Menu
Members Video skillAI tools and software explainers15–60 sec

Pipeline Stage Feed

Show a multi-stage software process as visible states and artifact handoffs on a vertical rail.

Two 19.2-second English pipeline stories with explicit stage states and artifact handoffs, plus a verified edit. 9:16 · 0:19

What you get

  • A vertical stage rail with explicit status and output artifact
  • Two different software-process briefs and one local stage edit
  • 1080×1920 / 30 fps video, burned captions, SRT and DOM-measured layout

You will need

  • Node.js 22+, FFmpeg/FFprobe and a browser
  • Three named stages and artifacts
  • Local Kokoro or an explicit silent export

Good fit

  • Git delivery stages
  • AI research handoffs
  • Build and review pipelines

Not for

  • A radial integration map
  • A generic checklist
  • Unverified claims about throughput or quality

You say

“Use Pipeline Stage Feed to explain how work moves through named stages. Provide three stages, their current statuses, and the artifact each stage hands forward; do not claim a measured improvement from an illustrative pipeline.”

After installing, say something like this to your agent with your own topic and assets. It asks only for what is missing.

FAQ

Do I need an account?

Yes. Members Skills install from a signed-in FeedSkills account with an active Founding Membership.

What does it cost to run?

The Skill is included with Founding Membership. It needs the tools listed under “You will need”. Any voice, model or media service you choose bills you directly; FeedSkills does not include provider credits.

Can I use the videos commercially?

Videos you make are yours to use, including commercially. The Skill package is licensed as: FeedSkills Source-Available License 1.0 · fonts SIL OFL 1.1. Fonts, music, footage and services you add keep their own terms.

Which agents does it work with?

Agents that read SKILL.md files, such as Codex or Claude Code. What FeedSkills has actually tested is listed under Tested scope below.

Tested scope

Version
0.1.0
Acceptance
This version has a recorded acceptance entry.
Tested
Two 19.2-second 1080x1920 / 30 fps English example films and one single-scene edit were rendered with burned captions, measured DOM layouts and full-stream checks; both themes recorded 19 passes, 0 info, 0 warnings and 0 fails. The edit rerendered s4 and reused the other five scenes with native-frame proof; package check/create and DOM guard passed. Real-phone review and customer adoption remain separate.
Runs on
Codex · macOS · Node.js 22+ · FFmpeg
License
FeedSkills Source-Available License 1.0 · fonts SIL OFL 1.1

Details

Pipeline Stage Feed

Pipeline Stage Feed is a Members Skill for showing work moving through named stages with visible statuses and artifact handoffs. It is a process explanation, not a throughput dashboard.

Reviewed A/B previews

Both examples show three ordered stages, explicit state and a named artifact passed forward. They are code-rendered English explainers with burned captions, SRT, measured layout and a local-edit path; illustrative pipelines do not claim a quality or speed improvement.

Install and use

Install the approved member package with:

npx --yes --package=https://feedskills.com/downloads/feedskills-0.3.6.tgz feedskills install pipeline-stage-feed --agent codex

Copy examples/theme-a.json or examples/theme-b.json into a project outside the installed Skill. Supply three named stages, each status and the artifact handed forward, then validate, create and render with the included scripts. Use local Kokoro for narration; node render.mjs --no-voice is an explicit silent export.

For a single-scene revision, keep stage order, ids and durations stable, edit one copied scene, rerun the render and inspect render-report.json. Compare the changed scene with native decoded frames for the five unchanged scenes.

Boundaries

Show the artifact actually produced by each stage and keep status claims tied to the input. A blocked stage is an observed input state, not a diagnosis of the external system. Do not use decorative arrows, remote logos or paid media generation as evidence.