技能 session-handoff

📦

session-handoff

Name: session-handoff
Author: agentkitco

v1.0 內容修訂 r2 安全 ⚙️ 外部命令

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.

支援: Claude Codex Code(CC)

🥉 78 銅級

Maintain this Skill? Claim it 🥉 78 銅級

使用我的智慧代理安裝

將此請求複製給你的智慧代理，其中包含權威 Skill 頁面和清單。

智能體請求

Review the Skillstore skill "session-handoff" from https://skillstore.io/skills/agentkitco-session-handoff.md and its manifest at https://skillstore.io/api/skills/agentkitco-session-handoff/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.

你的智慧代理仍應顯示其計畫，並依安全政策請求必要確認。

Agent 可讀資源

當 AI Agent、爬蟲或腳本需要乾淨脈絡、而不是讀取完整頁面時，請使用這些連結。

Markdown 詳情 GET /skills/agentkitco-session-handoff.md 已簽名 manifest GET /api/skills/agentkitco-session-handoff/manifest 已簽名 lockfile GET /api/skills/agentkitco-session-handoff/lockfile

測試它

正在使用「session-handoff」。 Prepare a handoff for an unfinished search filter change.

預期結果:

Goal: finish the search filter update.
Current state: the filter change is incomplete; tests have not been run.
Decision: preserve the existing query format to avoid changing callers.
Next steps: finish input validation, run focused tests, and review the final diff.
Not verified: behavior with empty search input.

正在使用「session-handoff」。 Hand off a failing build when the full error output is unavailable.

預期結果:

Goal: restore a passing build.
Current state: a build failure was reported, but its exact command and error are unavailable.
Open question: which build command produced the failure?
Next steps: reproduce the failure, record the exact command and error, and investigate the first failing step.
Not verified: the reported failure and its cause.

安全審計

安全

v2 • 2026/10/22 開啟版本化報告

All five static findings are false positives: Markdown backticks, read-only Git inspection, and verification placeholders explain the matches. No evidence found of prompt injection, data exfiltration, or malicious intent in SKILL.md. The workflow writes a handoff document and may run project tests, so repository trust and normal tool permissions still matter.

已掃描檔案

分析行數

複核項目

已忽略的誤報

風險因素

⚙️ 外部命令 (3)

SKILL.md:16 SKILL.md:17 SKILL.md:23-52

最近一次完成的靜態與語意稽核未偵測到已確認的安全發現。這並不能證明該 Skill 沒有副作用。

審計單位: codex 檢視審計紀錄 →

分享與引用此報告

分享版本化評估報告、中性徽章、嵌入卡片與引用。Skillstore 只報告證據，不判斷該 Skill 是否安全。

開啟版本化報告

複製報告連結

https://skillstore.io/skills/agentkitco-session-handoff/audits/2?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown 徽章

[![Skillstore security assessment](https://skillstore.io/badges/skills/agentkitco-session-handoff/security.svg)](https://skillstore.io/skills/agentkitco-session-handoff?utm_source=security_passport_badge)

HTML 徽章

<a href="https://skillstore.io/skills/agentkitco-session-handoff?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/agentkitco-session-handoff/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

嵌入卡片

<iframe src="https://skillstore.io/embed/skills/agentkitco-session-handoff.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>

學術引用 (APA · BibTeX · CFF)

APA 引用

agentkitco. (2026). session-handoff security audit report (audit version 2) [Author version 1.0]. Skillstore. https://skillstore.io/skills/agentkitco-session-handoff/audits/2

BibTeX 引用

@techreport{agentkitco-agentkitco-session-handoff-2026,
  author = {agentkitco},
  title = {session-handoff security audit report (audit version 2)},
  institution = {Skillstore},
  year = {2026},
  number = {2},
  url = {https://skillstore.io/skills/agentkitco-session-handoff/audits/2},
  note = {Author version 1.0}
}

