agentsclimarketplace
Sign in

Data corrections writer

Skill ur-grue/autopunk-media-skills/skills/data-journalism/publishing/data-corrections-writer

Writes a precise, publication-standard corrections notice for a data error published in an article — stating clearly what was wrong, what the correct figure is, and how the error affected the reported story.From its SKILL.md

Install
npx -y skills add ur-grue/autopunk-media-skills --skill data-corrections-writer

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 21 stars21 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

5.2 KB, ~1.0k tokens by cl100k_base, as published. Nobody here has run it

Data Corrections Writer

What This Skill Does

Writes a precise, publication-standard corrections notice for a data error published in an article — stating clearly what was wrong, what the correct figure is, and how the error affected the reported story.

When To Use This Skill

  • A data error has been identified in a published article and needs a formal correction notice
  • You need to word a correction that is honest about the scope of the error without overstating its impact on the story's conclusions
  • A reader or subject has disputed a figure and you have confirmed the error
  • An editor or legal team needs a corrections draft to review before publication

What You Need To Provide

Required: The original published figure (as it appeared in print or online). The correct figure. The article headline or title and publication date. A brief explanation of how the error occurred (if known — this can be "we do not know how this error occurred"). Optional: Whether the error affects the story's main conclusion (yes / no / partially); whether a related chart, table, or infographic also needs correction; the publication's standard corrections format or style.

How the Assistant Approaches This

  1. Drafts a correction that states the error precisely — the original figure, the correct figure, and where in the article it appeared — without defensive language or over-explanation.
  2. Assesses whether the correction should include a note on whether the story's core finding is affected, and drafts appropriate language: affirming the conclusion stands, or acknowledging that it changes.
  3. Produces the correction in the standard form: present tense, direct, no passive constructions that obscure responsibility.

Output Format

A corrections notice of two to five sentences. Standard structure: (1) The article title and date, (2) what was wrong and where it appeared, (3) what the correct figure is, (4) whether the error affects the article's conclusions. Optionally: a note on what caused the error if this is known and disclosable. Tone: direct, factual, no hedging. Plain language.

Quality Criteria

  • The original wrong figure is stated exactly as published
  • The correct figure is stated exactly
  • The location of the error in the article is specified (e.g. "in the second paragraph," "in the chart caption")
  • The correction states whether the story's central conclusion is affected
  • No defensive or minimising language (e.g. "a small error," "slight discrepancy")
  • No vague language (e.g. "some figures were incorrectly stated")

Example

Input

Original published figure: "North Coastal Authority had a year-on-year increase in orthopaedic waiting times of 32%" Correct figure: 22% Article: "Waiting time crisis: the regions left behind" published 14 March 2026 Where in article: Second paragraph and repeated in chart caption How error occurred: A data processing error in the original spreadsheet transposed two digits in the percentage change column Does it affect the conclusion? No — the finding that North Coastal had the highest rate of increase among all authorities remains correct even with the corrected figure

Output

Correction

In our article "Waiting time crisis: the regions left behind" (14 March 2026), we stated that North Coastal Authority recorded a year-on-year increase in orthopaedic waiting times of 32%. The correct figure is 22%. This error appeared in the second paragraph of the article and in the caption of the accompanying chart; both have been updated. The error resulted from a data processing mistake in which two digits in the percentage change calculation were transposed. The correction does not affect the article's central finding: North Coastal Authority recorded the highest rate of increase among all 47 health authorities analysed, and that finding holds with the corrected figure.

Corrected: 16 March 2026

Known Limitations

  • This skill drafts the correction based on the information provided. If the scope of the error is larger than described (e.g. if the same source error also affected other figures in the article), the correction draft will not reflect that. A full audit of all figures derived from the same source is recommended before the correction is published.
  • Some publications have specific house style requirements for corrections (placement, format, wording conventions). The draft should be reviewed against those standards before publishing.
  • This skill does not assess legal exposure. For errors involving living individuals, financial claims, or allegations, the correction should be reviewed by the publication's legal team before publishing.

Related Skills

What ships with it: 1 file

2.1 KB alongside SKILL.md

Gives 0 of the 12 instructions most docs writing skills give in ~1.0k tokens

Counted across 1,951 of the 3,904 authors here whose files we hold, read 2026-09-06

  • Use third-person for skill descriptionsin 54 of 1951, across 35 files
  • Start descriptions with Use whenin 43 of 1951, across 29 files
  • Run baseline scenarios before writing any skillin 40 of 1951, across 26 files
  • Use active voicein 40 of 1951, across 36 files
  • Map file responsibilities before defining tasksin 36 of 1951, across 29 files
  • Use checkbox syntax for tracking stepsin 35 of 1951, across 27 files
  • Ask one question at a timein 35 of 1951
  • Offer execution options after saving the planin 33 of 1951, across 24 files
  • Include complete code in every stepin 33 of 1951, across 27 files
  • Design units with clear boundaries and interfacesin 31 of 1951, across 23 files
  • Announce the skill usage at the startin 30 of 1951
  • Verify agent compliance after adding the skillin 29 of 1951, across 17 files

Said here and by no other author read

  • State the original figure exactly as published
  • State the correct figure exactly
  • Specify the location of the error in the article
  • State if the story's central conclusion is affected
  • Avoid defensive or minimizing language
  • Avoid vague language

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 325,949. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.