Skills handoff

📦

handoff

Name: handoff
Author: mattpocock

Content revision r2 Low Risk

Create a Clear Agent Handoff

Long conversations make session changes difficult and can expose sensitive details. This skill creates a concise, redacted handoff that references existing artifacts.

Supports: Claude Codex Code(CC)

📊 75 Adequate

Install with my Agent

Copy this request to your Agent. It includes the canonical Skill page and manifest.

Agent request

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

Your Agent should still show its plan and request any confirmation required by the security policy.

Agent-readable resources

Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.

Markdown detail GET /skills/mattpocock-handoff.md Signed manifest GET /api/skills/mattpocock-handoff/manifest Signed lockfile GET /api/skills/mattpocock-handoff/lockfile

Test it

Using "handoff". Prepare a handoff focused on finishing the payment integration.

Expected outcome:

The handoff summarizes completed work, names the next task, references the implementation plan, and lists open validation steps.

Using "handoff". Create a handoff and remove the credential mentioned earlier.

Expected outcome:

The handoff omits the credential, records that redaction occurred, and preserves only the operational context needed for continuation.

Using "handoff". Transfer the production regression investigation to another agent.

Expected outcome:

The handoff prioritizes the reported regression, links the issue and diff, identifies unresolved evidence, and recommends relevant debugging skills.

Security Audit

Low Risk

v5 • 7/23/2026 Open versioned report

The prompt contains no executable code, network requests, command execution, or injection. Saving conversation content outside the workspace creates low confidentiality risk despite required redaction.

Files scanned

Lines analyzed

Review items

False positives ignored

Confirmed security concerns (1)

Low

SKILL.md:8 SKILL.md:14

Conversation Content Written Outside Workspace

The skill saves conversation-derived content in the OS temporary directory. Required redaction reduces, but does not eliminate, unintended local disclosure.

The external temporary-directory write and redaction requirement are explicit. Actual exposure depends on operating-system permissions and generated content.

Audited by: codex View Audit History →

Share & cite this report

Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.

Open versioned report

Copy report link

https://skillstore.io/skills/mattpocock-handoff/audits/5?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

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

HTML badge

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

Embed card

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

Academic citations (APA · BibTeX · CFF)

APA citation

mattpocock. (2026). handoff security audit report (audit version 5) [Author version unspecified]. Skillstore. https://skillstore.io/skills/mattpocock-handoff/audits/5

BibTeX citation

@techreport{mattpocock-mattpocock-handoff-2026,
  author = {mattpocock},
  title = {handoff security audit report (audit version 5)},
  institution = {Skillstore},
  year = {2026},
  number = {5},
  url = {https://skillstore.io/skills/mattpocock-handoff/audits/5},
  note = {Author version unspecified}
}

CITATION.cff

cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "handoff security audit report (audit version 5)"
version: "unspecified"
type: report
authors:
  - name: "mattpocock"
date-released: "2026-07-23"
url: "https://skillstore.io/skills/mattpocock-handoff/audits/5"
identifiers:
  - type: other
    value: "skillstore:mattpocock-handoff:audit:5"
    description: "Skillstore immutable audit report identifier"

Skillstore Score

Why this score Evidence Confidence: High

Architecture

Maintainability

Content

Community

Spec Compliance

What You Can Build

Continue Implementation

Prepare continuity notes before moving implementation work to a new AI session.

Transfer Project Decisions

Summarize decisions and artifact references so another agent can continue a coordinated project.

Redact Operational Context

Create a redacted transfer document when active context contains credentials or personal data.

Try These Prompts

Basic Handoff

Create a handoff for the next session.

Focused Handoff

Create a handoff focused on completing the authentication tests. Reference existing plans and redact secrets.

Artifact-Aware Handoff

Prepare a handoff for deployment work. Link relevant commits, issues, and ADRs without repeating their content.

Investigation Handoff

Create a handoff for a fresh agent investigating the production regression. Prioritize verified evidence, unresolved questions, constraints, and suggested skills.

Best Practices

Provide a clear focus argument when the next session has a specific objective.
Keep durable decisions in existing artifacts and reference their paths or URLs.
Review the generated handoff for sensitive data and missing context before sharing it.

Avoid

Do not use the handoff as a substitute for project documentation.
Do not include secrets, passwords, tokens, or unnecessary personal information.
Do not assume the next agent can access local paths, private URLs, or uncommitted changes.

Frequently Asked Questions

What does this skill create?

It creates a concise handoff document that helps a fresh agent continue the current conversation.

Where is the handoff saved?

It is saved in the operating system temporary directory, not the current workspace.

Does the handoff duplicate existing documents?

No. It references PRDs, plans, ADRs, issues, commits, and diffs by path or URL.

How does it handle sensitive information?

It directs the agent to redact API keys, passwords, and personally identifiable information.

Can I focus the next session on a specific task?

Yes. Pass the next session objective as an argument, and the handoff will prioritize that objective.

Can the model invoke this skill automatically?

No. Its metadata disables model invocation, so users must start it explicitly.

Developer Details

Author

mattpocock

License

MIT

Skillstore revision

Version notice

The author did not declare a version.

Repository

https://github.com/mattpocock/skills/tree/main/skills/productivity/handoff/

Ref

ebdfe608f5de2b66ff37ab4af12af8ac4f5e8006

Maintenance freshness

7/25/2026

Usage

7 downloads · 26 views

File structure

📄 SKILL.md