Install
$ agentstack add skill-aploe-claude-handoff-skill-handoff-resume ✓ 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.
About
Handoff Resume
Pick up a handoff doc and orchestrate the bootstrap 5-step protocol so the user can verify state and approve continuation in one round-trip.
This skill is Claude-Code-specific. Other agents (Codex, Cursor, Gemini, GPT) follow the bootstrap block embedded in the doc itself — no skill needed on the receiving end.
Always do this first
Before any action, read references/instructions.md. It contains:
- Path/slug resolution priority
- Doc shape validation (version marker, minimum sections)
- The bootstrap 5-step execution flow
- Env verification logic (branch, processes, dirty files, paths)
- Status presentation format
- Discrepancy handling (critical / warning / info)
- INDEX update on confirmation
- Completion marking (
done) at end of session
references/bootstrap.md is also available — used as a reference when validating an incoming doc's shape.
Universal rules
- Never auto-correct env mismatches. The user should always see them.
- Never begin executing the next step from the doc's Section 3 until the user explicitly confirms. The bootstrap block exists to defeat the "let me get started for you" failure mode — honor it.
- Respect verbatim-quoted constraints in Section 4 before each significant decision. Re-read them; do not paraphrase.
- Redact secrets that may surface during env verification (running-process env vars, etc.).
- Output language follows the user's conversation language.
- Update INDEX status to
resumedonly AFTER the user confirms — not on load. The user might cancel.
Related sub-skills
/handoff-writeto create a new handoff./handoff-listto find available handoffs if the arg is ambiguous./handoff-archiveto clean up stale ones after resume.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: aploe
- Source: aploe/claude-handoff-skill
- 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.