# Control Knowledge Explorer

> Explore and structure local EDA knowledge, identify evidence gaps, and prepare targeted literature retrieval tasks for local download and follow-up parsing.

- **Type:** Skill
- **Install:** `agentstack add skill-mr-fang-vlsi-edagent-control-knowledge-explorer`
- **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/control-knowledge-explorer

## Install

```sh
agentstack add skill-mr-fang-vlsi-edagent-control-knowledge-explorer
```

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

## About

# Control Knowledge Explorer

## When to use

Use this skill at the start of a research topic or when evidence is fragmented across KB, logs, and papers.

## Knowledge And Tool Interaction

1. Use `eda-context-accessor` when the task first needs a shared scoped KB/tool snapshot before deeper evidence-gap mapping begins.
2. Treat the local knowledge base as the primary evidence source once exploration starts.
3. Write outputs as reusable knowledge artifacts that later skills can consume directly.

## Workflow

1. Read core KB context and recent experiment summaries.
2. Build a gap map:
- known claims,
- uncertain assumptions,
- missing evidence.
3. For missing external evidence, delegate to `eda-paper-fetch` and generate a local download queue.
4. If local PDFs are available, delegate parse/summarize to `eda-pdf-local-summary`.
5. Produce explicit research questions that can be tested in later experiment design.

## Outputs

1. `knowledge_gap_map.md`
2. `paper_download_queue.tsv`
3. `evidence_to_question_map.md`

## Hard rules

1. Distinguish confirmed evidence from hypotheses.
2. Do not present unsourced claims as conclusions.
3. Keep file/path-level references for each key claim.

## Reference

Load when needed:
1. `references/exploration-checklist.md`

## 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-control-knowledge-explorer
- 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%.