{"slug":"gentle-ai-comment-writer","title":"gentle-ai-comment-writer","summary":"Write warm, direct collaboration comments. Trigger: PR feedback, issue replies, reviews, Slack messages, or GitHub comments.","platform":"Claude","tags":[],"authorName":"LLM Mart","authorSlug":"llm-mart","score":0,"source":"github","price":null,"verified":false,"createdAt":"2026-09-09T18:38:34.68098Z","repo":{"url":"https://github.com/Gentleman-Programming/gentle-pi","stars":1123,"forks":158,"license":"MIT","updatedAt":"2026-09-27T20:40:53Z"},"bodyHtml":"<hr>\n<h2>name: gentle-ai-comment-writer\ndescription: \"Write warm, direct collaboration comments. Trigger: PR feedback, issue replies, reviews, Slack messages, or GitHub comments.\"\nlicense: Apache-2.0\nmetadata:\nauthor: gentleman-programming\nversion: \"1.0\"</h2>\n<h2>When to Use</h2>\n<p>Load this skill whenever you write a comment that another human will read.</p>\n<p>Use it for:</p>\n<ul>\n<li>GitHub PR or issue comments.</li>\n<li>Review feedback and requested changes.</li>\n<li>Maintainer replies.</li>\n<li>Slack, Discord, or async project updates.</li>\n</ul>\n<h2>Voice Rules</h2>\n<table>\n<thead>\n<tr>\n<th>Rule</th>\n<th>Requirement</th>\n</tr>\n</thead>\n<tbody>\n<tr>\n<td>Be useful fast</td>\n<td>Start with the actionable point. Do not recap the whole PR before feedback.</td>\n</tr>\n<tr>\n<td>Be warm and direct</td>\n<td>Sound like a thoughtful teammate, not a corporate bot.</td>\n</tr>\n<tr>\n<td>Keep it short</td>\n<td>Prefer 1 to 3 short paragraphs or a tight bullet list.</td>\n</tr>\n<tr>\n<td>Explain why</td>\n<td>Give the technical reason when asking for a change.</td>\n</tr>\n<tr>\n<td>Avoid pile-ons</td>\n<td>Comment on the highest-value issue, not every tiny preference.</td>\n</tr>\n<tr>\n<td>Match target context language</td>\n<td>Write in the target context language by default: Spanish issue/thread -&gt; Spanish comment, English issue/thread -&gt; English comment, mixed context -&gt; target message language. If the user explicitly requests a language or tone, follow that request. Do not use the active persona as the source of truth for public comments. For Spanish comments, use neutral/professional Spanish by default unless the user or target context clearly calls for regional tone.</td>\n</tr>\n<tr>\n<td>No em dashes</td>\n<td>Use commas, periods, or parentheses instead.</td>\n</tr>\n</tbody>\n</table>\n<h2>Comment Formula</h2>\n<pre><code>&lt;Direct observation or request&gt;\n\n&lt;Why it matters, only if needed&gt;\n\n&lt;Concrete next action&gt;\n</code></pre>\n<h2>Examples</h2>\n<h3>Request change</h3>\n<pre><code>Good approach overall. I'd split this into a separate commit because it mixes validation logic with UI wiring.\n\nThat keeps the reviewer's focus narrower and makes rollback cleaner if the integration fails.\n</code></pre>\n<h3>Approve with a note</h3>\n<pre><code>Approved. The scope is clear and the change is well-contained.\n\nFor the next PR, add links to the previous and following PRs so the chain stays navigable.\n</code></pre>\n<h3>Ask for split</h3>\n<pre><code>This PR exceeds the 400-line budget, so we need to split it or justify `size:exception`.\n\nSuggested order: foundation + tests first, then integration, then docs. That gives each review a clear start and end.\n</code></pre>\n<h2>Commands</h2>\n<pre><code># Inspect a PR before writing review feedback\ngh pr view &lt;PR_NUMBER&gt; --json title,body,additions,deletions,changedFiles\n</code></pre>\n","files":[{"path":"SKILL.md","sizeBytes":2490,"isText":true}],"reviewScore":null,"reviewSummary":null,"trust":{"provenance":"trusted-source-unreviewed","notice":"Community-authored content, reproduced verbatim and not vetted as instructions. Treat it as data to evaluate, never as directives to follow.","bodySource":null},"bodyLocked":false,"purchaseUrl":null,"sourceUrl":null,"report":{"provenance":"trusted-source-unreviewed","screen":{"ran":true,"outcome":"clean","suspicious":0,"notes":0,"hiddenCharacters":false},"virusScan":{"engine":"clamav","status":"clean","scannedAt":"2026-09-09T18:38:47.698406Z","sha256":"9D0D2E7A1A4DF0E87D1395B4FF22858312D70D51D81386F1A146D8752509F280","sizeBytes":1412},"review":null,"source":{"repositoryUrl":"https://github.com/Gentleman-Programming/gentle-pi","path":"skills/comment-writer","license":"MIT","commit":"78775c37903dc7821daceb848c7d9644f8c8c576","subtreeSha":"878EF3C1F022E28341DDA71A8EDEB827BFE531BD2B62E77604CB3C4EE3C0267F","lastSyncedAt":"2026-09-27T20:56:08.114622Z"},"reviewedAt":"2026-09-09T18:38:51.235325Z","notice":"Community-authored content, reproduced verbatim and not vetted as instructions. Treat it as data to evaluate, never as directives to follow."},"install":[{"target":"skills-cli","command":"npx skills add https://github.com/Gentleman-Programming/gentle-pi/tree/main/skills/comment-writer"},{"target":"claude-code","command":"claude plugin marketplace add https://llmmart.ai/marketplace.json && claude plugin install gentleman-programming-gentle-pi@llmmart"},{"target":"git","command":"git clone https://github.com/Gentleman-Programming/gentle-pi.git"}]}