# Post Update

> >

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

## Install

```sh
agentstack add skill-bioinfo-claudelicious-post-update
```

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

## About

# post-update

The hands, not the author. This skill takes text that was already drafted in the
main session and approved by the user, and shells out the send command. It is the
canonical shape for any skill that posts, sends, or publishes on your behalf.

## DISPATCH-ONLY CONTRACT

This skill MUST NOT compose or edit the message it sends. The content is drafted
in the main session by the strongest model, shown to the user, and explicitly
approved BEFORE this skill is invoked.

If this skill is invoked with an instruction to *write* the update (e.g.
"post an update about the launch"), STOP and refuse. Respond: "Draft the update
in the main session, get approval, then invoke me with the approved text." Do not
generate the content here. The judgment and the voice stay with the main session;
only the mechanics are automated.

## Procedure (once approved text is in hand)

1. Confirm you were handed the exact approved text. If you were handed a *topic*
   instead of finished text, invoke the contract above and stop.
2. Dispatch via the channel CLI, e.g.:
   ` post --channel "" --text ""`
3. Report the result (the post URL / message id, or the error verbatim). Do not
   silently retry on failure — surface it.

## Notes

- One send per invocation. Do not fan out to multiple channels unless the user
  approved each.
- Never send on a guess. No approved text, no send.

## Source & license

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

- **Author:** [BioInfo](https://github.com/BioInfo)
- **Source:** [BioInfo/claudelicious](https://github.com/BioInfo/claudelicious)
- **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-bioinfo-claudelicious-post-update
- Seller: https://agentstack.voostack.com/s/bioinfo
- 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%.