shenxingy/handoff
configs/skills/handoff/SKILL.md
End-of-session context handoff. Saves session state so the next session or a parallel agent can pick up exactly where the left off. Run this when context is getting full (~80%) or before stopping work.
$ install --global
skillsauthnpx skillsauth add shenxingy/claude-code-kit handoffInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Jun 10, 2026, 5:51 AM33.1s2 files scanned
SKILL.md
- name:
- handoff
- description:
- End-of-session context handoff. Saves session state so the next session or a parallel agent can pick up exactly where the left off. Run this when context is getting full (~80%) or before stopping work.
- when_to_use:
- context full, stop work, save state, end session, 保存, 交接, context getting full
- user_invocable:
- true
Handoff Skill
When context is ~80% full (or before stopping), output a structured handoff document so the next session can resume exactly where this one left off — no re-explanation needed.
Handoff Format (STRUCTURED HANDOFF v2)
The authoritative template lives in prompt.md (Step 3) — this is the shape it produces.
Saved to .claude/handoff-{YYYY-MM-DD-HH-MM}.md; /pickup parses these exact section headers.
# Handoff: {YYYY-MM-DD HH:MM}
<!-- STRUCTURED HANDOFF v2 — preserve all section headers exactly -->
## Goal
One sentence: the overall objective of this work session / task.
## Constraints & Preferences
- <technical constraints, stack choices, things explicitly NOT to do>
- <user preferences discovered this session>
## Progress
### Done ✅
- [x] <completed item with exact file path> (<short commit hash>)
### In Progress 🔄
- [ ] <item currently being worked on — what specifically remains>
### Blocked 🚫
- <specific blocker needing human input — OR "none">
## Key Decisions
- **<Decision>**: <rationale — why this over alternatives>
## Next Steps (ordered by priority)
1. <exact next action — specific file, specific change, specific command>
2. <second action>
## Critical Context
- <non-obvious codebase facts, pitfalls, configs that matter>
- <API keys or secrets needed (mention only location, never paste values)>
## Files
<read-files>
<absolute paths of files READ this session, one per line>
</read-files>
<modified-files>
<absolute paths of files MODIFIED this session, one per line>
</modified-files>
## Meta
- Branch: <git branch --show-current>
- Uncommitted: <git status -sb output, or "clean">
- Build: <passing | failing | unknown>
- Session: <approximate duration>
Subsequent handoffs are incremental: keep Goal/Constraints, move completed In-Progress items to Done ✅, update Next Steps (see prompt.md Step 2).
Rules
- Goal: Keep it to 1 paragraph. If you can't summarize it, the scope is too large.
- Key Decisions: Only record non-obvious decisions. "Used Python because it's the project language" doesn't need a note.
- Blocked: If blocked, write to
.claude/blockers.mdinstead of leaving it in handoff. - Secrets: Never paste actual API keys, tokens, or passwords. Just note where they are stored.
- Read/Modified files: These go in the XML-tagged sections so the next session can load them with exact context.
What Happens to the Handoff
The next session receives this via /pickup or by reading the handoff file. It should be able to:
- Understand the current state without asking you
- Know exactly where to pick up
- Understand why past decisions were made
Related Skills
shenxingy/trim-tests
testing
VerifiedTrustedCommunity
Test-suite diet — consolidate near-identical tests into table-driven cases, delete trivial/mock-only/brittle tests, and report every piece of coverage intentionally given up. Counterweight to AI test bloat that erodes loop clock speed.
8SKILL.mdUpdated Jun 13, 2026
shenxingy/iloop
development
VerifiedTrustedCommunity
In-session iterative loop — keeps Claude running in the current session until a task is done. Unlike /loop (which spawns background workers), /iloop stays in the current session and re-prompts each iteration via Stop hook. Use for: 'keep fixing until tests pass', 'iterate until this feature works', autonomous debugging. Triggers on: '/iloop', 'in-session loop', 'keep iterating', 'loop until done'.
8SKILL.mdUpdated Jun 10, 2026
shenxingy/email-write
development
VerifiedTrustedCommunity
Compose high-converting emails using proven copy frameworks (PAS, AIDA, BAB, FAB, 4Ps). Generates subject line variants with scores, responsive HTML templates with dark mode support, plain-text fallback, and preheader recommendations. Optimized for cold outreach, newsletters, product launches, promotions, and transactional emails. Adapts to user context from email-profile.md.
8SKILL.mdUpdated Jun 10, 2026
shenxingy/email-sequence
tools
VerifiedTrustedCommunity
Designs complete email automation sequences with timing, subject lines, copy, and conditional logic. Supports welcome series, nurture campaigns, re-engagement, abandoned cart, post-purchase, review requests, and custom sequences. Adapts sequence type, cadence, frameworks, and conditional branching to business context. Use when user wants to create an automated email series triggered by subscriber actions or time intervals.
8SKILL.mdUpdated Jun 10, 2026