core-handoff
Shared handoff protocol for cross-agent requests, artifact transfer, blockers, and escalation.
Skill by LiXin97
Chalk Labs
Need help deploying core-handoff?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/lixin97-core-handoff
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/core-handoff
What's inside
- Skill name
core-handoff- Description
- Shared handoff protocol for cross-agent requests, artifact transfer, blockers, and escalation.
- License
- Apache-2.0
- Instructions
- 34 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Core Handoff
Every cross-agent request should include:
1. the artifact or file path
2. the exact request
3. the success condition
4. the blocking question, if any
5. the downstream dependency, if any
## Message Pattern
Use the canonical shared message directory from your AGENTS/CLAUDE instructions when one agent needs another to:
- review an artifact
- unblock a decision
- inspect a result
- take over a next step
Name the file `{from}_to_{recipient}_{timestamp}_{type}.md` and include frontmatter with:
```yaml
---
from: <sender>
to: <recipient|all>
type: <instruction|question|review|notification>
timestamp: <ISO 8601>
status: unread
---
```
Keep the request narrow enough that the receiver can act without re-deriving the objective.From LiXin97/agora-lab, Apache-2.0.
More from LiXin97/agora-lab
- 0.505score
shared-references
LiXin97
Shared reference library for reviewer independence, evidence standards, meeting quality, handoff discipline, writing principles, venue checklists, and…
SkillDFreshness: D★ 51Claude Code +9 - 0.502score
student-analyze-results
LiXin97
Convert metrics into supported claims, anomalies, and next-step decisions.
SkillDFreshness: D★ 51Claude Code +9 - 0.502score
student-experiment-design
LiXin97
Design experiments with variables, baselines, ablations, resources, and success criteria.
SkillDFreshness: D★ 51Claude Code +9 - 0.502score
student-idea-refine
LiXin97
Turn a broad direction into a sharp, testable research question with clear failure modes.
SkillDFreshness: D★ 51Claude Code +9 - 0.502score
student-literature
LiXin97
Build a strong literature map with baselines, gaps, and concrete research opportunities.
SkillDFreshness: D★ 51Claude Code +9 - 0.502score
student-meeting
LiXin97
Student overlay for prepare, challenge, and response behavior in meetings.
SkillDFreshness: D★ 51Claude Code +9 - 0.502score
student-write-paper
LiXin97
Draft paper sections that stay aligned with the actual evidence and do not overclaim.
SkillDFreshness: D★ 51Claude Code +9 - 0.502score
core-meeting
LiXin97
Shared group-meeting protocol covering phases, artifact locations, and readiness rules.
SkillDFreshness: D★ 51Claude Code +9 - 0.502score
supervisor-meeting
LiXin97
Supervisor overlay for calling, steering, and closing meetings.
SkillDFreshness: D★ 51Claude Code +9 - 0.502score
core-kanban
LiXin97
Shared Research task board protocol for task state, review gates, artifact linkage, and escalation.
SkillDFreshness: D★ 51Claude Code +9 - 0.502score
student-run-experiment
LiXin97
Execute experiments reproducibly and publish usable results instead of private logs.
SkillDFreshness: D★ 51Claude Code +9 - 0.497score
supervisor-tasking
LiXin97
Convert directions into high-quality, reviewable tasks for the Research task board.
SkillDFreshness: D★ 51Claude Code +9
Signals
- Stars
- 51
- Forks
- 8
- Open issues
- 1
- Last commit (this folder)
- Apr 11, 2026 (7 months ago)
- Last release
- Apr 18, 2026 (6 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- Apache-2.0
- Repository
- github.com/LiXin97/agora-lab
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from LiXin97
- 0.505score
shared-references
LiXin97
Shared reference library for reviewer independence, evidence standards, meeting quality, handoff discipline, writing principles, venue checklists, and…
SkillDFreshness: D★ 51Claude Code +9 - 0.502score
student-analyze-results
LiXin97
Convert metrics into supported claims, anomalies, and next-step decisions.
SkillDFreshness: D★ 51Claude Code +9 - 0.502score
student-run-experiment
LiXin97
Execute experiments reproducibly and publish usable results instead of private logs.
SkillDFreshness: D★ 51Claude Code +9 - 0.502score
core-kanban
LiXin97
Shared Research task board protocol for task state, review gates, artifact linkage, and escalation.
SkillDFreshness: D★ 51Claude Code +9 - 0.502score
core-meeting
LiXin97
Shared group-meeting protocol covering phases, artifact locations, and readiness rules.
SkillDFreshness: D★ 51Claude Code +9 - 0.502score
student-experiment-design
LiXin97
Design experiments with variables, baselines, ablations, resources, and success criteria.
SkillDFreshness: D★ 51Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get core-handoff running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
core-handoff skill. Agent Mart. https://agentmart.dev/skills/lixin97-core-handoff (last updated 2026-10-24)