unresolved-comments
Fetch and display only unresolved comments from a GitHub pull request
Skill by bonzofenix
Chalk Labs
Need help deploying unresolved-comments?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/bonzofenix-unresolved-comments
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/unresolved-comments
What's inside
- Skill name
unresolved-comments- Description
- Fetch and display only unresolved comments from a GitHub pull request
- License
- MIT
- Instructions
- 117 lines in SKILL.md · view on GitHub
Agent Skills spec issues
- allowed-tools: must be a space-separated string
Files (1)
- SKILL.md
SKILL.md (first lines)
Fetch and display ONLY unresolved comments from a GitHub pull request, then assist with addressing them.
## Steps
1. Get PR number and repository: `gh pr view --json number,headRepository`
2. Fetch review threads using GitHub's GraphQL API:
```bash
gh api graphql -f query='
{
repository(owner: "OWNER", name: "REPO") {
pullRequest(number: NUMBER) {
reviewThreads(first: 100) {
nodes {
isResolved
isOutdated
comments(first: 50) {
nodes {
author { login }
body
path
line
originalLine
diffHunk
createdAt
}
}
}
}
}
}
}'
```
Replace OWNER, REPO, and NUMBER with actual values.
3. Filter threads where `isResolved: false`
4. Parse and format unresolved comments
5. Display formatted output
## Output Format
```markdown
## Unresolved Comments
- @author file.ts#line:
```diff
[diff_hunk]
```
> comment text
[replies indented]
```
If no unresolved comments exist, return "No unresolved comments found."
## Comment Classification
Before presenting a comment to the user, classify it:
- **Style/preference** — formatting, naming, if/return vs match, cosmetic structure. Reviewer has a preference, no correctness impact.
- **Correctness/logic** — the suggestion fixes a bug, closes a gap, or prevents future breakage.
- **Architectural** — changes where responsibility lives, call signatures, abstraction level.
## Comment Resolution Workflow
For each unresolved comment:
1. **Analyze the comment**: Read the relevant code context and classify it (style, correctness, or architectural).
2. **Present to user — lead with disposition, not reasoning**:
- **Style/preference**: Skip the tradeoff essay. Just ask apply or skip with a one-liner max.
> "Style preference — apply it or skip?"
- **Correctness/architectural**: Brief assessment (2-3 sentences max). State your recommendation clearly first, reasoning second.
> "Recommend applying — [one-line reason]. [Optional: one-line tradeoff only if genuinely non-obvious]."
Never defend the existing approach AND propose applying the change in the same message — pick one.
3. **Let user decide**: Wait for user input.
4. **Apply + reply atomically**: Do both in one step — never explain in a reply and commit separately.
- Make the code change
- Commit: `"fix: address review comment - [brief description]"`
- Push, so the commit link resolves on GitHub
- Post reply: `"Done in [commit_hash](commit permalink)."` — no re-explanation of what was already discussed
5. **If skipping**:
- One sentence max for the reply. State the reason, not the history.
- Format: `"Keeping this — [reason]."`
## Code References in Replies
Replies stay within the length limits above. When a reply references code (usually a skip reason), link it with a GitHub permalink instead of describing it:
- Link to the changed code: `[methodName](https://github.com/OWNER/REPO/blob/BRANCH/path/file.go#L42)`
- Link to line ranges: `#L10-L25` for multi-line references
- Link to relevant test cases when tests were added
- Link to third-party library source when explaining library behavior
- Build links using the PR's head branch: `https://github.com/OWNER/REPO/blob/BRANCH/path`
Example skip reply:
```
Keeping this — [`doAuthRequest`](https://github.com/org/repo/blob/branch/cf/wrapper.go#L174) already sends the Bearer token.
```
This makes it easy for reviewers to verify claims without searching the codebase.
## Important Notes
- Only show threads where `isResolved: false`
- PR-level comments (not in review threads) won't appear
- Preserve comment threading and nesting
- Show file and line number context
- Note outdated comments using `isOutdated` field
- Use jq to parse GraphQL JSON responsesFrom bonzofenix/skills, MIT.
More from bonzofenix/skills
- 0.566score
whatsapp-to-db
bonzofenix
Turn a WhatsApp chat export (.zip, unzipped folder, or bare chat .txt) into a queryable SQLite database — every message, every voice note transcribed locally…
SkillAFreshness: AClaude Code +9 - 0.565score
yolo
bonzofenix
Ship the current branch end-to-end without stopping to ask — commit staged/unstaged work, push, open a PR, watch CI, merge once green, and where merging…
SkillAFreshness: AClaude Code +9 - 0.560score
claude-new
bonzofenix
Start a new background Claude Code session in a project under ~/workspace, so it shows up in the agent view.
SkillAFreshness: AClaude Code +9 - 0.557score
analyze-ci
bonzofenix
Analyze CI checks for current branch's PR - polls pending checks until complete, diagnoses failures, auto-fixes straightforward issues, and suggests fixes for…
SkillAFreshness: AClaude Code +9 - 0.554score
smart-pr
bonzofenix
Generate or update PR title and description based on branch diffs
SkillAFreshness: AClaude Code +9 - 0.554score
last-screenshot
bonzofenix
References the most recent screenshot from the user's Desktop for analysis
SkillAFreshness: AClaude Code +9 - 0.554score
sonarcloud-issues
bonzofenix
Fetch and display SonarCloud/SonarQube analysis issues for a GitHub PR
SkillAFreshness: AClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Sep 25, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/bonzofenix/skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from bonzofenix
- 0.566score
whatsapp-to-db
bonzofenix
Turn a WhatsApp chat export (.zip, unzipped folder, or bare chat .txt) into a queryable SQLite database — every message, every voice note transcribed locally…
SkillAFreshness: AClaude Code +9 - 0.565score
yolo
bonzofenix
Ship the current branch end-to-end without stopping to ask — commit staged/unstaged work, push, open a PR, watch CI, merge once green, and where merging…
SkillAFreshness: AClaude Code +9 - 0.560score
claude-new
bonzofenix
Start a new background Claude Code session in a project under ~/workspace, so it shows up in the agent view.
SkillAFreshness: AClaude Code +9 - 0.557score
analyze-ci
bonzofenix
Analyze CI checks for current branch's PR - polls pending checks until complete, diagnoses failures, auto-fixes straightforward issues, and suggests fixes for…
SkillAFreshness: AClaude Code +9 - 0.554score
smart-pr
bonzofenix
Generate or update PR title and description based on branch diffs
SkillAFreshness: AClaude Code +9 - 0.554score
last-screenshot
bonzofenix
References the most recent screenshot from the user's Desktop for analysis
SkillAFreshness: AClaude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get unresolved-comments running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
unresolved-comments skill. Agent Mart. https://agentmart.dev/skills/bonzofenix-unresolved-comments (last updated 2026-10-24)