aum08desai/research-idea-generation
skills/research/research-idea-generation/SKILL.md
Generate and score candidate LLM research ideas from sparse user goals. Use when a project starts with no concrete benchmark, dataset, or training recipe and the agent needs to propose plausible, testable directions.
$ install --global
skillsauthnpx skillsauth add aum08desai/hermes-research-agent research-idea-generationInstall 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, 11:23 AM306.3s2 files scanned
SKILL.md
- name:
- research-idea-generation
- description:
- Generate and score candidate LLM research ideas from sparse user goals. Use when a project starts with no concrete benchmark, dataset, or training recipe and the agent needs to propose plausible, testable directions.
- version:
- 1.0.0
- author:
- Hermes Research Agent
- license:
- MIT
- tags:
- [research, ideation, literature, zero-spec]
Research Idea Generation
Use this skill when the user gives a vague or open-ended research goal.
Workflow
- Search recent literature and identify recurring limitations, evaluation gaps, or underexplored settings.
- Produce 3 candidate directions.
- For each direction, write:
- one-sentence thesis
- why it might work
- the likely benchmark or eval target
- expected cost/risk
- Score each direction on:
- novelty
- feasibility
- cost
- evaluation clarity
- Choose one and explain the decision in terms of upside versus execution risk.
Constraints
- Prefer ideas that can be tested with a clear baseline and measurable success criterion.
- Avoid open-ended ideas that require undefined new infrastructure for v1.
- Record all candidates and the chosen direction with
research_state.
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