— No reviews yet
0 installs
11 views
0.0% view→install
Install
$ agentstack add skill-ainova-systems-intelligence-dev-packs-dev-handoff ✓ 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.
Are you the author of Dev Handoff? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claimAbout
Handoff
Produce a portable prompt a fresh session (any tool, any machine) pastes to continue exactly where this one stands. The output is a prompt, not a summary. An argument describing the next session's focus tailors the content.
Steps
- Verify state with commands, never from memory:
git branch --show-current,git log --oneline -5,git status --porcelain, gate results actually observed this session. - Capture: the task in the owner's framing plus agreed scope; the spec path and current task position; done-and-verified vs in-progress, with the exact next action.
- Capture decisions with one-line rationale, including rejected approaches so they are not retried.
- Reference, don't duplicate: content already in artifacts (spec, ADRs, commits, PR description) is cited by path or URL, never copied in.
- Add a suggested skills section: the skills the next session should invoke (usually
spec-continue, plus whatever the stated focus needs). - Redact secrets and personal data - the handoff may travel between machines and tools.
- Write the prompt: repo-relative paths only, no "as we discussed"; ordered next steps starting with the immediate action; the verification commands the next session runs FIRST to confirm state.
- Output in full; save a copy outside version control (OS temp dir or the project's ignored scratch dir).
Verify
- A cold reader could run the verification commands and continue without asking anything this session already answered.
Scope / hand-off
- Resuming spec execution -
spec-continue(the handoff names it in suggested skills).
CRITICAL
- Unverified facts (did it commit? did tests pass?) are checked with a command now, never handed off as guesses.
- Trim to what the repo cannot re-derive: decisions and intent first, mechanics last.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: ainova-systems
- Source: ainova-systems/intelligence-dev-packs
- 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.