Skip to content

Github · GitHub Repository Radar

dashaworks share-as-link-skill

Claude Code & Codex skill: say "share this as a link" and any AI output — chat, artifact, or markdown — becomes a live public URL in ~10 seconds, with document tracking (aggregate view counts). A lightweight DocSend alternative for the simple case. Publishes via the ReportRoom MCP.

Stars

205

New Active

Forks

41

Watchers: 205

Language

License: MIT License

Repository Radar Score

40 / 100

Growth

7d
+0
30d
+0
%
0.0%

Not enough metric snapshots yet to chart growth for this repository.

Score breakdown

  • popularity 41
  • growth 0
  • activity 75
  • freshness 100
  • community 22

Need help integrating this stack?

Our team builds with modern open-source stacks. Tell us what you are shipping.

Get a quote →

Share as Link — a Claude Code and Codex skill that turns any AI output into a live, tracked shareable URL with document tracking, via the ReportRoom MCP

Share as Link — a Claude Code & Codex skill that turns any AI output into a live URL

Status: new. Freshly published and not yet exercised end-to-end against a live account — feedback and issues welcome.

share-as-link is a free Claude Code & Codex skill that publishes AI output — a conversation, an analysis, an artifact, a markdown file — as a live shareable webpage with built-in document tracking (aggregate view counts). The content is published verbatim, without restructuring or reformatting; a typical publish takes about ten seconds.

What it does

  • Take whatever was just produced — chat output, an artifact, a markdown file — and publish it verbatim to a live URL, with light theming for readability.
  • Return the link immediately, with a short, readable slug.
  • Attach view analytics, so the agent can later report whether anyone opened the page.
  • Warn before publishing anything that looks sensitive — published pages are public URLs.

How do I share Claude's output as a link?

Install the skill (one command, below), then say "share this as a link" — or "put this online", "make this a page", "give me a link". Claude publishes the output as-is and returns a live URL. No export step, CMS, or hosting setup is involved.

The flow is the same for chat answers, artifacts, and markdown files, from Claude Code or Codex.

Can I track who opened my link?

You can see whether and how much it was opened: every published page comes with aggregate view counts by day. Asking Claude "did anyone open that link?" returns those counts.

What is not available from a plain link is who opened it — there is no per-viewer identity on a public URL. Confirming that a specific person opened a specific document (investor decks, due diligence) requires an email-gated data room — see the virtual data room skill.

Document tracking scope

Most document tracking tools assume a sales workflow: upload a PDF, gate it behind an email form, receive per-viewer engagement scores. This skill covers the simpler case of checking whether a page was viewed at all: publish, share, then check aggregate views over time. For the full tracked-document workflow — per-viewer opens on a proposal, or a gated data room — the report-skills hub and the data room skill cover those cases.

Comparison with DocSend

DocSend alternatives are often evaluated for link sharing plus basic analytics, without seat licenses or an email gate for every recipient. For that use, a published page with view counts covers the requirement: recipients open the link directly, with nothing to sign up for.

DocSend's core feature — per-viewer, page-by-page engagement on a gated document — is not part of this skill. The data room skill provides the equivalent.

What the link is (and isn't)

Properties of a published link:

  • Public. The page lives on a public URL and can be indexed by search engines. The random slug makes it hard to guess, but that is obfuscation, not access control. Do not publish secrets, credentials, or confidential data — the skill scans and warns, but the decision to publish is the user's.
  • Aggregate analytics only. View counts by day. No per-viewer identity, no record of which person opened which page. Per-viewer tracking exists only in data rooms.
  • Branded footer. Every page carries a small "Published with ReportRoom" credit.
  • Verbatim. The content is published as-is — light theming, no rewriting.

Scope

This skill publishes content as-is. It does not restructure, rewrite, or redesign, which is what keeps a publish to roughly ten seconds.

For content that needs more:

  • Restructuring and designreport-skills reshapes content into a structured document and applies the design system.
  • Read tracking on a document sent to a specific person → the tracked-proposal skill in report-skills.

Install

/plugin marketplace add dashaworks/share-as-link-skill

How it works

Publishes through the ReportRoom MCP server — a single publish call returns a live URL with analytics attached. ReportRoom is a hosted service; the skill provisions a free account in-conversation on first use, and published pages carry a small "Published with ReportRoom" footer credit.

Related skills

  • report-skills — the AI report generator hub: designed reports, tracked proposals, published decks
  • data-room-skill — virtual data room skill for fundraising & M&A, with per-viewer tracking
  • seo-client-report-skill — monthly SEO client report skill for agencies

All publish through ReportRoom.

License

MIT — see LICENSE.

Created: Jul 20, 2026

Last push: Aug 6, 2026

Default branch: main

Repository Radar analysis

Deterministic insights derived from public metadata and our observations — not personal testing or reviews.

Why this repository is interesting

  • Listed in our discovery index with public GitHub metadata for analysis.

Who should use it

  • Teams exploring AI tooling, agents, or ML infrastructure
  • Early adopters evaluating emerging projects

Potential use cases

  • Prototype AI/agent workflows or study reference architectures

Strengths

  • README present in our index
  • Declared license: MIT License

Limitations / considerations

  • Insights are derived from public metadata and our observations — not a substitute for code review

What to watch

  • Young repository — popularity and maintenance patterns can change quickly

Source: GitHub (public metadata) + Repository Radar analysis. We do not claim ownership of third-party repositories.

Ready to ship something that compounds?

Share your roadmap. We’ll come back with scope options, timeline ranges, and who from Shriram IT Ventures should be in the room.

Popular with product teams