
Comment Mode
- 127 installs
- 31 repo stars
- Updated August 2, 2026
- shipshitdev/library
Review diffs by leaving precise inline comments on risks, style, tests, and regressions so authors fix issues before merge without rewriting entire patches.
About
Comment-mode enables focused code review behavior where the agent annotates pull requests and patches with targeted inline feedback. It is suited to SaaS, API, and CLI repos where reviewers must call out defects, missing tests, and maintainability concerns before changes ship.
- Leaves line-level review comments on diffs
- Flags security, performance, and test gaps
- Keeps feedback constructive and merge-oriented
- Separates nitpicks from blocking issues clearly
Comment Mode by the numbers
- 127 all-time installs (skills.sh)
- +3 installs in the week ending Jul 27, 2026 (Skillselion tracking)
- Ranked #403 of 1,352 Code Review & Quality skills by installs in the Skillselion catalog
- Data as of Aug 3, 2026 (Skillselion catalog sync)
npx skills add https://github.com/shipshitdev/library --skill comment-modeAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 127 |
|---|---|
| repo stars | ★ 31 |
| Last updated | August 2, 2026 |
| Repository | shipshitdev/library ↗ |
What it does
Review diffs by leaving precise inline comments on risks, style, tests, and regressions so authors fix issues before merge without rewriting entire patches.
Files
Comment Mode
Generate highlighted HTML with click-to-reveal comments for granular feedback on text. Alternative to rewrites—user keeps their voice, reviews feedback incrementally.
Contract
Inputs:
- The draft text to comment on (pasted inline or as a file path)
- Optional lens: editor feedback, POV simulation (e.g. "as brian would react"), or focused angle (e.g. "word choice only")
Outputs:
- An HTML file at
_private/views/{name}-comments-temp.htmlwith highlighted spans and click-to-reveal comment overlays
Creates/Modifies:
- Writes
_private/views/{name}-comments-temp.html
External Side Effects:
- Runs
open _private/views/{name}-comments-temp.htmlto launch the file in the default browser
Confirmation Required:
- None — the file is a temp view artifact in
_private/and does not modify source files
Delegates To:
- None.
When to Use
- User says: "comment on this", "leave comments on", "give feedback on"
- User pastes text and asks for feedback/critique
- User wants targeted feedback without a full rewrite
Clarify Before Commenting
Use AskUserQuestion to clarify scope when the request is ambiguous. Avoid over-commenting (overwhelming) or under-commenting (missing the point).
Clarify when:
- No lens specified → ask what angle they want
- Long document → ask if they want full coverage or just key sections
- Unclear audience → ask who the recipient is (affects POV comments)
Skip clarification when:
- Lens is explicit ("comment on word choice only")
- Document is short (<500 words)
- Context is obvious from conversation
Example clarification:
User: "comment on this"
[long doc, no lens specified]
→ Use AskUserQuestion:
"What should I focus on?"
