session-handoff
78Create 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.
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.
์ด ์์ฒญ์ ์์ด์ ํธ์ ๋ณต์ฌํ์ธ์. ๊ณต์ Skill ํ์ด์ง์ ๋งค๋ํ์คํธ๊ฐ ํฌํจ๋์ด ์์ต๋๋ค.
Review the Skillstore skill "repro-first-debugging" from https://skillstore.io/skills/agentkitco-repro-first-debugging.md and its manifest at https://skillstore.io/api/skills/agentkitco-repro-first-debugging/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.
"repro-first-debugging" ์ฌ์ฉ ์ค์ ๋๋ค. Illustrative request: an empty search returns an error instead of an empty result list.
์์ ๊ฒฐ๊ณผ:
"repro-first-debugging" ์ฌ์ฉ ์ค์ ๋๋ค. Illustrative request: investigate an intermittent export crash that does not occur in the available environment.
์์ ๊ฒฐ๊ณผ:
All four static findings are false positives caused by Markdown formatting or ordinary debugging prose. No evidence found of malicious execution, reconnaissance, exfiltration, or prompt injection in SKILL.md. The skill describes a reproduction-first debugging workflow with explicit verification and scope limits.
๋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-repro-first-debugging/audits/2?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report[](https://skillstore.io/skills/agentkitco-repro-first-debugging?utm_source=security_passport_badge)<a href="https://skillstore.io/skills/agentkitco-repro-first-debugging?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/agentkitco-repro-first-debugging/security.svg" alt="Skillstore security assessment" loading="lazy"></a><iframe src="https://skillstore.io/embed/skills/agentkitco-repro-first-debugging.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). repro-first-debugging security audit report (audit version 2) [Author version 1.0]. Skillstore. https://skillstore.io/skills/agentkitco-repro-first-debugging/audits/2@techreport{agentkitco-agentkitco-repro-first-debugging-2026,
author = {agentkitco},
title = {repro-first-debugging security audit report (audit version 2)},
institution = {Skillstore},
year = {2026},
number = {2},
url = {https://skillstore.io/skills/agentkitco-repro-first-debugging/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: "repro-first-debugging 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-repro-first-debugging/audits/2"
identifiers:
- type: other
value: "skillstore:agentkitco-repro-first-debugging:audit:2"
description: "Skillstore immutable audit report identifier"
Reproduce a regression, compare possible causes, and verify a focused fix against the original test and nearby tests.
Turn a complex failure into a minimal input or automated regression test with clear expected and actual behavior.
Trace evidence through code and recent changes, then report similar patterns without expanding the patch scope.
Use repro-first-debugging for this bug: [symptom]. Expected behavior: [expected]. Actual behavior: [actual]. Ask for missing reproduction details before editing.
Use repro-first-debugging on [failing test command]. Capture the failure, list plausible causes, make the smallest supported fix, and show verification.
Investigate [failure] using [steps or input]. Reduce the reproduction, add a regression test, compare three hypotheses, and remove temporary diagnostics after verification.
Investigate the regression between [known good revision] and [failing revision] in an isolated checkout. Reproduce first, test hypotheses, and report evidence and related risks.
์์ฑ์
agentkitco๋ผ์ด์ ์ค
MIT
์์ฑ์ ๋ฒ์
v1.0
Skillstore ๋ฆฌ๋น์
r1
๋ฒ์ ์๋ด
์์ฑ์๊ฐ ์ ์ธํ ๋ฒ์ ์ ์ ํจํ SemVer๊ฐ ์๋๋๋ค.
๋ฆฌํฌ์งํ ๋ฆฌ
https://github.com/agentkitco/agentkit-dev-skills/tree/a5058856442fcb89bd538b1c01f94558488bfac3/skills/repro-first-debugging์ฐธ์กฐ
18efac79a818d7e997295839638fdd21906cfd1c
์ ์ง๋ณด์ ์ต์ ์ฑ
2026. 10. 22.
์ฌ์ฉ๋
6 ๋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.
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.
Upgrade Dependencies With Focused Migration Checks
Dependency upgrades can introduce breaking changes and obscure existing failures. This skill guides focused migrations through release notes, baseline comparisons, minimal edits, and rollback reporting.
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.
