link-text-review
Enhances Markdown links by replacing vague phrases like 'click here' with descriptive, task-focused anchor text.
Install
mkdir -p .claude/skills/link-text-review && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/10231" && unzip -o skill.zip -d .claude/skills/link-text-review && rm skill.zipInstalls to .claude/skills/link-text-review
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Review and improve accessible Markdown link text in Arm Learning Paths and install guides. Use when asked to find vague links, fix link text such as here or click here, verify internal links, improve screen-reader clarity, or make links descriptive and task-focused.Key capabilities
- →Review link text
- →Improve accessibility
- →Verify internal links
- →Make links descriptive
How it works
Analyzes anchor text and suggests descriptive rewrites for better screen-reader clarity.
Inputs & outputs
When to use link-text-review
- →Fix vague 'click here' links
- →Improve screen-reader accessibility
- →Standardize link formatting in docs
About this skill
Link text review
Use this skill to review or improve Markdown link text so links are descriptive, accessible, and useful out of context.
This skill focuses on anchor text and link clarity. For tables, notices, tab panes, and other structural Markdown components, use .github/skills/markdown-component-edit/SKILL.md.
Prerequisites
- Work from the repository root.
- Read
AGENTS.mdonly if you need repository routing context. - Read
.github/skills/writing-style-review/SKILL.mdonly when changing prose around links. - For Learning Paths, read
.github/skills/learning-path-structure-review/SKILL.mdwhen link placement orfurther_readingis involved.
Workflow
- Identify the target file, directory, section, or selected text. If you've previously read the page, use context and don't re-read it unless there's a change since the last read.
- Read surrounding context before suggesting any changes.
- After understanding the context of the URL, suggest concise and natural rewrites to the anchor text based on
Quality rules. - After the user accepts suggestions, make changes, then re-open or search changed lines to verify the Markdown link syntax is valid.
- After you make changes, report changed links and any links not verified.
Quality rules
- Link text should make sense without nearby words when possible.
- Prefer destination-specific anchors such as
Docker install guide,Arm Developer resources, orGoogle Cloud firewall rules. - Avoid anchors that only describe the mechanic, such as
here,click here,this page,read more,link, orwebsite, as well as bare URLs or repeated generic text. - Avoid overlong anchors that wrap a whole sentence.
- Don't change product names, tool names, URLs, or technical meaning to satisfy prose preferences.
- Don't add speculative links. Verify internal targets or state when verification was not possible. Preserve the URL unless it's broken or the user asks for a change.
Examples
Use these examples for both link format and link text guidance.
Poor:
See [here](/install-guides/docker/) for setup.
Better:
For setup instructions, see the [Docker install guide](/install-guides/docker/).
Poor:
A list of all AWS instance types can be [viewed here](https://aws.amazon.com/ec2/instance-types/).
Better:
For a complete list, see [Amazon EC2 instance types](https://aws.amazon.com/ec2/instance-types/).
When not to use it
- →Structural Markdown edits
Limitations
- →Requires manual verification of internal targets
How it compares
Focuses on accessibility and context-aware link descriptions rather than just fixing broken URLs.
Compared to similar skills
link-text-review side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| link-text-review (this skill) | 0 | 1mo | No flags | Beginner |
| ml-paper-writing | 48 | 6mo | Review | Advanced |
| docs-review | 10 | 7mo | No flags | Beginner |
| claude-md-improver | 21 | 6mo | Review | Beginner |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by ArmDeveloperEcosystem
View all by ArmDeveloperEcosystem →You might also like
ml-paper-writing
davila7
Write publication-ready ML/AI papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM. Use when drafting papers from research repos, structuring arguments, verifying citations, or preparing camera-ready submissions. Includes LaTeX templates, reviewer guidelines, and citation verification workflows.
docs-review
metabase
Review documentation changes for compliance with the Metabase writing style guide. Use when reviewing pull requests, files, or diffs containing documentation markdown files.
claude-md-improver
anthropics
Audit and improve CLAUDE.md files in repositories. Use when user asks to check, audit, update, improve, or fix CLAUDE.md files. Scans for all CLAUDE.md files, evaluates quality against templates, outputs quality report, then makes targeted updates. Also use when the user mentions "CLAUDE.md maintenance" or "project memory optimization".
write-docs
tldraw
Writing SDK documentation for tldraw. Use when creating new documentation articles, updating existing docs, or when documentation writing guidance is needed. Applies to docs in apps/docs/content/.
update-docs
vercel
This skill should be used when the user asks to "update documentation for my changes", "check docs for this PR", "what docs need updating", "sync docs with code", "scaffold docs for this feature", "document this feature", "review docs completeness", "add docs for this change", "what documentation is affected", "docs impact", or mentions "docs/", "docs/01-app", "docs/02-pages", "MDX", "documentation update", "API reference", ".mdx files". Provides guided workflow for updating Next.js documentation based on code changes.
wiki-architect
microsoft
Analyzes code repositories and generates hierarchical documentation structures with onboarding guides. Use when the user wants to create a wiki, generate documentation, map a codebase structure, or understand a project's architecture at a high level.