Options:
- "Editor feedback (structure, clarity, word choice)"
- "Recipient POV (how [person] would react)"
- "Specific angle (tell me what)"Lenses
| Lens | Color | Comment style |
|---|---|---|
| Editor | Yellow (#fff3cd) | observations, suggestions: "weak opener", "add proof here" |
| POV (as person) | Blue (#e3f2fd) | reactions from that person's perspective: "i know this already", "legal would freak out" |
| Focused | Yellow | specific angle only: "word choice", "tone", "weak arguments" |
Comment Style
- Always lowercase
- Short (5-15 words)
- Smart about type: observations when noting, suggestions when alternatives help, reactions when simulating POV
- Only comment where there's something worth saying—sparse beats exhaustive
Output Rules
DO:
- Write to
_private/views/{name}-comments-temp.html - Open with
open _private/views/{name}-comments-temp.html - Use highlight colors matching the lens
- Keep comments sparse and high-signal
DO NOT:
- Comment on everything—only where there's an obvious edit or insight
- Over-explain in comments—keep them punchy
- Mix lenses in one output—pick one and stick to it
Template
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="UTF-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>{title}</title>
<style>
* { box-sizing: border-box; }
body {
font-family: -apple-system, BlinkMacSystemFont, 'Segoe UI', Roboto, sans-serif;
max-width: 700px;
margin: 0 auto;
padding: 40px 20px;
line-height: 1.7;
color: #1a1a1a;
background: #fafafa;
}
h1, h2, h3 { margin-top: 2em; font-weight: 600; }
h1 { font-size: 1.4em; }
h2 { font-size: 1.2em; color: #333; }
p { margin: 1em 0; }
.highlight {
background: {highlight-bg}; /* #fff3cd yellow for editor, #e3f2fd blue for POV */
padding: 1px 4px;
border-radius: 3px;
cursor: pointer;
border-bottom: 2px solid {highlight-border}; /* #ffc107 for editor, #2196f3 for POV */
transition: background 0.15s;
}
.highlight:hover, .highlight.active {
background: {highlight-hover}; /* #ffe69c for editor, #bbdefb for POV */
}
.comment {
display: none;
background: {comment-bg}; /* #1a1a1a for editor, #0052cc for POV */
color: #fff;
padding: 8px 12px;
border-radius: 6px;
font-size: 0.85em;
margin: 8px 0;
line-height: 1.5;
}
.comment.show { display: block; }
.section-break {
border: none;
border-top: 1px solid #ddd;
margin: 2em 0;
}
.legend {
position: fixed;
bottom: 20px;
right: 20px;
background: #fff;
padding: 12px 16px;
border-radius: 8px;
box-shadow: 0 2px 12px rgba(0,0,0,0.1);
font-size: 0.8em;
color: #666;
}
</style>
</head>
<body>
{content with <span class="highlight" data-comment="comment text">highlighted phrase</span>}
<div class="legend">{count} comments · click highlights to reveal</div>
<script>
document.querySelectorAll('.highlight').forEach(el => {
const commentText = el.getAttribute('data-comment');
const commentDiv = document.createElement('div');
commentDiv.className = 'comment';
commentDiv.textContent = commentText;
el.insertAdjacentElement('afterend', commentDiv);
el.addEventListener('click', () => {
const wasActive = el.classList.contains('active');
document.querySelectorAll('.highlight').forEach(h => h.classList.remove('active'));
document.querySelectorAll('.comment').forEach(c => c.classList.remove('show'));
if (!wasActive) {
el.classList.add('active');
commentDiv.classList.add('show');
}
});
});
</script>
</body>
</html>Color Reference
Editor lens (yellow):
.highlight { background: #fff3cd; border-bottom: 2px solid #ffc107; }
.highlight:hover, .highlight.active { background: #ffe69c; }
.comment { background: #1a1a1a; }POV lens (blue):
.highlight { background: #e3f2fd; border-bottom: 2px solid #2196f3; }
.highlight:hover, .highlight.active { background: #bbdefb; }
.comment { background: #0052cc; }Workflow
1. User pastes text + asks for comments 2. If ambiguous: Use AskUserQuestion to clarify lens/scope 3. Read text, identify key phrases worth commenting on (sparse, high-signal) 4. Generate HTML with highlights and data-comment attributes 5. Write to _private/views/{name}-comments-temp.html 6. Run open _private/views/{name}-comments-temp.html
Examples
Editor lens:
User: "comment on this, focus on word choice"
→ Yellow highlights, suggestions like "vague, try 'specifically'" or "jargon, simplify"POV lens:
User: "comment on this as brian would react"
→ Blue highlights, reactions like "i already know this" or "legal would push back here"Focused lens:
User: "leave comments on this, only flag weak arguments"
→ Yellow highlights on weak claims, comments like "needs evidence" or "assumes too much"Sparse/sharp lens:
User: "comment only where there's an obvious fix"
→ Minimal highlights, only typos, missing words, or clear improvements{
"name": "comment-mode",
"version": "1.0.0",
"description": "Granular feedback on drafts without rewriting. Generates highlighted HTML with click-to-reveal inlin",
"author": {
"name": "Ship Shit Dev",
"email": "hello@shipshit.dev",
"url": "https://shipshit.dev"
},
"license": "MIT",
"skills": "."
}