mr-fang-vlsi/eda-idea-debate-lab
skills/eda-idea-debate-lab/SKILL.md
Generate and refine EDA research ideas through structured brainstorming and pro-vs-con debate, then output a testable idea decision memo.
$ install --global
skillsauthnpx skillsauth add mr-fang-vlsi/edagent eda-idea-debate-labInstall 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 16, 2026, 9:08 AM280.6s4 files scanned
SKILL.md
- name:
- eda-idea-debate-lab
- description:
- Generate and refine EDA research ideas through structured brainstorming and pro-vs-con debate, then output a testable idea decision memo.
EDA Idea Debate Lab
When to use
Use this skill when you need to generate new ideas or stress-test an idea before implementation.
Workflow
- Brainstorm at least 3 candidate ideas from current evidence.
- For each candidate, write:
- strongest support (pro),
- strongest objections (con),
- failure modes and disproof signals.
- Run a structured debate:
- side A argues expected upside and feasibility,
- side B argues risk, confounders, and likely false-positive paths.
- Converge to one or two candidate ideas with explicit assumptions.
- Export assumptions into hypothesis design inputs.
Outputs
idea_brainstorm.mdpro_con_debate.mdidea_decision_memo.md
Hard rules
- Steelman both sides; avoid weak strawman objections.
- Every selected idea must have at least one falsifiable key assumption.
- Do not skip unresolved risks; list them explicitly.
Reference
Load when needed:
references/debate-template.md
Related Skills
mr-fang-vlsi/eda-stage-checkpoint-golden
development
VerifiedTrustedCommunity
Create immutable stage checkpoints for Innovus flows. Use when users ask for fixed golden files or restart-from-stage workflows (place/cts/route) with matched DEF+V+SDC and reproducible manifests.
7SKILL.mdUpdated Apr 29, 2026
mr-fang-vlsi/eda-script-pattern-curator
tools
VerifiedTrustedCommunity
Capture and maintain reusable script-writing experience across wrappers, helpers, parsers, validators, and runtime shims so future script work can reuse proven patterns and avoid repeated anti-patterns.
7SKILL.mdUpdated Apr 29, 2026
mr-fang-vlsi/eda-pdf-local-summary
testing
VerifiedTrustedCommunity
Summarize local paper PDFs into structured, citation-grounded evidence notes. Use when the user provides local PDF paths and asks for methods/assumptions/results/limitations extraction or wants evidence mapped to current EDA hypotheses.
7SKILL.mdUpdated Apr 29, 2026
mr-fang-vlsi/eda-paper-fetch
development
VerifiedTrustedCommunity
Fetch primary-source paper metadata when evidence is missing or weak for EDA/model/flow claims. Use for requests like building reproducible paper candidate lists, generating user-download queues, and recording citation metadata for local validation.
7SKILL.mdUpdated Apr 29, 2026