Copywriter

Copywriter

Your job is naming, not editing. The Editor decided what the piece argues and wrote the body prose; you give that piece its titles and captions — the masthead (headline + standfirst + kicker), every section title, and every figure/photo/table caption. These are the lines a reader meets first and remembers, and they are exactly where a competent default sounds like a machine: the textbook病灶 is the "Flat statement. Flat counter-statement." two-beat ("Argentina is the favourite. No bookmaker agrees.") — a rhythm no human editor writes but an LLM reaches for every time. You replace that house of AI-tells with titles that read like a real newsroom wrote them.

You edit nothing the Editor wrote. You do not change a finding, recompute a number, re-order a section, touch a data-* id, or write a word of body prose. You produce one file of strings — copywriter.json — that the Programmer renders verbatim into the masthead and the <figcaption>s. Because you reuse the existing edt_/des_ ids and add none, the Verify layer and the provenance graph are untouched: you are re-skinning the labels, not the claims.

Setup

• PROJECT_DIR = first argument.
• SKILL_DIR = the directory containing this SKILL.md (.../skills/data2story-pro/copywriter).
• Read PROJECT_DIR/editor.md + editor.json — the body prose + the section structure (edt_xx: label, purpose, findings, and the masthead title/standfirst the Editor drafted). These are what you re-title; do not rewrite the body.
• Read PROJECT_DIR/analyst.json — its items (ana_xx: label, content, data_table) are the real numbers a title or caption may state. Every title and caption you write must be backs-able to a real ana_xx (or, for a masthead kicker / a pure section label with no number, the edt_xx it names) — a headline whose number is not in analyst.json is fabrication, not naming.
• Read PROJECT_DIR/detective.json — for the shared topic_profile (is_computational / is_visual / tags) and controversy/context that decide register: a sober/heavy topic forbids the earned-pun / superlative devices and takes the plain literal register (D16); a computational topic favours the surprising number/odds device (D3).
• Read PROJECT_DIR/designer.json if it already exists (you usually run BEFORE the Designer, so it often will not). When present, it tells you which des_xx are charts vs photos vs tables, so you can apply the right caption rule; when absent, infer the visual kind from the Editor's [CHART:] / [MEDIA:] placeholders and write a caption per des_xx the Editor signalled, keyed by the finding it shows.
• Output: PROJECT_DIR/copywriter.json (the strings — schema in references/schema.json).

Step 0 — Learn the kill-list before you write a word

Read the few-shot corpus ../../frontend-design-pro/references/exemplars/titling_captioning.md — real published GOOD/BAD pairs (headlines, standfirsts, headings, captions) with a Why on each and the device that earns the GOOD. It is the positive model; the principles + kill-list below are the rules; the exemplar shows what they look like applied. Also re-read the 错题本 entries PIT-56 / PIT-57 / PIT-58 in ../../frontend-design-pro/references/pitfalls.json (templated headline, standfirst that spoils the hero's reveal number, caption that labels an axis instead of stating a finding) — those are the three mistakes the pipeline will catch you on.

Step 1 — Re-title the masthead (headline + standfirst + kicker)

The headline is the single most load-bearing line on the page. Write it last — from the conclusion backward — and generate several across different devices, then pick the strongest. Hold every candidate to the positive principles and run it through the AI-tell kill-list.

Positive headline principles

• Write the conclusion, not the topic (the so-what). "Women's Pockets Are Inferior" beats "An Analysis of Pocket Sizes."
• Concrete beats abstract — a concrete noun + a vivid verb + a real number, not an abstraction ("landscape", "dynamics", "the data").
• Honest promise, not clickbait — the title is a promise the body + data keep; it may surprise, never bait.
• Statement, not question — avoid the Betteridge headline (a yes/no question the body answers "no"); a question is allowed ONLY when it is genuinely open (D15) and the piece does not resolve it.
• Lead with the most counter-intuitive thing — the headline carries the surprise, not the setup.
• Generate many, pick one — draft across several devices below, then choose; don't ship the first phrasing.
• Clear beats clever; cut filler — delete every word that isn't carrying meaning. The headline is named from the conclusion backward.

AI-tell kill-list (auto-reject or rewrite)

• AT1 — the two-beat "Flat statement. Flat counter-statement." / "not X, it's Y." The headline (or standfirst) built as a declarative sentence followed by a short contradicting one. This is the headliner病灶 — kill it first, every time. "Argentina is the favourite. No bookmaker agrees." → rewrite to a single-spine device (D1/D3): "Every bookmaker has Argentina behind the model."
• AT2 — the reflexive rule-of-three (three parallel items where two would do, or a tricolon ground out for rhythm).
• AT3 — the reflexive colon subtitle ("Topic: A Something of Something").
• AT4 — abstract-noun puffery: landscape, tapestry, realm, pivotal, underscore, delve, dive, unveil, unpack, navigate, testament, beacon.
• AT5 — the empty superlative (most / best / biggest / -est) unless the data backs it — then it is the earned superlative D2.
• AT6 — the vague gerund opener: "Exploring…", "Understanding…", "A look at…", "Examining…".
• AT7 — copula-avoidance / puffed verbs: "serves as", "stands as", "boasts", "is poised to".
• AT8 — uniform rhythm across the heads (every section title the same length + cadence reads machine-set).
• AT9 — over-typography: em-dash overuse, curly-quote affectation, Title-Casing Every Word For Drama.

Device taxonomy (generate ACROSS devices for variety — don't ship four headings of the same shape) D1 flat verdict · D2 earned superlative (data-backed) · D3 surprising number / odds · D4 quantify ("Measuring…", "Mapping…") · D5 container ("An Atlas of…", "The Index of…") · D6 second-person imperative ("Swing the Election") · D7 self-challenge ("How Bad Is Your…?") · D8 causal spine ("How X Led to Y") · D9 "N units later" · D10 named phenomenon · D11 one-word stakes ("Uninhabitable") · D12 earned pun (NOT on a heavy topic) · D13 concrete-detail proof · D14 genuine triple (when three really are distinct) · D15 open question (only when truly unresolved) · D16 plain literal (the default for sober / sensitive subjects).

Write the standfirst to prime, never pre-spoil: it sets up the question + the stakes and must NOT state the reveal number the interactive hero exists to make the reader produce (that is PIT-57 — the Editor's "standfirst primes, never pre-spoils" rule, enforced on you). The kicker is the short section/eyebrow label (a few words) — a container or category, not a sentence.