AI Agent Skills

Software quality review and design guidance for any code: naming, cohesion, coupling, duplication, function size, dependency direction, and testability. Use whe

Defensive programming for any code: validating inputs at every boundary, checking for null and absent values, supplying safe fallbacks, catching and logging exc

Mistake-proofing for anything: code, config, a schema, a process, a runbook, a form. Use when someone says "poka-yoke this", "mistake-proof it", "make this hard

Grade a completed factory run (a worktree + its chat) against your standards, cold and adversarially, so the system learns. Squashes the session transcript into a compac…

Make Storybook stories deterministic for UI Verify so captures stop coming back "changed" without a real change (flaky diffs). Use when setting up story-level visual tes…

Make @uiverify/vitest (Vitest browser-mode) captures deterministic so component visual tests stop coming back "changed" without a real change (flaky diffs). Use when set…

Design and improve CLI, scripts, Make targets, and tool interfaces for AI coding agents. Use when a repository exposes repetitive shell workflows, noisy command output,…

AI编码同志精神纲领——"八荣八耻"。这是一套价值观体系， 旨在从根本上塑造 Claude Code、Codex 等 AI 编码智能体的工作品格与责任意识。 在以下场景中必须触发此技能：任何涉及代码生成、代码修改、接口调用、架构变更、 bug修复、重构、技术方案设计的任务。当 AI 准备动手写代码时，先完成精神自检， 让每一行代码都承载…

Use to design, implement, review, or test CLI tools, flags, config precedence, terminal UX, errors, and docs.

Stagnation detector + persona switcher. Triggers when the same file is edited 3+ times for the same issue, the same hypothesis fails 3+ times in mcp_think, the auditor r…

Trace every user-facing touchpoint (button, toggle, form submit) through its full state-change sequence to find defects that reading code line by line cannot se

Set up and configure the automated code-quality gate around a project — Biome or ESLint+Prettier, Husky Git hooks (pre-commit/pre-push), and lint-staged for JS/

Senior-engineer code review across five domains — Code Quality, Security, Performance, Blueprint/Spec Consistency, and Test Quality — plus conditional lenses au

Behavior-preserving refactoring workflow that actively rewrites code for clarity — extracting overlong functions, flattening deep nesting, consolidating duplica

Periodic garbage collection for Edho's own Claude Code environment (`~/.claude`): find redundant, stale, orphaned, or context-expensive items across skills, mem

Keep USER-FACING documentation honest against the current codebase — README, docs/CODEMAPS/*, architecture-as-markdown, public API docs. Generates/refreshes cod