AgentStack
SKILL verified CC0-1.0 Self-run

Handoff

skill-ahgraber-skills-handoff · by ahgraber

|-

No reviews yet
0 installs
16 views
0.0% view→install

Install

$ agentstack add skill-ahgraber-skills-handoff

✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.

Security review

✓ Passed

No 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.

Are you the author of Handoff? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Handoff

Produce a transfer-ready handoff for in-progress work.

Invocation Notice

  • Inform the user when this skill is being invoked by name: handoff.

Critical Constraints

  • Assume the recipient can only see the handoff output and nothing else.
  • Output one fully filled handoff payload in chat.
  • Do not create a handoff file unless explicitly requested.
  • Do not rely on references like "above" or "earlier in this thread".
  • If information is missing, write Unknown and specify what is needed.

When to Use

  • Handing off work to a new conversation or agent.
  • Resetting context while preserving execution continuity.
  • Transferring partially complete implementation/debugging work.
  • Capturing next actions before ending a session.

When Not to Use

  • Simple same-thread progress updates.
  • Creating long-lived project documentation.
  • Retrospectives not intended for immediate continuation.

Workflow

  1. Extract the objective, success criteria, and current status from available context.
  2. Collect concrete evidence: files touched, commands run, validation status, blockers, and risks.
  3. Capture decisions with rationale so the recipient understands intent and tradeoffs.
  4. Fill every section of assets/handoff-template.md.
  5. Ensure next steps are ordered and step 1 is immediately executable.
  6. Return the completed template in chat for copy/paste.

Output Rules

  • Match the template section headings exactly.
  • Keep statements specific and verifiable; avoid vague summaries.
  • Include validation details (passed, failed, or not run).
  • Include blockers with owner/dependency and concrete impact.

Quality Checklist

  • The goal and definition of done are explicit.
  • Done vs. pending work is unambiguous.
  • Blockers include dependency/owner and impact.
  • Validation status includes what passed, failed, or was skipped.
  • The first next step can be executed immediately.
  • The recipient can proceed without asking for missing context.

References

  • assets/handoff-template.md - canonical output format.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet — be the first.

Versions

  • v0.1.0 Imported from the upstream source.