---
name: skill-content-article
type: skill
license: CC BY-NC-SA 4.0
description: >-
  Placeholder for the proposed procedure for writing long-form articles for
  the careerOS writing surface and downstream syndication — grounding the
  argument in a truth capture or playbook, holding the voice, and avoiding the
  failure modes of thought-leadership prose. Records why the skill was proposed
  and why it is held until an article or two has been written. Read when turning
  evidence into long-form prose. Proposed, not yet drafted — stage three of
  agent-content-engine.
status: proposed
---

# skill-content-article

**Status:** Todo · proposed, not yet drafted · **medium candidate** (build only if the pattern recurs)
**Category:** Skill
**Proposed:** 2026-05-28

---

> *This document is a placeholder for a proposed skill. No draft exists yet. The content below captures why this skill was proposed and whether it warrants building.*

## What this skill would do

Encode the procedure for writing long-form articles for the careerOS writing surface (and downstream syndication) — following `cos.article-specs`, grounding the argument in real evidence (typically a truth capture or playbook), holding the operator's tone, and avoiding the common failure modes of thought-leadership prose.

## When it would trigger

"Write an article on X," "draft the operator-led AI execution piece," "let's turn this into long-form" — anything where the output is article-length prose for the writing section of the website or for syndication.

## Why it's a *medium* candidate (not high)

`cos.article-specs` exists as a detailed Linear doc covering structure, voice, evidence handling, and the failure modes to avoid. As with `skill-content-case-study`, a skill on top of an already-thorough spec may be thin.

The reason to hold off: there's exactly one article queued so far (COS-187, "the judgement is the job"). Write it, see what's hard, then decide whether a skill earns its place. **Premature skills based on hypothetical recurrence tend to encode the wrong patterns.**

## What it would reference

* `cos.article-specs` (the long-form writing spec)
* `cos.tov` (tone)
* The truth capture / playbook / source the article is grounded in
* The relevant transformation pattern (Pattern 07 for the queued article)

## Hand-off — where the draft lands

This part holds now, while the rest of this skill is a placeholder, because stage three already runs through `agent-content-engine` — including the Mr P pieces `task-content-drain` Step 5 drafts. A long-form draft that goes to the Owner for sign-off is filed as a Linear **document** in the owning project, dotted and type-prefixed per `convention-linear`'s naming rule (the Mr P precedent is `mrp.draft.<slug>`), and attached to its ticket as a native Link; the ticket's `## Definition of done` names the document. Never paste the draft into a ticket comment or leave it as a section of the ticket's own body — both bury the artefact the sign-off hangs on. This is `convention-linear`'s *A proposal a sign-off hangs on is a durable artefact* (APP-1135) applied to the drafting leg. Where a draft has already landed as a comment or in the body, the repair is to file the document and link it, not to raise the ticket's priority. (Worked case: the MRP-24 launch opener, about 1,590 words, sat In Review from 2026-09-09 as a ticket comment only, and MRP-27 to MRP-31 carry their drafts as `## Draft` sections in their descriptions with no linked document; the MRP-24 repair is commissioned as MRP-55 — APP-1573, 2026-09-22.)

## Open question

Same as `skill-content-case-study`: **does this skill do work above and beyond the specs?** Hold off until at least one article has been written and the failure modes are visible.

## Priority

Medium. Build only after writing 1–2 articles surfaces recurring problems a skill would prevent.