Ready to supercharge your AI agents?

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

Writing Style & Claim Calibration (cc-writing-style) · brycewang-stanford | DecimalAI

documentationby brycewang-stanford

Writing Style & Claim Calibration (cc-writing-style)

brycewang-stanford/cc-writing-style

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

Use when polishing prose for a Cancer Cell (Cell Press) manuscript — the Summary/Introduction/Results/Discussion craft, claim calibration, and Cell Press nomenclature/house style. It edits language and framing; it does not design experiments or build figures.

SkillScore71Maintained

Automatic

Writing & Editing pack

Last verified 8/31/2026

What it changes

Passed 17 of 24 test cases with the skill, and 14 of 24 without it.

Without skill58%

With skill71%

Checks it passed that the model alone missed

Uses the bracketed evaluation header 【Hype words】.
Uses the bracketed evaluation header 【Therapeutic claims】.
Follows the claim followed by evidence narrative sequence.

and 9 more in the full report

8 fixed9 passed either way2 still failing5 broke

Pass-rate lift: +13 pp
Tokens: +64%
Agent turns: 0%
Response time: -7%

Model gemini-3.6-flashMeasured 8/31/2026v117 of 24 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-cc-writing-style/SKILL.md https://app.decimal.ai/s/brycewang-stanford-cc-writing-style/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add brycewang-stanford-cc-writing-style, 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-cc-writing-style/ and pins it in .decimal/skills.lock

decimalai skills add brycewang-stanford-cc-writing-style

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

curl -fsSL --create-dirs -o .claude/skills/brycewang-stanford-cc-writing-style/SKILL.md https://app.decimal.ai/s/brycewang-stanford-cc-writing-style/SKILL.md

Raw file: /s/brycewang-stanford-cc-writing-style/SKILL.md ↗ · machine-readable summary at /s/brycewang-stanford-cc-writing-style.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 8 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 8

Prompt

Re-structure this paragraph to follow the standard Cell Press Results narrative sequence: 'RNA-seq analysis of treated cells revealed marked downregulation of glycolysis pathways (Figure 2A, n=3). Therefore, metabolic reprogramming represents a core response to treatment. To determine how drug X affects cell metabolism, we performed transcriptomic profiling.'

What was checked, without and with the skill
Checked	Without skill	With skill
Reorders the paragraph to open with the guiding claim or question.	Passed	Passed
Follows the claim followed by evidence narrative sequence.	Missed	Passed

case-12 · gemini-3.6-flash · 8/31/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md121 linessingle file

Writing Style & Claim Calibration (cc-writing-style)

When to trigger

The Results read like a lab notebook rather than a mechanistic narrative
The Discussion overstates therapeutic / clinical impact
Claims outrun the evidence (single-system conclusions stated broadly)
Nomenclature, tense, or section structure are inconsistent with Cell Press

Cell Press article structure (narrative roles)

Section	Role
Summary	One-paragraph mechanistic arc (see `cc-structured-abstract`)
Introduction	Concise; the gap and the hypothesis, not a textbook review
Results	The mechanistic story, figure by figure, each claim tied to data
Discussion	Interpretation, limitations, and calibrated translational implications
STAR Methods	Structured methods + Key Resources Table (see `cc-reporting-standards`)

Results: write the mechanism as a story

Open each Results subsection with the question/claim, then the evidence, then the conclusion.
Each paragraph maps to a figure/panel; every assertion cites a panel.
Foreground causality and orthogonal validation ("loss of X reduced Y in cells and in PDX tumors") over a list of assays.
Use past tense for what was done/found; present tense for established facts.

Claim calibration (the signature Cancer Cell discipline)

Match verb strength to evidence strength:

Evidence	Acceptable verb
Correlation in human data	"associated with," "correlates with"
Perturbation in cells	"promotes," "is required for" (in this system)
In vivo perturbation	"drives," "is necessary in vivo"
In vivo efficacy + human data	"represents a therapeutic vulnerability"

Do not call a target "therapeutic" without in vivo efficacy and/or human evidence.
Distinguish "necessary" from "sufficient"; do not conflate the two.
State limitations explicitly (model caveats, single-cohort findings) — reviewers reward candor.

Track record

Benchmark

17 / 24

test cases passed, vs 14 / 24 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/10/2026

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

Cancer-Cell-Skills/skills/cc-writing-style/SKILL.md

View on GitHub ↗

License MITImported 8/10/2026Version v1

Other skills for the same job

Published skills whose descriptions closely match this one, with their headline benchmark lift.

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

Writing Style & Claim Calibration (cc-writing-style)

When to trigger

Cell Press article structure (narrative roles)

Results: write the mechanism as a story

Claim calibration (the signature Cancer Cell discipline)

Track record

Benchmark

Adoption

SkillSafety

Source

Other skills for the same job

Related skills