# Eda Autoidea Bridge

> Bridge autoIdea literature recommendation, historical formulation, and idea-generation outputs into the current repo's paper/knowledge/skill workflow.

- **Type:** Skill
- **Install:** `agentstack add skill-mr-fang-vlsi-edagent-eda-autoidea-bridge`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [Mr-Fang-VLSI](https://agentstack.voostack.com/s/mr-fang-vlsi)
- **Installs:** 0
- **Category:** [AI & ML](https://agentstack.voostack.com/c/ai-and-ml)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [Mr-Fang-VLSI](https://github.com/Mr-Fang-VLSI)
- **Source:** https://github.com/Mr-Fang-VLSI/EDAgent/tree/main/skills/eda-autoidea-bridge

## Install

```sh
agentstack add skill-mr-fang-vlsi-edagent-eda-autoidea-bridge
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# EDA AutoIdea Bridge

## When to use
Use this skill when the user wants to combine `external_tools/autoIdea` outputs with current infra:
1. import recommended papers into local download queue,
2. merge autoIdea recommendations with landscape feedback queue,
3. ingest autoIdea idea/experiment drafts into a governed report for follow-up debate and hypothesis design.

## Inputs
- `external_tools/autoIdea` clone with at least one of:
  - `citation_graph_output/recommended_top30.json`
  - `outputs/final_idea.txt`
  - `outputs/experiment.txt`
  - `citation_graph_output/historical_problem_formulation.txt`

## Execution
Run:

```bash
python3 scripts/common/autoidea_bridge.py --autoidea-root external_tools/autoIdea
```

## Outputs
- `docs/papers/queues/autoidea_recommended_top30_bridge.tsv`
- `docs/papers/queues/literature_feedback_merged_with_autoidea.tsv`
- `docs/knowledge_base/99_AUTOIDEA_FUSION_REPORT_20260306.md`

## Integration contract
1. New autoIdea-driven queue rows must still pass current paper/validation gates.
2. Imported idea/experiment drafts are treated as candidates, not accepted plans.
3. Promotion requires `control-theory-veto` and non-regression execution evidence.

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [Mr-Fang-VLSI](https://github.com/Mr-Fang-VLSI)
- **Source:** [Mr-Fang-VLSI/EDAgent](https://github.com/Mr-Fang-VLSI/EDAgent)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-mr-fang-vlsi-edagent-eda-autoidea-bridge
- Seller: https://agentstack.voostack.com/s/mr-fang-vlsi
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.