Baixun.Huang
Community@huangbaixun · Shenzhen
Hadoop,Data warehouse,Kubernates,Docker,Microservices,APM, LLM,AIOps,AgenticOps
Agent Skills by Baixun.Huang
Showing 19 vetted skills indexed across 1 GitHub repositories.
harness:using-git-worktrees
Create an isolated Git worktree for feature work and run baseline tests.
harness:init
Generate project files and configurations for a Claude Code Harness.
harness:test-driven-development
Enforce RED-GREEN-REFACTOR cycles with failing tests before production code.
harness:systematic-debugging
Guide structured root-cause debugging with hypothesis testing and incident documentation.
harness:archive
Archive completed feature specs and verify documentation consistency with the codebase.
harness:canary
Generate a risk-based canary deployment runbook with rollback triggers and observability checks.
harness:dispatching-parallel-agents
Dispatch parallel agents to debug independent failure domains.
harness:using-harness
Route agent sessions to the correct Harness workflow skill by intent and timing.
harness:executing-plans
Execute implementation plans with review checkpoints and features.json scope validation.
harness:finishing-a-development-branch
Verify tests and present merge, PR, keep, or discard choices for Git branches.
harness:evolve
Trim and evolve CLAUDE.md rules to fit a 60-line budget.
harness:audit
Audit Harness frameworks and generate prioritized optimization plans.
harness:brainstorming
Convert product or engineering ideas into approved design specifications before implementation.
harness:writing-plans
Generate an end-to-end implementation plan from requirements with acceptance-criteria traceability and scope boundaries.
harness:requesting-code-review
Request structured pre-merge code reviews with task-specific reviewer context.
harness:receiving-code-review
Verify code-review feedback for technical correctness and constraint compliance before implementation.
harness:writing-skills
Write and validate process documentation skills using TDD and YAML frontmatter.
harness:verification-before-completion
Run precise proof commands before reporting completion with evidence.
harness:subagent-driven-development
Dispatch isolated subagents to execute implementation plan tasks with spec and code quality reviews.