agentleFS
sugarforeversugarforever/boring-video-studio/skills/boring-video/to-article/SKILL.md

to-article

Skill186 starsChanged 21 days agoMITView on GitHub

Use when an approved content topic, research bundle, and evidence need to become a complete platform-independent article before video beats or publication adaptation.

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. samuhs/mad-science★ 1same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository10 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 0 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read content/TOPIC.md, content/RESEARCH.md, every cited experiment report, and the source material needed to verify the selected evidence.

    line 12
  2. Very specific:

    Write content/ARTICLE.md with this frontmatter:

    line 26
  3. Very specific:

    Before presenting content/ARTICLE.md or any later revision, follow ../boring-video/references/markdown-review.md.

    line 60

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

To article

Turn an approved content/TOPIC.md into content/ARTICLE.md: the readable content master for both the eventual blog post and the video plan.

Preconditions

Read content/TOPIC.md, content/RESEARCH.md, every cited experiment report, and the source material needed to verify the selected evidence. Continue only when TOPIC.md has status: approved.

Return to /develop-topic when writing exposes a missing material claim, contradictory evidence, an unsupported conclusion, or a needed change to the approved audience, thesis, scope, argument, evidence, or conclusion boundaries. Immediately return TOPIC.md to status: draft, resolve the gap there, and renew topic approval before drafting from it. Adding evidence that changes the confidence, boundary, or interpretation is material; adding an equivalent source without changing the contract is not.

Voice

Resolve the article voice from the approved topic. Before drafting, inspect the available skills for a writing-style skill matching the output language and content type, then load every applicable user, project, or brand style source named in voice.skills or voice.documents.

If no reliable source exists for a publication-grade article, ask one compact question for the desired voice or a sample. When the user delegates that choice, or the article is explicitly an internal draft, use a clear explanatory default and record voice.status: assumed. Record unavailable named sources under voice.unavailable; they are not evidence that their rules were applied. An unavailable source does not block drafting when another available source resolves the voice.

Draft

Write a complete, platform-independent article. It must stand alone for a reader, preserve the approved argument and boundaries, distinguish fact from interpretation, and cite the original sources behind material claims. Use headings, links, tables, or notes when they help reading; site-specific SEO fields, publishing components, and platform paths belong to a later publishing adaptation.

Write content/ARTICLE.md with this frontmatter:

---
source: content/TOPIC.md
source_digest: sha256:<TOPIC approved_digest>
status: draft
voice:
  language: ...
  skills: []
  documents: []
  unavailable: []
  status: resolved | assumed
---

The article may improve the working title, prose, examples, and section order. It may compress or explain approved claims, but every material fact, viewpoint, and conclusion must trace to the approved topic and its evidence. New content goes upstream first.

Approval gate

Present the complete article for review. Only explicit user approval changes its frontmatter to:

status: approved
approved_at: YYYY-MM-DD
approved_digest: sha256:<digest>

Compute approved_digest as SHA-256 of the complete file after removing only the approved_digest: line. Before drafting or approving, recompute the topic digest and require it to match both TOPIC.md's approved_digest and this article's source_digest. A mismatch makes the relevant approval or dependent draft stale. A verified non-material edit may refresh and propagate digests without renewed approval.

Until then, do not create BEATS.md. A request to continue production does not substitute for approval of the article itself.

A material revision to TOPIC.md returns the article to draft. A material revision to an approved article also returns it to draft; copy edits, title changes, and examples that preserve the approved meaning do not.

Before presenting content/ARTICLE.md or any later revision, follow ../boring-video/references/markdown-review.md. Keep the canonical Markdown path as the current version and apply review feedback there.

The article is complete when it is approved, reads independently, every material statement traces to the approved content contract and sufficient evidence, a video planner can reorganize it without inventing facts, viewpoints, argument, or scope, and the Markdown review completion criterion is satisfied.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.