CITATION.cff

cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "session-handoff 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-session-handoff/audits/2"
identifiers:
  - type: other
    value: "skillstore:agentkitco-session-handoff:audit:2"
    description: "Skillstore immutable audit report identifier"

比較變體

3 個可安裝變體

每位作者的技能都保留為獨立的可安裝項目。推薦變體依 Skillstore 證據排序。

為何此變體排名第一

Skillstore 評分最高

作者 / 來源 Skillstore 評分證據置信度 Skillstore 使用量已更新

agentkitco 推薦目前

agentkitco-session-handoff

Skillstore 評分 78

證據置信度中

Skillstore 使用量 8

已更新

2026-10-22

alapha888

alapha888-session-handoff

Skillstore 評分 77

證據置信度中

Skillstore 使用量 8

已更新

2026-10-06

softaworks

softaworks-session-handoff

Skillstore 評分 50

證據置信度高

Skillstore 使用量 44

已更新

2026-09-09

Skillstore 評分

評分依據證據置信度: 中

架構

可維護性

內容

社群

規範符合度

你可以打造什麼

Pause unfinished development

Capture unfinished changes, test results, and next steps before ending a coding session.

Transfer an investigation

Record reproduction commands, exact errors, rejected approaches, and unresolved questions for the next investigator.

Coordinate agent changes

Provide another agent with verified project state and ordered actions without requiring the full conversation.

試試這些提示

Create a basic handoff

Create HANDOFF.md for this session. Include the goal, current state, and next steps. Do not commit it.

Verify project state

Prepare a handoff after checking Git status, branch, and recent commits. Run quick tests if available and permitted. Mark anything unverified.

Transfer a blocked investigation

Create a debugging handoff with exact failing commands, errors, rejected approaches, and questions requiring my decision. Exclude secrets and personal data.

Prepare another agent to resume

Write a handoff under about 80 lines for another agent. Separate verified facts from assumptions, identify unfinished files, and order actionable next steps. Do not commit.

最佳實務

Verify repository state immediately before writing, and distinguish completed checks from assumptions.
Keep next steps specific and ordered; include exact commands and errors for observed failures.
Review the handoff for secrets, tokens, and personal data, and keep it uncommitted unless explicitly requested.

避免

Treating remembered test results as current verification without rerunning or labeling them.
Writing vague next steps that require access to the previous conversation.
Including credentials or accidentally committing session notes to a shared branch.

常見問題

What does this skill create?

It creates HANDOFF.md with goals, verified state, decisions, ordered next steps, known traps, open questions, and unverified claims.

Which tools are listed as supported?

The listing supports Claude, Codex, and Claude Code. Repository inspection and file writing require appropriate tool access.

Does it run tests automatically?

It asks the agent to run quick project tests or a build when possible. Checks that were not run must remain labeled unverified.

Will it commit the handoff?

No. The instructions prohibit committing the handoff unless asked and require warning about accidental inclusion on a shared branch.

Can I choose a different output location?

Yes. The default is the repository root, but you can specify another path.

How do I resume work later?

Start a new session and ask the agent to read HANDOFF.md and continue. The file does not automatically restore the previous conversation.

開發者詳細資訊

作者

agentkitco

授權

MIT

作者版本

v1.0

Skillstore 修訂

版本提示

作者聲明的版本不符合 SemVer 規範。

儲存庫

https://github.com/agentkitco/agentkit-dev-skills/tree/a5058856442fcb89bd538b1c01f94558488bfac3/skills/session-handoff

引用

18efac79a818d7e997295839638fdd21906cfd1c

維護新鮮度

2026/10/22

使用量

5 次下載 · 0 次瀏覽

檔案結構

📄 SKILL.md

agentkitco 的更多技能

查看全部

📦

security-quick-review

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.

安全與法遵查看

📦

review-my-diff

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.

程式開發查看

📦

repro-first-debugging

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.

程式開發查看

📦

safe-refactor

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.

程式開發查看

📦

prove-it-ran

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.

程式開發查看

📦

dependency-upgrade

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.

程式開發查看

查看全部

📦