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.
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.
์ด ์์ฒญ์ ์์ด์ ํธ์ ๋ณต์ฌํ์ธ์. ๊ณต์ Skill ํ์ด์ง์ ๋งค๋ํ์คํธ๊ฐ ํฌํจ๋์ด ์์ต๋๋ค.
Review the Skillstore skill "prove-it-ran" from https://skillstore.io/skills/agentkitco-prove-it-ran.md and its manifest at https://skillstore.io/api/skills/agentkitco-prove-it-ran/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.
"prove-it-ran" ์ฌ์ฉ ์ค์ ๋๋ค. Verify whether my bug fix is covered by the regression test.
์์ ๊ฒฐ๊ณผ:
"prove-it-ran" ์ฌ์ฉ ์ค์ ๋๋ค. The test command exited successfully. Can I report that the tests passed?
์์ ๊ฒฐ๊ณผ:
"prove-it-ran" ์ฌ์ฉ ์ค์ ๋๋ค. Summarize release verification when device checks are unavailable.
์์ ๊ฒฐ๊ณผ:
All six static findings are false positives: Markdown formatting, local verification commands, and reporting guidance do not establish malicious execution or reconnaissance. No evidence found of prompt injection, credential access, or data exfiltration in SKILL.md. The regression procedure temporarily changes source files, so users should preserve unrelated edits.
๋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-prove-it-ran/audits/2?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report[](https://skillstore.io/skills/agentkitco-prove-it-ran?utm_source=security_passport_badge)<a href="https://skillstore.io/skills/agentkitco-prove-it-ran?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/agentkitco-prove-it-ran/security.svg" alt="Skillstore security assessment" loading="lazy"></a><iframe src="https://skillstore.io/embed/skills/agentkitco-prove-it-ran.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). prove-it-ran security audit report (audit version 2) [Author version 1.0]. Skillstore. https://skillstore.io/skills/agentkitco-prove-it-ran/audits/2@techreport{agentkitco-agentkitco-prove-it-ran-2026,
author = {agentkitco},
title = {prove-it-ran security audit report (audit version 2)},
institution = {Skillstore},
year = {2026},
number = {2},
url = {https://skillstore.io/skills/agentkitco-prove-it-ran/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: "prove-it-ran 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-prove-it-ran/audits/2"
identifiers:
- type: other
value: "skillstore:agentkitco-prove-it-ran:audit:2"
description: "Skillstore immutable audit report identifier"
Confirm the regression test fails without the fix and passes after restoration before closing a development task.
Check test discovery, skip markers, exit codes, and unverified claims before accepting a change.
Collect fresh test, lint, type check, and build evidence, with explicit notes for checks that cannot run.
Verify that the relevant tests actually ran for my latest change. Report the command, test count, exit code, and anything unverified.
Run the relevant tests and confirm changed tests appear in the output. Check discovery settings, skipped tests, and focused test markers.
Verify this fix with a failing-before, passing-after test. Preserve unrelated edits, restore the fix, and report any verification limits.
Audit every completion claim for this change. Run project-defined tests, lint, type checks, and builds; report exact commands, evidence, failures, and unverified items.
์์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/prove-it-ran์ฐธ์กฐ
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.
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.
์น ์ฑ์ QA ์ปค๋ฒ๋ฆฌ์ง ๊ฐ์
์์ฑ์ alirezarezvani
ํ๋ ํ์๋ ๋ฐฐํฌ ์๋๋ฅผ ๋ฆ์ถ์ง ์์ผ๋ฉด์๋ ๋ช ํํ ํ ์คํธ ์ ๋ต๊ณผ ์ค์ฉ์ ์ธ ์๋ํ๊ฐ ํ์ํฉ๋๋ค. ์ด ์คํฌ์ Claude, Codex, Claude Code๊ฐ ํ ์คํธ๋ฅผ ๊ณํํ๊ณ , ์ปค๋ฒ๋ฆฌ์ง๋ฅผ ๊ฒํ ํ๋ฉฐ, QA ์ํฌํ๋ก๋ฅผ ์ค์บํด๋ฉํ๋๋ก ๋์ต๋๋ค.
์๊ตฌ์ฌํญ ๋ณ๊ฒฝ ์ํฌํ๋ก ํ์คํ
์์ฑ์ yunshu0909
์๊ตฌ์ฌํญ ๋ณ๊ฒฝ์ ์๋ํ ๋ฒ์๋ฅผ ๋์ด ํ์ฅ๋๋ ๊ฒฝ์ฐ๊ฐ ๋ง๊ณ ๋ถ๋ช ํํ ํ๊ท ์ํ์ ๋ง๋ญ๋๋ค. ์ด ์คํฌ์ Claude, Codex, Claude Code์ ๋ฒ์ ์ง์ , ์ํฅ ๊ฒํ , ๊ฒ์ฆ, ์์ฌ๊ฒฐ์ ๊ธฐ๋ก์ ์ํ ๊ฒ์ดํธํ ์ํฌํ๋ก๋ฅผ ์ ๊ณตํฉ๋๋ค.
์ปค๋ฐ ์ ์ฝ๋ ๋ฆฌ๋ทฐ
์์ฑ์ 2389-research
ํ์ ์ต์ข ๋ณ๊ฒฝ ์ฌํญ์ ๋๋ฌด ๋น ๋ฅด๊ฒ ์ ๋ขฐํ ๋ ๋ฒ๊ทธ๋ฅผ ๋ฐฐํฌํฉ๋๋ค. ์ด ์คํฌ์ ๋ณด์, ๋ก์ง, ๋น์ฆ๋์ค ๊ท์น, ์ฑ๋ฅ์ ์ด์ ์ ๋ง์ถ ์ปค๋ฐ ์ ๋ฆฌ๋ทฐ๋ฅผ ์ถ๊ฐํฉ๋๋ค.
๊ตฌ์กฐํ๋ ํธ๋ฆฌ์์ง๋ก ๋ฒ๊ทธ ์์
์์ฑ์ Crearize
๋ฐฑ์๋์ ํ๋ก ํธ์๋ ์ ๋ฐ์ ๋๋ฒ๊น ์ ๋งฅ๋ฝ์ ์๊ณ ํ๊ท ํ ์คํธ๋ฅผ ๋์น ์ ์์ต๋๋ค. ์ด ์คํฌ์ ๊ทผ๋ณธ ์์ธ ๋ถ์, ์ต์ ์์ , ๊ฒ์ฆ, pull request ์ธ๊ณ๋ฅผ ์๋ดํฉ๋๋ค.
์ง์ค๋ ํ๋ ํ ์คํธ ์์ฑ
์์ฑ์ EIS-ITS
ํ์ ์ฌ์ฉ์ ํ๋ ๋์ ๊ตฌํ ์ธ๋ถ ์ฌํญ์ ๊ทธ๋๋ก ๋ฐ์ํ๋ ์ทจ์ฝํ ํ ์คํธ๋ฅผ ์ถ๊ฐํ๋ ๊ฒฝ์ฐ๊ฐ ๋ง์ต๋๋ค. ์ด ์คํฌ์ Claude, Codex, Claude Code๊ฐ ํต์ฌ ์ํฌํ๋ก๋ฅผ ์ํ ์ง์ค๋ ํ ์คํธ๋ฅผ ์์ฑํ๋๋ก ์๋ดํฉ๋๋ค.