Write Evidence-Based Pull Request Descriptions
Reviewers need clear reasons, behavior changes, and testing evidence before assessing a pull request. This skill turns diffs and commits into structured descriptions with review priorities and rollout risks.
์ด ์์ฒญ์ ์์ด์ ํธ์ ๋ณต์ฌํ์ธ์. ๊ณต์ Skill ํ์ด์ง์ ๋งค๋ํ์คํธ๊ฐ ํฌํจ๋์ด ์์ต๋๋ค.
Review the Skillstore skill "pr-description" from https://skillstore.io/skills/agentkitco-pr-description.md and its manifest at https://skillstore.io/api/skills/agentkitco-pr-description/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.์์ด์ ํธ๋ ๊ณ์ํด์ ๊ณํ์ ํ์ํ๊ณ ๋ณด์ ์ ์ฑ ์์ ์๊ตฌํ๋ ํ์ธ์ ์์ฒญํด์ผ ํฉ๋๋ค.
AI ์์ด์ ํธ, ํฌ๋กค๋ฌ, ์คํฌ๋ฆฝํธ๊ฐ ์ ์ฒด ํ์ด์ง ๋์ ์ ๋ฆฌ๋ ์ปจํ ์คํธ๋ง ํ์ํ ๋ ์ด ๋งํฌ๋ฅผ ์ฌ์ฉํ์ธ์.
"pr-description" ์ฌ์ฉ ์ค์ ๋๋ค. The diff prevents duplicate form submissions while saving. The user reports passing form tests, but provides no command or manual test results.
์์ ๊ฒฐ๊ณผ:
"pr-description" ์ฌ์ฉ ์ค์ ๋๋ค. The diff adds an optional request timeout setting. Existing behavior remains the default, and no tests were run.
์์ ๊ฒฐ๊ณผ:
All five static findings are false positives involving Markdown formatting, read-only Git inspection, or guidance against unsupported screenshot claims. No evidence found of credential access, data exfiltration, destructive commands, or prompt injection in SKILL.md. Pull request creation is explicitly prohibited unless requested.
๋ฒ์ ์ด ์ง์ ๋ ํ๊ฐ ๋ณด๊ณ ์, ์ค๋ฆฝ ๋ฐฐ์ง, ์๋ฒ ๋ ์นด๋ ๋ฐ ์ธ์ฉ์ ๊ณต์ ํ์ธ์. Skillstore๋ ๊ทผ๊ฑฐ๋ฅผ ๋ณด๊ณ ํ์ง๋ง ์ด Skill์ ์์ ์ฌ๋ถ๋ฅผ ํ๋จํ์ง ์์ต๋๋ค.
https://skillstore.io/skills/agentkitco-pr-description/audits/2?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report[](https://skillstore.io/skills/agentkitco-pr-description?utm_source=security_passport_badge)<a href="https://skillstore.io/skills/agentkitco-pr-description?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/agentkitco-pr-description/security.svg" alt="Skillstore security assessment" loading="lazy"></a><iframe src="https://skillstore.io/embed/skills/agentkitco-pr-description.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>agentkitco. (2026). pr-description security audit report (audit version 2) [Author version 1.0]. Skillstore. https://skillstore.io/skills/agentkitco-pr-description/audits/2@techreport{agentkitco-agentkitco-pr-description-2026,
author = {agentkitco},
title = {pr-description security audit report (audit version 2)},
institution = {Skillstore},
year = {2026},
number = {2},
url = {https://skillstore.io/skills/agentkitco-pr-description/audits/2},
note = {Author version 1.0}
}cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "pr-description security audit report (audit version 2)"
version: "1.0"
type: report
authors:
- name: "agentkitco"
date-released: "2026-10-22"
url: "https://skillstore.io/skills/agentkitco-pr-description/audits/2"
identifiers:
- type: other
value: "skillstore:agentkitco-pr-description:audit:2"
description: "Skillstore immutable audit report identifier"
๊ฐ ์์ฑ์์ ์คํฌ์ ๋ณ๋์ ์ค์น ํญ๋ชฉ์ผ๋ก ์ ์ง๋ฉ๋๋ค. ์ถ์ฒ ๋ณํ์ Skillstore ๊ทผ๊ฑฐ๋ก ์์๊ฐ ์ ํด์ง๋๋ค.
์ด ๋ณํ์ด 1์์ธ ์ด์
bfdcampos-pr-description
2026-09-09
agentkitco-pr-description
2026-10-22
Summarize behavior changes, testing evidence, and review priorities before submitting a feature branch.
Draft a contribution description using the repository template and linked issue context.
Highlight migrations, configuration changes, compatibility concerns, and rollback considerations for review.
Write a pull request title and description for my current branch. Inspect the diff and commits, and clearly state any missing testing evidence.
Draft this branch's pull request using the repository template. Include linked issues when supported, and ask me for missing motivation.
Review this PR draft against the actual diff: [draft]. Remove unsupported claims, group behavior changes, and distinguish completed testing from missing coverage.
Compare this branch with [base branch] and draft a risk-focused PR description. Cover review order, intentional exclusions, testing, migrations, compatibility, and rollback considerations.
์์ฑ์
agentkitco๋ผ์ด์ ์ค
MIT
์์ฑ์ ๋ฒ์
v1.0
Skillstore ๋ฆฌ๋น์
r2
๋ฒ์ ์๋ด
์์ฑ์๊ฐ ์ ์ธํ ๋ฒ์ ์ ์ ํจํ SemVer๊ฐ ์๋๋๋ค.
