Agent skill

GitHub Commenting

by juspay in juspay/neurolink

How to post clean, rich, deduplicated GitHub PR review comments — suggestion blocks, multi-line anchors, markers, formatting rules.

MITAuto-check passedDevelopment

Install GitHub Commenting

skills CLI
$ npx skills add juspay/neurolink --skill github-commenting -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install juspay/neurolink github-commenting --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/juspay/neurolink.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.yama/skills/github-commenting .claude/skills/github-commenting && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
github-commenting
GitHub stars
143
Token cost
~698 tokens
SKILL.md length
378 words
Files
1
Skills in repo
3
Repo updated
First seen
Licence
MIT

At a glance

How to post clean, rich, deduplicated GitHub PR review comments — suggestion blocks, multi-line anchors, markers, formatting rules.

  • Works in 2 steps: List the existing review comments AND… → Every comment you post starts with an…
  • Tasks that involve Pull requests
  • SKILL.md covers Before posting anything, Inline comments, Suggestion blocks — a fix the… and Formatting for humans, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

GitHub Commenting is an agent skill from juspay/neurolink. How to post clean, rich, deduplicated GitHub PR review comments — suggestion blocks, multi-line anchors, markers, formatting rules. Load before posting or fixing any PR comment.

Its SKILL.md is about 700 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Development, covering Pull requests, MCP servers and Text to speech and voice. It works with GitHub, Model Context Protocol, OpenAI and Vercel AI SDK. The repository describes itself as: The pipe layer of an AI nervous system — one interface connecting provider neurons to your application, across three inference types: generate, stream, and a calibrated decide… The licence is MIT.

When your agent uses it

  • Tasks that involve Pull requests
  • Tasks that involve MCP servers
  • Tasks that involve Text to speech and voice

Example prompts

  • “/github-commenting”

Workflow steps

2 steps, taken from the first numbered list in SKILL.md.

  1. List the existing review comments AND issue comments on the pull request first.
  2. Every comment you post starts with an invisible marker line: <!-- yama: -->. If a marker for the same finding already exists, do NOT post…

What it can do on your machine

Read from SKILL.md and the folder at commit 171cc74. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

GitHub Commenting loads about 698 tokens when it runs. Until then it costs about 49 tokens; SKILL.md has 378 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~49
When it runs · the whole SKILL.md, loaded when a task matches
~698

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from juspay/neurolink at commit 171cc74, republished under its MIT licence (© juspay). 378 words, ~698 tokens.

Download SKILL.mdSave it as .claude/skills/github-commenting/SKILL.md (or your agent's skills folder).
name
github-commenting
description
How to post clean, rich, deduplicated GitHub PR review comments — suggestion blocks, multi-line anchors, markers, formatting rules. Load before posting or fixing any PR comment.

Clean GitHub PR commenting

Before posting anything

  1. List the existing review comments AND issue comments on the pull request first.
  2. Every comment you post starts with an invisible marker line: <!-- yama:<stable-finding-id> -->. If a marker for the same finding already exists, do NOT post it again — update that comment if it needs fixing, otherwise leave it alone.

Inline comments

  • Anchor to the exact file and line in the DIFF. A line that is not part of the diff cannot hold a comment — anchor to the nearest changed line and say so.
  • Multi-line ranges: start_line is the first line, line is the last; side / start_side are RIGHT for added lines and LEFT for deleted ones.
  • Tool shapes differ: some GitHub MCP servers post an inline comment in one call; the hosted server may require the pending-review lifecycle (create review → add comments → submit). If a pending review is opened it MUST be submitted — both or neither, never half.

Suggestion blocks — a fix the author applies in one click

Explain the issue in one or two sentences ABOVE the block, then:

markdown
```suggestion
the replacement for the entire anchored line range
```
  • The block's body replaces the WHOLE start_line..line range — include every line of the range, exactly indented.
  • If the replacement itself contains triple backticks (markdown files, code fences), use a four-backtick outer fence (````suggestion) so GitHub does not close the block early.
  • Prefer a suggestion block whenever you propose a concrete code fix - it is the fix the author applies in one click, and an inline comment about a code change should normally carry one. Fall back to prose only when the right code is genuinely uncertain.
Show full SKILL.md (115 more words)Show less

Formatting for humans

  • One finding per comment: severity (CRITICAL / MAJOR / MINOR), what breaks, why it matters here, and the fix.
  • Cite rulebook ids where they apply.
  • Evidence longer than ~10 lines goes in a collapsible section: <details><summary>evidence</summary>…</details>.
  • Prefer short headers, tables and task lists over walls of prose. No emoji noise.

The one summary comment

Post exactly ONE summary comment (an issue comment on the PR), marker <!-- yama:summary -->:

  • verdict at the top (APPROVE or NEEDS_WORK), one sentence of rationale,
  • a short table of findings — severity, file:line, one-line description,
  • what was checked and found clean, so silence is distinguishable from absence.

If a comment with that marker already exists, UPDATE it — never add a second summary.

© juspay, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .yama/skills/github-commenting of juspay/neurolink.