์ค๋ฅ์ ๊ทผ๋ณธ ์์ธ ๋๋ฒ๊ทธ
์์ฑ์ 89jobrien
์ฆ๊ฑฐ๊ฐ ๋ก๊ทธ, ์คํ ํธ๋ ์ด์ค, ์๋น์ค ์ ๋ฐ์ ํฉ์ด์ ธ ์์ผ๋ฉด ์ค๋ฅ์ ์ธ์๋ํธ๋ฅผ ๋ถ๋ฅํ๊ธฐ ์ด๋ ต์ต๋๋ค. ์ด ์คํฌ์ ์ง๋จ์ ๊ตฌ์กฐํํ๊ณ , ๋ก๊ทธ๋ฅผ ํ์ฑํ๋ฉฐ, ํจํด์ ์๋ณํ๊ณ , ์ต์ํ์ ์์ ์ผ๋ก ์๋ดํฉ๋๋ค.
์ํํธ์จ์ด ๋ฌธ์ ๋ฅผ ์ฒด๊ณ์ ์ผ๋ก ๋๋ฒ๊น ํ๊ธฐ
์์ฑ์ Asmayaseen
๊ตฌ์กฐํ๋์ง ์์ ๋ฒ๊ทธ ์์ ์ ์๊ฐ์ ๋ญ๋นํ๊ณ ์ค์ ์คํจ ์์ธ์ ์จ๊ธธ ์ ์์ต๋๋ค. ์ด ์คํฌ์ Claude, Codex, Claude Code๊ฐ ์ฆ๊ฑฐ ๊ธฐ๋ฐ ๊ทผ๋ณธ ์์ธ ๋ถ์์ ์ํํ๋๋ก ์๋ดํฉ๋๋ค.
์ํํธ์จ์ด ์ค๋ฅ๋ฅผ ์ฒด๊ณ์ ์ผ๋ก ๋๋ฒ๊น ํ๊ธฐ
์์ฑ์ shubhamsaboo
์ฆ์์ด ์ค์ ์์ธ์ ๊ฐ๋ฆฌ๋ฉด ๋ฒ๊ทธ๋ ์์ง๋์ด๋ง ์๊ฐ์ ๋ญ๋นํ๊ฒ ๋ง๋ญ๋๋ค. ์ด ์คํฌ์ Claude, Codex, Claude Code๊ฐ ๊ตฌ์กฐํ๋ ์กฐ์ฌ, ๊ฐ์ค ๊ฒ์ฆ, ์์ , ์๋ฐฉ์ ์ํํ๋๋ก ์๋ดํฉ๋๋ค.
๋ฒ๊ทธ ์ง๋จ ๋ฐ ์์ ๊ณํ ์๋ฆฝ
์์ฑ์ 727474430
์ํํธ์จ์ด ์ฅ์ ๋ ์์ธ์ด ๋ถ๋ถ๋ช ํ๊ณ ์ฆ๊ฑฐ๊ฐ ํฉ์ด์ ธ ์๋ ๊ฒฝ์ฐ๊ฐ ๋ง์ต๋๋ค. ์ด ์คํฌ์ Claude, Codex, Claude Code๊ฐ ์ค์ฉ์ ์ธ ๋ณต๊ตฌ ๋จ๊ณ๊ฐ ํฌํจ๋ ๊ตฌ์กฐํ๋ ์ง๋จ ๋ณด๊ณ ์๋ฅผ ์์ฑํ๋๋ก ์๋ดํฉ๋๋ค.
ํ๋ก๋์ ์ค๋ฅ๋ฅผ ๋ ๋น ๋ฅด๊ฒ ์ง๋จ
์์ฑ์ sickn33
๋ก๊ทธ, ํธ๋ ์ด์ค, ๋ฆด๋ฆฌ์ค๊ฐ ํฉ์ด์ ธ ์์ผ๋ฉด ํ๋ก๋์ ์ค๋ฅ ๋๋ฒ๊น ์ด ๋๋ ค์ง๋๋ค. ์ด ์คํฌ์ Claude, Codex, Claude Code๊ฐ ๊ตฌ์กฐํ๋ ๊ทผ๋ณธ ์์ธ ๋ถ์๊ณผ ์ต์ ๋ฒ๋น๋ฆฌํฐ ๊ฐ์ ์ ์ํํ๋๋ก ์๋ดํฉ๋๋ค.