๋ฆฌํฌ์งํ ๋ฆฌ
https://github.com/agentkitco/agentkit-dev-skills/tree/a5058856442fcb89bd538b1c01f94558488bfac3/skills/pr-description์ฐธ์กฐ
18efac79a818d7e997295839638fdd21906cfd1c
์ ์ง๋ณด์ ์ต์ ์ฑ
2026. 10. 22.
์ฌ์ฉ๋
5 ๋ค์ด๋ก๋ ยท 0 ์กฐํ
ํ์ผ ๊ตฌ์กฐ
๐ SKILL.md
Create Clear Agent Session Handoffs
Long sessions and agent switches can lose decisions, test results, and unfinished work. This skill creates a concise HANDOFF.md with verified state and actionable next steps.
Review Code Changes for Security Risks
Code changes can introduce security problems that routine reviews miss. This skill guides focused AI triage with evidence, realistic severity, and concrete fixes.
Review Your Diff Before Opening a Pull Request
Local changes can hide bugs, security gaps, and missing tests before human review. This skill guides an evidence-based review with prioritized findings and explicit verification results.
Debug Bugs With Reproducible Evidence
Speculative fixes can hide causes and leave bugs unresolved. This skill guides assistants through reproduction, hypothesis testing, focused changes, and evidence-based verification.
Refactor Code with Tests and Small Changes
Code cleanup can introduce behavior changes that are difficult to detect. This skill guides small refactoring steps with baseline tests, dependency checks, and repeated verification.
Verify Tests Ran Before Reporting Completion
Passing claims can hide skipped tests, stale results, or checks that never exercised a change. This skill guides fresh verification and evidence-based completion reports.
๊ตฌ์กฐํ๋ ํ์ง ๊ฒ์ฌ๋ก ์ฝ๋ ๋ฆฌ๋ทฐํ๊ธฐ
์์ฑ์ alirezarezvani
์ฝ๋ ๋ฆฌ๋ทฐ์์๋ ํ์ง, ๋ณด์, ์ ์ง๋ณด์์ฑ ๋ฌธ์ ๊ฐ ๋๋ฝ๋ ์ ์์ต๋๋ค. ์ด ์คํฌ์ ์คํฌ๋ฆฝํธ, ์ฒดํฌ๋ฆฌ์คํธ, ๋ณด๊ณ ์ ์์ฑ์ ํตํด ๊ตฌ์กฐํ๋ ๋ฆฌ๋ทฐ๋ฅผ ์๋ดํฉ๋๋ค.
GitHub ํ ๋ฆฌํ์คํธ๋ฅผ ๋ ๋น ๋ฅด๊ฒ ๋ฆฌ๋ทฐํ๊ธฐ
์์ฑ์ Bind
์ฝ๋ ๋ฆฌ๋ทฐ ์กฐ์จ์๋ ๋ฐ๋ณต์ ์ธ GitHub CLI ํ์ธ๊ณผ ๋๊ธ ์์ฑ์ด ํ์ํ ๊ฒฝ์ฐ๊ฐ ๋ง์ต๋๋ค. ์ด ์คํฌ์ PR ๋ฆฌ๋ทฐ๋ฅผ ์ํ triage, guideline ์กฐํ, inline ํผ๋๋ฐฑ ํฌํผ๋ฅผ ๋ฌธ์ํํฉ๋๋ค.
Review Defects and Verify Root-Cause Repairs
์์ฑ์ aakashh242
Reviews can miss failure conditions or accept fixes without reliable evidence. Gauntlet guides scoped adversarial reviews, authorized repairs, and revision-bound verification within a finite budget.
๊ณ ๊ธ Git ์ํฌํ๋ก ๋ง์คํฐํ๊ธฐ
์์ฑ์ AutumnsGrove
๋ณต์กํ Git ํ์คํ ๋ฆฌ๋ ์์ ๋ด์ฉ์ ์์ง ์๊ณ ๋ณต๊ตฌํ๊ธฐ ์ด๋ ค์ธ ์ ์์ต๋๋ค. ์ด ์คํฌ์ rebase, ์ถฉ๋, bisect, ๋ณต๊ตฌ, ๋ธ๋์น ๊ด๋ฆฌ๋ฅผ ์ํ ์๋ดํ ์ํฌํ๋ก๋ฅผ ์ ๊ณตํฉ๋๋ค.
Audit NestJS Code with Evidence-Backed Findings
์์ฑ์ amirtaherkhani
NestJS repositories can hide boundary flaws and runtime risks that lint results alone cannot reveal. This skill combines local evidence collection and semantic review into one prioritized report.
์ฝ๋ฉ ์์ด์ ํธ ์ํฌํ๋ก ๊ด๋ฆฌ
์์ฑ์ kiwi-phantomworks
์์ , ๋ฒ์, ๊ฒ์ฌ๊ฐ ๋ชจํธํ๋ฉด ์ฝ๋ฉ ์์ด์ ํธ ํ๋ก์ ํธ๋ ๋ฐฉํฅ์ด ํ๋ค๋ฆด ์ ์์ต๋๋ค. ์ด ์คํฌ์ Claude, Codex, Claude Code ์์ ์ ์ ํ๋ ๋ฒ์ ์์ ๋๊ณ ๊ฒ์ฆ ๊ฐ๋ฅํ๊ฒ ์ ์งํ๋ PM ํ ํ๋ฆฟ๊ณผ ๋ฆฌ๋ทฐ ๊ท์น์ ์ ๊ณตํฉ๋๋ค.