skill-tschuehly-skill-incubator-focus-handoff · by Install
$ agentstack add skill-tschuehly-skill-incubator-focus-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.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-tschuehly-skill-incubator-focus-handoff) 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
Focus handoff
Produce a mission brief for a fresh session to complete one bounded slice of the current work.
1. Pin the mission
Treat the user's invocation text as the intended slice. Infer the slice when only one interpretation fits the conversation. Ask one short question when different interpretations would change the task or file set.
Complete this step when the mission fits in one imperative sentence with a clear boundary.
2. Map the minimum context
Inspect the current conversation and workspace only far enough to identify:
- the exact files the fresh session should read or change;
- decisions, constraints, dependencies, or partial state that those files do not reveal;
- observable completion conditions.
Prefer source artifacts over retelling their contents. Account for current diffs when they affect the mission.
Complete this step when every selected item changes how the fresh session should act and the session can begin without broad rediscovery.
3. Write the mission brief
Return only one paste-ready prompt in a fenced block, using this shape:
Task
Relevant files
- —
Context from this session
-
Done when
- Keep the complete prompt at or below 220 words. Use the smallest sufficient file set, normally two to six entries and at most eight; tighten the mission or group a genuinely cohesive directory when more are needed. Include at most three context bullets and omit that section when the files contain all necessary context. Name symbols or sections when they provide a better starting point than a bare path. Replace sensitive values with the safe source from which the fresh session can retrieve them.
The brief is complete when a fresh agent knows exactly what to do, where to start, which prior facts matter, and how to recognize completion.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: tschuehly
- Source: tschuehly/skill-incubator
- 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.