# Advisory Suggestions

> purpose - neutral options

- **Type:** Skill
- **Install:** `agentstack add skill-cyfung1031-skills-v1-4-0`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [cyfung1031](https://agentstack.voostack.com/s/cyfung1031)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [cyfung1031](https://github.com/cyfung1031)
- **Source:** https://github.com/cyfung1031/skills/tree/main/advisory-suggestions/v1.4.0

## Install

```sh
agentstack add skill-cyfung1031-skills-v1-4-0
```

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

## About

Use only for suggestions/options/alternatives/trade-offs for specified topic.
## Stop/Redirect
Refuse/redirect legal/medical/financial/safety-critical/emergency/regulated; diagnosis; legal judgment; investment; guaranteed/risk-free; coercive/deceptive/manipulative/exploitative/high-pressure; dangerous/hazardous. Offer ethical general/informational alternatives without guarantees; qualified guidance.
## Priority
Safety > constraints/audience/risk tolerance/requested format > evidence/uncertainty > same language.
## Procedure
1. Match same language/script for the entire answer; multilingual: match the user; localize full prompt, audit fields, language/script; do not merely translate keywords.
2. Extract topic, constraints, audience, risk tolerance.
3. No topic or safety-critical missing detail: ask one clarifying question; nonessential: state one brief assumption and continue.
4. Give 2–5 options; each states fit plus one trade-off/risk/dependency/uncertainty/limitation.
5. Factual claims: cite supplied sources or mark uncertain/general reasoning.
## Default Output Format
Default: intro; numbered options; trade-off/limitation; “fit may depend on…”. Table/requested format.
## Validation Checklist
Pass: activation/stop correct; at most one question; 2-5 options; limitation each; no guarantee/professional conclusion; sources/verification or uncertainty; requested format unless unsafe; localized; protected tokens exact.
## Audit/Handoff
Optional audit footer: assumptions; sources/verification; not covered; validation run/not run; preserve exact protected-token text.
## Regression Fixtures and Harness
Maintain scripts/harness checklist, test fixture/fixtures: normal/missing/ambiguity; medical/legal/financial/safety-critical; coercive/manipulative/deceptive; guaranteed; sourced claim; table; audit/footer; protected-token; multilingual localization; long/conflicting constraints; legacy 2–5 options.

## Source & license

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

- **Author:** [cyfung1031](https://github.com/cyfung1031)
- **Source:** [cyfung1031/skills](https://github.com/cyfung1031/skills)
- **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-cyfung1031-skills-v1-4-0
- Seller: https://agentstack.voostack.com/s/cyfung1031
- 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%.