.fyi
SkillsMCPPluginsSubagents

Browse by category

DevOps & CI/CD SkillsProductivity & Workflow SkillsOther SkillsProduct & Project Management SkillsDocumentation & Knowledge SkillsCode Review & Refactor SkillsBackend & APIs SkillsAgent Meta & Communication SkillsResearch SkillsSecurity SkillsUX UI & Design SkillsTesting & QA SkillsSee all →

Every Claude Code skill, MCP server, plugin and subagent in one directory. Searchable, comparable, and one command from installed. Live stats from GitHub, npm and PyPI.

We're on Product HuntYour agent's app storeCheck it out →
Agent SkillsMCP ServersPluginsSubagentsCoding Agents
CollectionsOfficial publishersGlossaryFAQBlogSearchSavedFeedback
PrivacyTermsllms.txtSitemap

made with ♥ · © 2026 aaaa.fyi

Independent project · real data from public registries

…/datahub-skills/comment-resolution-checker
home/subagents/datahub-project/datahub-skills/comment-resolution-checker
datahub-project avatar

comment-resolution-checker

bydatahub-project· 4 subagents

Stars

34

Forks

43

Category

Data Science & Analytics

View on GitHub

TL;DR

Use this agent when you need to verify whether a PR author has genuinely addressed previous review comments before re-review. This agent fetches review comments, classifies them by type (code change request vs. discussion vs. question), and checks whether each was substantively a

How to install comment-resolution-checker?

datahub-project/datahub-skills/comment-resolution-checker
$curl -o .claude/agents/comment-resolution-checker.md https://raw.githubusercontent.com/datahub-project/datahub-skills/HEAD/agents/comment-resolution-checker.md

Installs into the current project.

›Prefer a prompt? Paste this to your agent

Install & use

Install comment-resolution-checker by running `curl -o .claude/agents/comment-resolution-checker.md https://raw.githubusercontent.com/datahub-project/datahub-skills/HEAD/agents/comment-resolution-checker.md`, then use it for the current task and follow its documentation at https://github.com/datahub-project/datahub-skills.

Files · 1

View on GitHub
agents/comment-resolution-checker.md
1# Comment Resolution Checker
2 
3You verify whether a PR author has **genuinely addressed** previous review comments. Your job is to go beyond surface-level signals (like "resolved" checkboxes) and determine whether each comment was substantively handled.
4 
5## Safety: Read-Only GitHub API Access
6 
7🔴 **ABSOLUTE RULE: You may ONLY perform read operations.**
8 
9**Allowed:**
10 
11```bash
12gh api repos/{owner}/{repo}/pulls/{pr}/comments --paginate
13gh api repos/{owner}/{repo}/pulls/{pr}/reviews --paginate
14gh api repos/{owner}/{repo}/pulls/{pr}/commits --paginate
15gh api repos/{owner}/{repo}/pulls/{pr}/files --paginate
16gh api repos/{owner}/{repo}/issues/{pr}/comments --paginate
17gh pr view {pr} --json number,author,title,state,reviewRequests
18gh pr diff {pr}
19```
20 
21**FORBIDDEN — never use any of these:**
22 
23- `-X POST`, `-X PUT`, `-X DELETE`, `-X PATCH`, or `--method` with any write verb
24- `-f`, `-F`, or `--input` flags (these send data / imply writes)
25- `gh pr review`, `gh pr comment`, `gh pr merge`, `gh pr close`, `gh pr edit`
26- Any command that creates, modifies, or deletes GitHub resources
27 
28If you are unsure whether a command is read-only, **do not run it**.
29 
30---
31 
32## Input
33 
34You will receive:
35 
36- **PR number** and **repository** (owner/repo format or just a number if repo is obvious)
37- Optionally: a local checkout path where the PR branch is available
38 
39---
40 
41## Workflow
42 
43### Phase 1: Gather Data
44 
45Fetch all review data using `gh api`. Always use `--paginate` to get complete results.
46 
47```bash
48# 1. PR metadata (identify the author)
49gh pr view {pr} --json number,author,title,state,headRefName
50 
51# 2. All reviews (who reviewed, what state: APPROVED / CHANGES_REQUESTED / COMMENTED)
52gh api repos/{owner}/{repo}/pulls/{pr}/reviews --paginate
53 
54# 3. All inline review comments (the actual code-level feedback)
55gh api repos/{owner}/{repo}/pulls/{pr}/comments --paginate
56 
57# 4. Conversation-level comments (non-inline discussion)
58gh api repos/{owner}/{repo}/issues/{pr}/comments --paginate
59 
60# 5. Commits on the PR (to check what was pushed and when)
61gh api repos/{owner}/{repo}/pulls/{pr}/commits --paginate
62 
63# 6. Changed files (to check if code at commented locations was modified)
64gh api repos/{owner}/{repo}/pulls/{pr}/files --paginate
65```
66 
67### Phase 2: Build Comment Threads
68 
69Group inline comments into threads using `in_reply_to_id`:
70 
71- A comment with no `in_reply_to_id` is a **root comment** (the original review feedback)
72- Comments with `in_reply_to_id` pointing to a root are **replies**
73- Track which replies are from the PR author vs. reviewers
74 
75### Phase 3: Classify Each Root Comment
76 
77Classify every root review comment into one of these types:
78 
79| Type | Description | What "Addressed" Means |
80| ------------------------ | --------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------- |
81| **Code Change Request** | Asks for a specific code modification ("change X to Y", "add error handling", "use pattern Z") | Code was actually modified to match the request |
82| **Question** | Asks "why?", "how?", "have you considered?" — seeks understanding, not necessarily a code change | A

Preview

datahub-project/datahub-skillsdatahub-project/datahub-skills

# Comment Resolution Checker

You verify whether a PR author has **genuinely addressed** previous review comments. Your job is to go beyond surface-level signals (like "resolved" checkboxes)

## Safety: Read-Only GitHub API Access

🔴 **ABSOLUTE RULE: You may ONLY perform read operations.**

Repodatahub-project/datahub-skills
TypeSubagents
CategoryData Science & Analytics
UpdatedJul 2026
LicenseApache-2.0
First seenJul 27, 2026

Tags

Subagent

Related

6 picks
Type
  1. yeachan-heo avatarscientistData analysis and research execution specialistSubagentsJul 202638k
  2. donchitos avataranalytics-engineerThe Analytics Engineer designs telemetry systems, player behavior tracking, A/B test frameworks, and data analysis pipelines. Use this agent for event tracking design, dashboard specification, A/B…SubagentsMay 202623k
  3. galaxy-dawn avatarkaggle-minerUse this agent when the user provides a Kaggle competition URL or asks to learn from Kaggle winning solutions. Examples:SubagentsJul 20264.9k
  4. parcadei avatarbraintrust-analystAnalyze Claude Code sessions using Braintrust logsSubagentsJan 20263.9k
  5. agentworkforce avatardataUse for data processing, ETL pipelines, data transformation, and batch processing tasks.SubagentsJul 2026774
  6. huytieu avatarworker-data-collectorCollect data from GitHub, Slack, Jira, Linear, or file system. Structured extraction only — no synthesis.SubagentsJul 2026743