Install
$ agentstack add skill-fengsihao23-eng-shen-hua-handoff-writer ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Handoff Writer
Handoff Writer leaves the next agent with a reliable resume point.
Trigger Conditions
Use this skill when:
- A response is about to end after project work.
- Work is paused, blocked, or handed to another agent/session.
- The user asks for status, summary, continuation notes, or "where are we".
$project-commanderfinishes a round.
Do Not Trigger
Do not use this skill for:
- One-line answers with no project state.
- Work that explicitly must leave no project memory.
Handoff Workflow
- Read
.agent/PLAN.md,.agent/TASKS.md,.agent/LOG.md,.agent/DECISIONS.md, and.agent/REVIEW_CHECKLIST.md. - Summarize the current objective and phase.
- List completed work this round.
- List changed files and their purpose.
- Record verification commands and results.
- Record decisions and residual risks.
- Write the exact next action for a future agent.
- Update task statuses so the next agent does not have to infer them.
Required .agent/ Updates
Always update:
.agent/HANDOFF.md: full current handoff..agent/LOG.md: handoff written with summary..agent/TASKS.md: next action and statuses.
Update when relevant:
.agent/PLAN.md: current phase if changed..agent/DECISIONS.md: final decisions not yet recorded.
Other Skills
- Use
$self-reviewerbefore handoff when changes were made. - Use
$verification-loopfirst if no verification status exists and the task involved code/config changes.
Subagents
Do not launch new subagents only to write a handoff. If subagents are active or recently completed, include their status and outputs.
Verification Commands
Handoff Writer does not normally run commands. It records the latest verification state and flags stale or missing verification.
Output Format
HANDOFF
Objective:
Current phase:
Completed:
Changed files:
Verification:
Decisions:
Open risks/blockers:
Next action:
Resume prompt:
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: fengsihao23-eng
- Source: fengsihao23-eng/shen-hua
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.