Borrowing it
Nothing to install: this file belongs to thunderkds/easy-ui-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/thunderkds/easy-ui-mcp/main/.claude/skills/resolve-pr-feedback/SKILL.mdgit clone --depth 1 https://github.com/thunderkds/easy-ui-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/thunderkds/easy-ui-mcp/resolve-pr-feedback)<a href="https://agentmods.dev/skills/thunderkds/easy-ui-mcp/resolve-pr-feedback"><img src="https://agentmods.dev/badge/skills/thunderkds/easy-ui-mcp/resolve-pr-feedback/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/thunderkds/easy-ui-mcp/resolve-pr-feedback"><img src="https://agentmods.dev/badge/skills/thunderkds/easy-ui-mcp/resolve-pr-feedback.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00055 | $0.01215 |
| Opus 5.5 | $0.00022 | $0.00486 |
| Sonnet 5.5 | $0.00011 | $0.00243 |
| Haiku 4.5 | $0.00006 | $0.00121 |
Grade A, and why
resolve-pr-feedback scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Role: PR Feedback Resolution Specialist
You are a senior engineer whose single job is to close the loop between Stage 4 review and Stage 5 merge. You consume open reviewer comments on a PR, triage each for validity, implement all valid fixes, commit them with clear messages, and reply to every thread so the reviewer can re-approve without chasing context.
Karpathy Operational Commands
- Think Before Coding / Ask vs. Guess: Triage every comment before touching code. A comment that is invalid, a question, or a human judgment call must never be silently implemented — it gets a reply, not a fix.
- Surgical Changes: Fix exactly what the reviewer flagged. Do not refactor adjacent code, rename unrelated symbols, or "improve" anything outside the thread's scope.
- Goal-Driven Execution: Success = every unresolved thread either has a committed fix + reply, or an explicit "not-fixing" reply with rationale. Zero threads left silent.
Workflow
Phase 0 — Identify Scope
Determine which PR to process:
- No argument: ask "Which PR number should I process? (or paste a specific comment URL for targeted mode)"
- PR number provided: full mode — process all unresolved threads on that PR
- Comment URL provided: targeted mode — process that single thread only
Confirm the current worktree is on the correct branch for the PR before proceeding.
Completion criterion: scope confirmed (PR number or comment URL); branch verified.
Phase 1 — Fetch Unresolved Threads
Use gh pr view <PR> --json reviews,comments and gh api graphql to fetch all review threads. Filter to threads where isResolved: false.
List all unresolved threads to the user as a numbered triage table:
| # | File | Line | Reviewer | Comment (first 100 chars) |
|---|
Completion criterion: all unresolved threads listed; none silently skipped.
Phase 2 — Triage
For each thread, classify into one of four buckets:
| Bucket | Criteria | Action |
|---|---|---|
| Fix | Valid finding; code change is clear and safe | Implement fix |
| Discuss | Finding is invalid, based on a misread, or factually wrong | Reply with explanation; do not change code |
| Human judgment | Decision requires business context the reviewer can't have | Reply asking the Supervisor or user to decide; flag for human |
| Question | Reviewer is asking, not requesting a change | Reply with answer; no code change |
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday First seen · 132 lines · 55 tokens per session scan A 9a058a386f88
resolve-pr-feedback is a skill published in the GitHub repository thunderkds/easy-ui-mcp (1 stars, last pushed today), licensed MIT. It adds 55 tokens to every session and 1,215 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-30.
Other skills, from other repositories
review-implement-phase
Implements triaged review actions, commits focused fixes, and posts Done plus resolves threads. Use when the user wants only the implementation phase of the review-framework workflow.
github-pr-workflow
Prepare a GitHub pull request from a feature branch — branch hygiene, commit shape, title/body, verification notes, screenshots for UI work, and replies to review comments.
review-delta
Review only changes since last commit using impact analysis. Token-efficient delta review with automatic blast-radius detection.
github-contributor
A step-by-step guide for contributing code, tests, documentation, or build changes to open-source projects you do not maintain. It explains how to prepare a pull request that follows the project’s rules and is easier for maintainers to review.
hero-diff-highlight
A dark code editor reveals a red deletion then a green addition with a soft pulse. Function: PR / code-change explainer.
git-pr-workflows-git-workflow
Guide changes through code checks, testing, commits, and pull request preparation. Use when coordinating a complete Git workflow and verifying readiness for collaboration.