aum08desai/literature-to-experiment
skills/research/literature-to-experiment/SKILL.md
Convert literature findings into concrete LLM experiment plans. Use when the agent has papers, blog posts, or benchmark notes and needs to turn them into hypotheses, training plans, dataset choices, and evaluation criteria.
$ install --global
skillsauthnpx skillsauth add aum08desai/hermes-research-agent literature-to-experimentInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 3, 2026, 11:19 AM136.1s2 files scanned
SKILL.md
- name:
- literature-to-experiment
- description:
- Convert literature findings into concrete LLM experiment plans. Use when the agent has papers, blog posts, or benchmark notes and needs to turn them into hypotheses, training plans, dataset choices, and evaluation criteria.
- version:
- 1.0.0
- author:
- Hermes Research Agent
- license:
- MIT
- tags:
- [research, literature, experiment-design, planning]
Literature To Experiment
Workflow
- Extract the core claim or gap from each relevant source.
- Map the claim to a testable hypothesis.
- Decide the minimum viable experiment:
- baseline
- intervention
- dataset
- evaluation suite
- expected win condition
- Write a stop condition before any training job starts.
- Save the result as an experiment plan with
research_state(action="record_experiment_plan", ...).
Heuristics
- Prefer the smallest experiment that can falsify the hypothesis.
- If a paper uses complex infrastructure, define the closest tractable approximation first.
- If no benchmark is obvious, choose one that directly measures the stated claim instead of a broad aggregate score.
Related Skills
aum08desai/writing-plans
development
VerifiedTrustedCommunity
Use when you have a spec or requirements for a multi-step task. Creates comprehensive implementation plans with bite-sized tasks, exact file paths, and complete code examples.
6SKILL.mdUpdated Apr 3, 2026
aum08desai/test-driven-development
development
VerifiedTrustedCommunity
Use when implementing any feature or bugfix, before writing implementation code. Enforces RED-GREEN-REFACTOR cycle with test-first approach.
6SKILL.mdUpdated Apr 3, 2026
aum08desai/systematic-debugging
development
VerifiedTrustedCommunity
Use when encountering any bug, test failure, or unexpected behavior. 4-phase root cause investigation — NO fixes without understanding the problem first.
6SKILL.mdUpdated Apr 3, 2026
aum08desai/subagent-driven-development
development
VerifiedTrustedCommunity
Use when executing implementation plans with independent tasks. Dispatches fresh delegate_task per task with two-stage review (spec compliance then code quality).
6SKILL.mdUpdated Apr 3, 2026