whenever someone is planning a study, asks… An automated scan of this public skill from K-Dense-AI/scientific-agent-skills: security, token cost, spec and clarity, with every finding and its fix.
Verdict
K-Dense-AI/scientific-agent-skills/skills/experimental-design at a1043ef
Spec 25 · Efficiency 25 · Clarity 25 · Security 23 (each out of 25)
Always loaded 259 tokens · on trigger 3,706 · on demand 12,609
sec/plain-httpinfo · SKILL.mdLinks over plain http.
Source
| Fact | Value |
|---|---|
| Repository | K-Dense-AI/scientific-agent-skills |
| Skill folder | skills/experimental-design |
| Stars | 51,324 |
| License | MIT |
| Commit scanned | a1043ef |
| Scanned | 2026-10-16 |
| Files | 7 |
ProSkills doesn't host or redistribute this skill. Get it from its repository, and check the license before reusing it. Something wrong here? Open an issue for a rescan or removal.
Badge for the README
If you maintain this skill, this badge shows its score and links to this report. Fix findings and the score moves with the next scan.
[](https://proskills.dev/reports/k-dense-ai-experimental-design)
Scanned alternatives on ProSkills
Skills in the ProSkills catalog that cover similar ground. Every one passes the same scanner before it ships.
- Test Writer$9Scan 100/1005 rules · Code ReviewTests that fail before the fix and pass after.Loads when the user needs tests for new code or a bug fix.
- Context Diet$9Scan 100/1004 rules · Agent OpsCut token waste, with before and after numbers.Loads when the agent is slow, expensive or running out of context.
- Subagent Designer$9Scan 100/1005 rules · Agent OpsSplit work into agents that earn their keep.Loads when the user designs subagents or specialist roles.
More from K-Dense-AI/scientific-agent-skills
| Skill | Scan | Grade |
|---|---|---|
| 13c-metabolic-flux | 90/100 | A |
| adaptyv | 89/100 | B |
| aeon | 96/100 | A |
| alphagenome | 98/100 | A |
| analytical-method-validation | 98/100 | A |
| anndata | 92/100 | A |
| arbor | 89/100 | B |
| arboreto | 98/100 | A |
| astropy | 89/100 | B |
| autoskill | 90/100 | A |
| benchling-integration | 94/100 | A |
| bgpt-paper-search | 97/100 | A |
Questions
- Is experimental-design safe to install?
- No critical findings, some security notes. The scan covers prompt injection, hidden Unicode, remote code execution and credential access in every text file of the skill. It cannot judge intent, so read any flagged line in context before installing.
- How was this score calculated?
- Four checks of 25 points each: spec, efficiency, clarity and security. Findings take points off the check they belong to, and any critical finding caps the grade at F. The same scanner runs in your browser at proskills.dev/scan.
- Is this report current?
- It was made from commit a1043ef on 2026-10-16. If the skill has changed since, paste the new version into the scanner for a fresh score.
- I wrote this skill. Can I fix the score or have the page removed?
- Fix the findings and push. The reports are rebuilt from GitHub on a schedule, so the next run picks the change up. To have the page removed, open an issue on the ProSkills GitHub repo.
Keep reading
Paste a SKILL.md or drop a folder. It is scored in your browser and nothing is uploaded.
Want a skill that already passes? Start with a free one.