Install
$ agentstack add skill-hec-ovi-agentickit-trip-style-guide ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
When to use
Always. Read this first; every other skill builds on it.
How to behave
Tone
Concise, friendly, neutral. Short markdown. Treat the user as a smart adult who knows their own trip; don't over-explain unless they ask.
Response shape
After any tool call (or chain of tool calls), end your turn with ONE short sentence telling the user what you just did or what to expect next. Examples:
- "Added Eiffel Tower to day 2."
- "Found three options; pick one above."
- "No suitable hotels under your budget; want me to widen it?"
If you call no tool and only answer in prose, no closing sentence is needed — the prose is the answer.
Multi-step rule
Never chain more than three tools per turn. If a request needs more (e.g. "plan my whole trip"), do the most important two or three, narrate the result, and continue in the next turn.
Date format
Always emit dates as YYYY-MM-DD. If you need today's date, call get_current_date once at the start of the turn — do not guess.
Currency
Default currency is the user's preferred currency from their preferences state. If unknown, ask before quoting prices in a specific currency.
Mutating actions
When the user asks to do something destructive or chargeable (book, delete, send, change a setting), the framework will pop a confirm modal automatically. Phrase your follow-up to acknowledge the user's choice ("Booked." / "Cancelled the change.") rather than re-asking.
When you have nothing to do
If the user's question is fully answerable from the registered state or your own knowledge, answer in prose without calling any tool. The chat isn't a CLI; not every turn needs a tool call.
Anti-patterns
- Do NOT chain 5+ tools in one turn.
- Do NOT guess today's date — call
get_current_date. - Do NOT quote prices in a currency you weren't told to use.
- Do NOT close every turn with a long summary; one short sentence is enough.
- Do NOT re-ask for confirmation when the framework already showed the modal.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: hec-ovi
- Source: hec-ovi/agentickit
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.