Handoff Package — Testing skill for Claude Code
Package an internal agent into a public-safe, reproducible handoff bundle — cleaned source, docs, examples, MIT licence, pinned deps, smoke test, optional GitHub push.
How to install Handoff Package
Installs to ~/.claude/skills/matthew2rs-claude-agent-handoff-handoff-package/SKILL.md
mkdir -p ~/.claude/skills/matthew2rs-claude-agent-handoff-handoff-package && curl -fsSL https://raw.githubusercontent.com/matthew2rs/claude-agent-handoff/HEAD/commands/handoff-package.md -o ~/.claude/skills/matthew2rs-claude-agent-handoff-handoff-package/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Handoff Package does
name: handoff-package description: Package an internal agent into a public-safe, reproducible handoff bundle — cleaned source, docs, examples, MIT licence, pinned deps, smoke test, optional GitHub push. argument-hint: " (e.g. 'agents/my-thing' or 'scripts/order-monitor.py')"
/handoff-package — internal agent to clean public bundle
A reusable process for turning an internal script/agent into a clean handoff bundle a stranger could clone, install, and run. Run inside Claud
Alternatives in Testing
- Check Package — Run full validation (build + lint + test + typecheck) on a package 1.1k ★
- AI Agents Public — Production-grade agent skills and Custom GPT prompts for ChatGPT, Claude Code, and Codex 82 ★
- Work — Pick up a GitHub issue and set up everything needed to start working on it: understand the issue, create a fea 77 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Public Browser
Token-efficient Chrome browser automation MCP server for AI agents. Direct CDP, a11y-tree refs, multi-tab, ser
Repro Issue
by rzykov - Creates reproducible test cases for GitHub issues, ensuring tests fail reliably and documenting cl
Claudebench
Stop arguing about prompts. Measure them. A reproducible, statistically-honest benchmark harness for Claude Co
Static Ads Skill
I tried using it with some models that are considered as weak rn (gemini 3.8) against latest claude and openai
Function Test
Act as a rigorous senior Perl SDET. Write a comprehensive set of white-box subtests in ./t/function.t to valid
Hoofy
Hoofy — AI development companion MCP server. Persistent memory, spec-driven development, adaptive change pipel
Related Agents
Perf Profiler
Agent-agnostic performance profiler. Measures web, API, bundle, and database performance using reproducible ev
Weavie Reviewer
Reviews a Weavie change set for correctness bugs and adherence to the project's strict standards (no fallbacks
Fallow
Run a codebase-intelligence audit (fallow) scoped to working-tree changes and report raw findings — dead code,