All skills
harlan-zw avatar

/im-not-a-fly

@4d33e4d

Edit prose for its human reader: clear meaning, accurate claims, concise wording, and preserved voice. Use for blogs, docs, release notes, tweets, email, or copy that needs a reader-focused rewrite.

  • 8 files
  • 35.9 KB
  • Updated 12 hours ago
  • GitHub

Recorded with OpenCode, zai-coding-plan/glm-5.3

PromptRewrite these Markdown documents to remove AI writing tells and make them clear and natural. Preserve all facts, uncertainty, code, links, identifiers, and useful document structure. Return only the requested documents, without review notes. Documents: {"reading-list.md":"# Keeping a reading list that works for you\n\nIn today's fast-paced digital landscape, managing a reading list has become an increasingly important part of staying informed. Indeed, it goes without saying that by leveraging a thoughtful approach, you can transform a simple collection of links into a valuable resource for learning and growth.\n\n## A streamlined approach\n\nIt's worth noting that a reading list doesn't need to be complicated. Our fictional reading-list app, Margin, offers a streamlined approach that truly delivers. Margin stores a title, URL, and category for each link. Furthermore, you can filter by category and bookmark items you want to return to. Everything stays in your browser. It's important to note that there is no account or cloud sync, which keeps things refreshingly straightforward.\n\n## Building better habits\n\nMoreover, a weekly review can help you navigate the ever-growing collection of articles. Remove links you no longer want to read. Keep the ones that connect to a project you are working on. This simple habit can make a world of difference over time.\n\nUltimately, the goal is to create a seamless reading experience that empowers you to make the most of your time. At the end of the day, a small, focused list can be more useful than an extensive collection you never open.","README.md":"# Margin\n\nMargin is a fictional TypeScript package designed to streamline the management of reading lists. It provides a robust yet intuitive API for organizing links by category, enabling developers to create seamless reading experiences.\n\n## Getting started\n\nTo begin leveraging Margin, simply import `filterLinks` and pass your links and the desired category. It's worth noting that the function returns matching links in their original order. Furthermore, passing an empty category returns all links.\n\n```ts\nimport { filterLinks } from 'margin'\n\nconst links = [\n { title: 'CSS notes', url: 'https://example.com/css', category: 'CSS' },\n { title: 'TypeScript notes', url: 'https://example.com/ts', category: 'TypeScript' },\n]\n\nconst cssLinks = filterLinks(links, 'CSS')\n```\n\n## Important considerations\n\nIt's important to note that category matching is case-sensitive. Moreover, the function does not modify the input array. It's also worth highlighting that Margin does not fetch URLs or store links. Ultimately, Margin is solely a filtering function, making it a valuable addition to your toolkit.","pr.md":"# Add category filtering to the reading list\n\nThis pull request introduces a streamlined category filtering experience to our fictional reading-list app, Margin. By leveraging the existing category field, users can now navigate their saved articles with greater ease and efficiency.\n\nPreviously, the list displayed every saved link regardless of the selected category. With this enhancement, selecting a category displays only matching links. It's worth noting that selecting All displays the complete list.\n\nFurthermore, filtering preserves the original order of links and does not change bookmarks. It's important to note that the selected category resets when the page reloads. Moreover, search and saved filter preferences are outside the scope of this change.\n\nUltimately, this improvement provides a more focused and intuitive reading experience while maintaining the simplicity of the existing interface."} Return one JSON object with exactly these keys: "reading-list.md", "README.md", "pr.md". Each value is the complete Markdown document as a JSON string. No outer Markdown fence or commentary.

FolderAI-generated original Markdown and a shared no-Skill rewrite. Three documents about the fictional Margin app and package.

Keeping a reading list that works for you

A pile of saved links is not the same as a useful reading list. A little structure turns one into the other, and into something you actually learn from.

A simple setup

Margin, our fictional reading-list app, keeps it simple. For each link, Margin stores a title, URL, and category. You can filter by category and bookmark items you want to come back to. Everything stays in your browser. There is no account and no cloud sync.

A weekly review

Each week, look over the list. Remove links you no longer want to read. Keep the ones that connect to a project you are working on.

A small, focused list can be more useful than an extensive collection you never open.

Markdown
# Keeping a reading list that works for you

A pile of saved links is not the same as a useful reading list. A little structure turns one into the other, and into something you actually learn from.

## A simple setup

Margin, our fictional reading-list app, keeps it simple. For each link, Margin stores a title, URL, and category. You can filter by category and bookmark items you want to come back to. Everything stays in your browser. There is no account and no cloud sync.

## A weekly review

Each week, look over the list. Remove links you no longer want to read. Keep the ones that connect to a project you are working on.

A small, focused list can be more useful than an extensive collection you never open.

Recorded on an older version of this Skill.

Use this Skill: https://skilld.dev/gh/harlan-zw/brundlefly/im-not-a-fly

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

referencesaccessible-writing.md

≈1.7k tokens on demand. Your agent reads this file only when SKILL.md points to it.