Open the folder on GitHubat commit 171cc74

Compare with similar skills

GitHub Commenting next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

GitHub Commenting compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
GitHub Commenting this skilljuspay/neurolink143—~698Automated safety check: PassMIT
Project Pull Requestswimmwatch/cloakbrowser-mcp161—~1kAutomated safety check: PassMIT
Chatgpt App Builderalpic-ai/skybridge2.1k—~1kAutomated safety check: PassMIT
Code Reviewnteract/semiotic2.7k—~1.5kAutomated safety check: PassApache-2.0
Open PRArcadeAI/arcade-mcp1k—~2.9kAutomated safety check: PassMIT
Skybridgealpic-ai/skybridge2.1k—~923Automated safety check: PassMIT

Similar skills

  • Project Pull Request

    swimmwatch/cloakbrowser-mcp

    Create, update, prepare, or review a cloakbrowser-mcp GitHub Pull Request only when the user explicitly requests PR work.

    161 GitHub stars~1k tokensUpdated 5 days ago
    DevelopmentAuto-check passed
  • Chatgpt App Builder

    alpic-ai/skybridge

    Guide developers through creating and updating ChatGPT plugins.

    2.1k GitHub stars~1k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed
  • Code Review

    nteract/semiotic

    Review Semiotic pull requests for behavioral bugs, regressions, contract drift, and missing evidence.

    2.7k GitHub stars~1.5k tokensUpdated today
    DevelopmentAuto-check passed
  • Open PR

    ArcadeAI/arcade-mcp

    Prepare arcade-mcp changes for review by verifying intended behavior, filling the repository PR template, and creating or updating the PR.

    1k GitHub stars~2.9k tokensUpdated today
    Agent WorkflowsAuto-check passed
  • Skybridge

    alpic-ai/skybridge

    Guide developers through creating and updating ChatGPT plugins and MCP Apps.

    2.1k GitHub stars~923 tokensUpdated yesterday
    Agent WorkflowsAuto-check passed
  • PR Review

    confluentinc/mcp-confluent

    Reviews pull requests for the Confluent MCP server. An agent skill from confluentinc/mcp-confluent.

    167 GitHub stars~4.6k tokensUpdated today
    DevelopmentAuto-check: notes

More from juspay/neurolink

  • Neurolink Guide

    juspay/neurolink

    Guide for using the NeuroLink SDK and CLI. An agent skill from juspay/neurolink.

    143 GitHub stars~1.4k tokensUpdated today
    Auto-check passed
  • Repo Conventions

    juspay/neurolink

    NeuroLink's review standards — the critical rules to enforce, what NOT to comment on, the security bar, hot paths.

    143 GitHub stars~1.3k tokensUpdated today
    Auto-check passed

Questions about GitHub Commenting

What does GitHub Commenting do?

How to post clean, rich, deduplicated GitHub PR review comments — suggestion blocks, multi-line anchors, markers, formatting rules. GitHub Commenting is an agent skill from juspay/neurolink. How to post clean, rich, deduplicated GitHub PR review comments — suggestion blocks, multi-line anchors, markers, formatting rules.

When should I use GitHub Commenting?

GitHub Commenting fits situations like: tasks that involve Pull requests; tasks that involve MCP servers; tasks that involve Text to speech and voice.

How do I install GitHub Commenting in Claude Code?

Run `npx skills add juspay/neurolink --skill github-commenting -a claude-code`. Or copy the skill folder (.yama/skills/github-commenting in juspay/neurolink) into .claude/skills/github-commenting in your project. Claude Code loads it when a task matches its description.

How do I install GitHub Commenting in Codex?

Run `npx skills add juspay/neurolink --skill github-commenting -a codex`. Or copy the skill folder (.yama/skills/github-commenting in juspay/neurolink) into .agents/skills/github-commenting in your project. Codex loads it when a task matches its description.

Can I use GitHub Commenting in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add juspay/neurolink --skill github-commenting -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/github-commenting, .gemini/skills/github-commenting, .github/skills/github-commenting and .opencode/skills/github-commenting in your project.

What does GitHub Commenting need to run?

SKILL.md names no scripts, command-line tools or credentials: GitHub Commenting is instructions for the agent only.

Does GitHub Commenting access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is GitHub Commenting safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does GitHub Commenting use?

GitHub Commenting is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does GitHub Commenting use?

About 698 tokens (SKILL.md is roughly 2.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to GitHub Commenting?

Skills that share tags, products or a category with GitHub Commenting: Project Pull Request (swimmwatch/cloakbrowser-mcp, 161 stars), Chatgpt App Builder (alpic-ai/skybridge, 2.1k stars), Code Review (nteract/semiotic, 2.7k stars) and Open PR (ArcadeAI/arcade-mcp, 1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains GitHub Commenting?

juspay (a GitHub organization) maintains it in juspay/neurolink, which has 143 GitHub stars. The repository holds 3 skills in this directory. The repository was last updated on October 7, 2026.

Source: juspay/neurolink on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.