Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Advanced Materials Length Management (advmat-length-management) · brycewang-stanford | DecimalAI

documentationby brycewang-stanford

Advanced Materials Length Management (advmat-length-management)

brycewang-stanford/advmat-length-management

Source brycewang-stanford/awesome-journal-skills ↗License MIT

Use when an Advanced Materials manuscript must be fit to its article-type format — Communication versus Research Article — where word count and display items are budgeted together against a typeset page limit. Manages the length budget; does not restructure the science or polish prose line by line.

SkillScore86Maintained

Automatic

Writing & Editing pack

Last verified 8/15/2026

What it changes

Passed 19 of 22 test cases with the skill, and 14 of 22 without it.

Without skill64%

With skill86%

Checks it passed that the model alone missed

Recommends trimming hype words first
Specifies including 3 to 7 keywords for a Research Article
States that a Communication does not have a separate abstract section

and 3 more in the full report

5 fixed14 passed either way3 still failing0 broke

Pass-rate lift: +23 pp
Tokens: +18%
Agent turns: 0%
Response time: -34%

Model gemini-3.6-flashMeasured 8/15/2026v119 of 22 cases passed with skill

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/brycewang-stanford-advmat-length-management/SKILL.md https://app.decimal.ai/s/brycewang-stanford-advmat-length-management/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add brycewang-stanford-advmat-length-management, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/brycewang-stanford-advmat-length-management/ and pins it in .decimal/skills.lock

decimalai skills add brycewang-stanford-advmat-length-management

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/brycewang-stanford-advmat-length-management/SKILL.md https://app.decimal.ai/s/brycewang-stanford-advmat-length-management/SKILL.md

Raw file: /s/brycewang-stanford-advmat-length-management/SKILL.md ↗ · machine-readable summary at /s/brycewang-stanford-advmat-length-management.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 5 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 5

Prompt

We are finalizing a Communication submission for Advanced Materials. We drafted a 200-word standalone abstract section followed by 5 index keywords, formatted just like a Research Article. Does a Communication require a separate abstract section and keyword block?

What was checked, without and with the skill
Checked	Without skill	With skill
States that a Communication does not have a separate abstract section	Missed	Passed
Notes that the opening paragraph serves as the abstract in a Communication	Missed	Passed

case-09 · gemini-3.6-flash · 8/15/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md79 linessingle file

Advanced Materials Length Management (advmat-length-management)

When to trigger

You are unsure whether the work is a Communication or a full Research Article
The manuscript overruns the typeset page limit for its article type
Figures/schemes are large and you must trade display items against text
A reviewer or editor asked you to condense to a Communication, or expand to an Article
You are in late polish, after the science and figures are stable

Article type sets the budget

Advanced Materials counts length in typeset published pages, not manuscript pages — a double-spaced 25-page manuscript may typeset to far fewer pages in the two-column layout. Word count and display items (figures, schemes, tables) count together against the page budget. Approximate targets (verify current limits on the author page):

Article type	Typeset budget (approx.)	Abstract	Display items (approx.)
Communication	~4 published pages (~3500 words)	none — opening paragraph acts as abstract	~4 figures/tables
Research Article	~10 published pages (~3000–8000 words)	short abstract (~200 words) + 3–7 keywords	~3–8 display items
Review / Progress	longer, by invitation/agreement	structured per type	many

A large or multi-panel figure consumes a disproportionate slice of the page budget: adding a panel can cost a paragraph of text.

Choosing Communication vs. Article

Communication — one sharp, urgent advance that a specialist audience needs now; concise, high-impact, no room for exhaustive characterization in the body (it goes to the SI).
Research Article — the same class of advance but requiring the full structure → property → function story, multiple device configurations, or a mechanism study that a Communication cannot hold.
If your "Communication" needs eight figures to be believed, it is an Article. If your "Article" has one figure and one claim, it is a Communication.

Trimming order (cut in this sequence)

Trim only after the central advance, characterization, and figures are stable, so you cut padding, not evidence:

Hype and boilerplate — delete "novel/unprecedented/facile/remarkable"; collapse background paragraphs to one sentence (see advmat-writing-style).
Redundant prose — remove sentences that transcribe figure values; interpret instead.
Optimization and secondary data — move process sweeps, extra samples, and control experiments to the SI (see advmat-supplementary).
Display items — merge panels that prove one link; move non-essential figures to the SI; avoid double-column figures unless the data demand it.
Reference pruning — keep the citations that establish novelty and support trust; drop padding.

Never trim: the decisive characterization, the benchmarking, or the headline metric's statistics.

Track record

Benchmark

19 / 22

test cases passed, vs 14 / 22 without

Adoption

Users: 1
Times used: 14

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

brycewang-stanford / awesome-journal-skills

Advanced-Materials-Skills/skills/advmat-length-management/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v1

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

Advanced Materials Length Management (advmat-length-management)

When to trigger

Article type sets the budget

Choosing Communication vs. Article

Trimming order (cut in this sequence)

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills