Eric Lam
Community@voidful · Taiwan
👩🎓PhD@NTU Speech Lab. Formerly, Microsoft Research Intern.
Agent Skills by Eric Lam
Showing 61 vetted skills indexed across 3 GitHub repositories.
systematic-debugging
Diagnose bugs through a four-phase root cause investigation workflow.
documentation-review
Review documentation for accuracy against source code and detect doc-code drift.
git-workflow
Enforces atomic commits with structured messages and pre-commit checks for Rust projects.
code-review
Reviews code diffs for correctness bugs, regressions, missing tests, and risky assumptions.
performance-analysis
Diagnose slow execution, high memory usage, and excessive token consumption through systematic measurement.
writing-plans
Creates implementation plans with bite-sized tasks, exact file paths, and verification steps.
security-audit
Review code changes for prompt injection, path traversal, and command injection vulnerabilities.
refactoring
Guides incremental code restructuring while preserving behavior and passing tests.
architecture-review
Review proposed code changes against layered architecture rules and dependency direction constraints.
tdd
Enforces RED-GREEN-REFACTOR test-first development cycle for features and bugfixes.
launch
Automate VS Code and Code OSS UI interactions via Chrome DevTools Protocol.
anthropic-sdk-upgrader
Upgrades Anthropic SDK packages and migrates breaking API changes in TypeScript codebases.
init
Generates or updates agent instruction files like AGENTS.md for AI coding agents.
agent-customization
Create and debug VS Code agent customization files including instructions, prompts, agents, hooks, and skills.
troubleshoot
Diagnose unexpected chat agent behavior by analyzing JSONL debug session logs.
project-setup-info-local
Scaffolds complete project structures for VS Code extensions, Next.js, Vite, MCP servers, and Python projects.
create-prompt
Create reusable .prompt.md prompt files for repeatable AI assistant tasks.
project-setup-info-context7
Scaffolds complete project structures using context7 library documentation tools.
create-skill
Creates reusable SKILL.md files that package workflows into discoverable skills.
install-vscode-extension
Installs VS Code extensions by extension ID using the workbench command.
create-instructions
Creates .instructions.md files that codify project rules and coding conventions.
create-agent
Create custom .agent.md agent definitions for specialized jobs.
get-search-view-results
Retrieves current search results from the VS Code Search view via command.
create-hook
Create JSON hooks that enforce policies or automate agent lifecycle events.
Frequently Asked Questions About Eric Lam
FAQPage SchemaWhat tasks can I accomplish using voidful's skills?▼
You can debug root causes systematically, run TDD cycles, audit security and memory leaks, analyze V8 CPU profiles and heap snapshots, manage VS Code agent customizations, fix CI failures, and produce academic artifacts like LaTeX proofs, paper reviews, and experiment designs.
Who is the target audience for these skills?▼
VS Code core contributors and extension engineers benefit most, given skills for hygiene checks, accessibility, Azure Pipelines, and component fixtures. A secondary audience is academic researchers and PhD students needing paper writing, proof generation, and professor-fit analysis.
How do I install and run these skills?▼
Skills are invoked as named commands inside a compatible coding agent environment, typically by placing SKILL.md folders in the agent's skills directory. VS Code-specific skills run inside the VS Code repository and may require the gh CLI, agent-browser, or test scripts.
Are voidful's skills open source and free to use?▼
Yes. The engineering skills authored by Aixlarity carry the Apache-2.0 license, permitting free use, modification, and redistribution. Several are adapted from the Hermes Agent and obra/superpowers projects under the same permissive terms.
What prerequisites or dependencies do these skills require?▼
VS Code repo skills require the VS Code codebase, scripts/test.sh or test.bat, and the gh CLI for CI failure investigation. Launch and screenshot skills need agent-browser via Chrome DevTools Protocol. Academic skills need only LaTeX tooling for proof and paper output.