Overview Benchmark Contents Activity Versions 1 Ratings 0
See it in action One of 12 test cases the skill fixed. Same model, same prompt, with and without the skill.
Prompt Where and under what filename pattern must scientific investigation reports be stored in the workspace repository?
What was checked, without and with the skill Checked Without skill With skill Specifies the relative directory path workspace/development/research/ Includes the filename prefix [C]sciomc- with topic and date placeholders
Show both answers
What's inside The instructions your model reads when the skill loads.
SKILL.md 78 lines single file
Dev Sciomc (Scientific Method)
Derived from oh-my-claudecode (MIT, Yeachan Heo). Adapted for the EvoNexus Engineering Layer.
Scientific method discipline applied to engineering investigations. Forces explicit hypothesis statement, experimental design, evidence collection, and provisional conclusions.
Use When
Investigation requires rigor beyond "let me try X"
Performance optimization (you need controls and measurements, not guesses)
A/B comparison of two implementations
Anything where the cost of being wrong is high
Do Not Use When
Trivial bug → use @hawk-debugger
Pure exploration → use @scout-explorer
Workflow
Phase 1 — Hypothesis
State the hypothesis as a falsifiable claim
"X is faster than Y" not "X feels faster"
Identify the dependent variable, independent variables, controls
Phase 2 — Experiment Design
What measurement will prove/disprove the hypothesis?
What's the minimum sample size for statistical significance?
What confounders need to be controlled?
Phase 3 — Evidence Collection
Run the experiment
Collect raw data
Note environmental factors that could affect results
Phase 4 — Analysis
Apply statistical tests (delegate to @prism-scientist)
Calculate effect size, CI, p-value
Compare against the hypothesis
Phase 5 — Conclusion
Provisional, never absolute
When it activates Automatically, when a task matches.
Use when you need rigorous causal reasoning rather than vibes-based debugging.
Track record Benchmark 19 / 22
test cases passed, vs 7 / 22 without
Adoption
Users 0
Times used 0 View activity → Safety and source details
SkillSafety ✓ 3 of 3 passed ✓ Code scan 15 of 15 checks clean
0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026
View 15 scanner checks live_secret remote_code_execution reverse_shell data_exfiltration ssrf_metadata agent_snooping anti_refusal destructive_commands obfuscated_unicode unicode_homoglyph opaque_blob suspicious_url tool_overreach trigger_abuse prompt_injection_phrasing
✓ Intent Safe
LLM judge · does the skill do what it claims
✓ Content Clean
LLM judge · policy & harmful-content review
Source Imported evolution-foundation / evo-nexus
.claude/skills/dev-sciomc/SKILL.md
View on GitHub ↗ License NOASSERTIONImported 8/3/2026Version v1