Accessible writing

Start with the useful point. Let readers choose how much detail to read. Use structure to reduce reading effort while preserving the full meaning.

What supports the rules

Research reviewed on 5 October 2026. These sources support different claims and have different limits. The rules combine published guidance with editorial judgment. They do not guarantee accessibility for every reader.

Source Supported practice Evidence limit
W3C cognitive accessibility note, 2021 Summaries, separate instructions, clear language, and whitespace Supplemental guidance, not a WCAG conformance requirement
W3C: avoid too much content Show essential content first; make further detail available Extra images and text can also overload readers
W3C: use clear words Use familiar vocabulary and explain unfamiliar terms Familiarity depends on the audience
British Dyslexia Association style guide, 2023 Short prose, section headings, bullets, and supporting images Specialist practice guidance, not proof of one universal layout
CDC Clear Communication Index Put the main message first; group information with headings and lists Developed for public health communication
Mayer and Moreno, 2003 Segment explanations; teach component names first; remove irrelevant material Multimedia learning research, not an ADHD-specific prose trial
W3C heading guidance Descriptive headings with a logical hierarchy Semantic structure matters beyond visual appearance
W3C complex-image guidance Provide a short alternative and a fuller explanation when needed A visual alone cannot serve every reader

Mayer and Moreno review experiments on instructional multimedia and problem-solving transfer. Their segmentation discussion notes that the segmented group also had more study time. The authors call for further research separating segmentation from interactivity. Applying these findings to ordinary prose is an editorial inference. They support manageable explanations, without establishing a fixed paragraph count.

Defaults and limits

Use these as editing prompts. Do not score readability by counts alone.

Default Purpose When to adapt
Answer before explanation Make the useful point easy to find Preserve a requested narrative reveal or required template
Sentences under 20 words Reduce stacked clauses Keep a longer sentence when splitting would obscure its meaning
One to three sentences per paragraph Keep each block focused Preserve deliberate literary rhythm and necessary context
Review three consecutive prose paragraphs Notice a wall of explanation Keep short connected prose when another format would fragment it
Five list items or fewer Keep a group easy to scan Preserve a complete sequence or reference list; group by meaning

The numeric defaults are house rules. These sources do not establish them as universal thresholds. Neither a readability score nor a successful Skill load proves reader comprehension. Do not claim that most humans have ADHD or dyslexia. These sources do not establish that claim. Readers can need support without disclosing a diagnosis. Preferences and prior knowledge vary.

Choose a format by the reader's task

Reader needs to Use Keep accessible
Understand a connected argument Short prose under meaningful headings Keep logical connections explicit
Scan several independent points Bullets Use parallel wording and short items
Complete actions in order Numbered steps Separate actions; put conditions before commands
Compare options on the same criteria A small table Label columns; avoid wide or dense cells
Understand relationships or branches A diagram Include an equivalent text explanation
Learn a difficult concept A concrete example Mark invented examples as illustrative; preserve source facts

Never alternate formats merely to decorate a page. Every change should make finding or understanding information easier. Keep labels beside the content they explain. Do not force readers to remember distant definitions. Keep prerequisites, costs, risks, and destructive effects visible before the relevant action. Link or label optional background. Never hide information needed to choose or act safely.

If you control layout, use readable spacing and left-aligned text. Respect reader display preferences. Do not hard-code a special font or color as a universal remedy. For Markdown, use real headings, list syntax, blank lines, and labelled table columns. Avoid layout tables and emphasis that competes with the message.

Illustrative rewrite

This invented example demonstrates ordering and chunking. It is not a measured writing-quality result.

Before

To export your project, open Settings and select Export, although before doing so you should save your changes. The export includes saved changes only, and after it finishes you can download the archive. Large projects may take longer, and you can continue working while the export runs.

After

Export your project from Settings. The archive includes saved changes only.

  1. Save your changes.
  2. Open Settings and select Export.
  3. When the export finishes, download the archive.

Large projects may take longer. You can keep working while the export runs.

The rewrite keeps the prerequisite, scope, sequence, timing uncertainty, and permission to continue working. It moves the prerequisite before the action and separates the steps.

Final review

  • Can the reader find the answer from headings and opening lines?
  • Does each new term have enough context before its first use?
  • Can the reader act without remembering a condition from another section?
  • Does each list, table, or visual make the content easier to use?
  • Did the rewrite preserve facts, qualifiers, required steps, and the author's voice?

When available, inspect the rendered result at a narrow width and check its reading order. For consequential public content, reader feedback is stronger evidence than an editor's impression. Include people with relevant reading and attention needs when testing comprehension.

Source: SKILL.md on GitHub

No rule matched.

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

No third-party reports yet.

Signed by skilld at 4d33e4d. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 9 hours ago.

Activeupdated 12 hours ago

README badge

README badge for harlan-zw/brundlefly/im-not-a-fly