# Control Preflight Reflect

> Before each experiment, analyze latest route/STA evidence, reflect on method gaps, and output concrete improvement hypotheses and next-step A/B plan. Use when user asks to start new experiments or when model/flow conclusions may be unstable.

- **Type:** Skill
- **Install:** `agentstack add skill-mr-fang-vlsi-edagent-control-preflight-reflect`
- **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-preflight-reflect

## Install

```sh
agentstack add skill-mr-fang-vlsi-edagent-control-preflight-reflect
```

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

## About

# Control Preflight Reflect

Run this skill before submitting new experiment batches.

## Background Knowledge Links

This skill should stay linked to:
1. the current route-policy and comparison-policy KB context,
2. local paper-derived or primary-source notes when assumptions about routing behavior may drift,
3. experiment-experience artifacts from `eda-experiment-phenomenology-analyst` when similar branches were already attempted,
4. `eda-context-accessor` when current KB or paper context is missing from the preflight brief.

If the latest evidence contradicts background knowledge, surface that contradiction directly in the reflection artifact and trigger KB feedback rather than hiding it inside a generic root cause label.

## Mandatory outputs
1. `preflight_reflection_*.md`
2. selected next-step plan (A/B/C)
3. explicit go/no-go for new experiment submission

## Operational References

1. Load `references/evidence-lock.md` when collecting required artifacts and deciding whether the run is in `insufficient_evidence` state.
2. Load `references/checklist.md` when scoring the explicit preflight checks and producing pass or fail per item.
3. Load `references/reflection-artifact.md` when writing the root-cause ranking, A/B/C plan, and acceptance criteria.
4. Load `references/model-gap-patterns.md` when deciding whether simple `min(front,back)` logic should be vetoed in favor of a judgment model path.

## 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-preflight-reflect
- 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%.