@liuzhengdongfortest

cs-issue routes bug reports through a three-stage workflow (report, analyze, fix) or fast-tracks simple issues with single fix-notes. decides which sub-skill to invoke based on existing artifacts in the issue directory.

browser-bridge executes javascript in real chrome tabs and returns structured results (dom diffs, transient text, rendered evidence). operates via cli commands (exec, scan, navigate, screenshot, evidence) backed by a websocket-connected chrome extension.

cs-refactor-ff enables fast-track refactoring for low-risk, single-function changes by skipping design docs and checklists, requiring only three entry checks (behavior preservation, scope <100 lines, test coverage) and validation through test runs.

cs-refactor guides code optimization through a gated three-phase process (scan, design, apply) that maintains behavior equivalence while improving structure, performance, or readability. it routes away architectural changes, new features, and bugs to dedicated workflows.

cs-guide prescribes writing task-oriented dev-guide and user-guide documents for external readers, distinguishing these from spec artifacts. establishes dual-track templates, yaml frontmatter convention, and integration points with feature acceptance and design workflows.

cs-issue-analyze reads problem reports and codebase to identify root causes, assess impact scope, and propose 2-3 repair strategies for user approval before implementation. it enforces code inspection over speculation and defers execution decisions to the user.

cs-issue-report captures user-reported problems into structured issue records and routes them to fast-track or standard analysis based on code inspection. focuses on observable symptoms, defers root cause analysis to stage 2.

cs-issue-fix executes targeted bug repairs following confirmed root cause analysis, enforcing scope discipline and verification before documenting fixes in {slug}-fix-note.md. two entry paths: standard from analysis stage, fast-track from report with oral confirmation.

cs-decide formalizes tech selections, architecture decisions, constraints, and coding conventions into permanent decision records. guides users through identification, extraction, drafting, and archival with explicit supersede vs update semantics.

cs-learn captures pitfalls and best practices into searchable learning documents via two tracks. triggered by workflow completion, user prompts, or one-off engineering problems. deduplicates against existing docs before archiving.

cs routes open-ended codestable requests to specialized sub-skills after scanning repo state and user intent. it diagnoses whether users need onboarding, brainstorming, feature work, bug fixes, or knowledge capture.

cs-explore codifies repository investigation into searchable evidence trails. it structures code reading into question/module-overview/spike types, enforces evidence-first documentation with file:line citations, and prevents exploratory work from becoming throwaway analysis.

cs-req maintains capability vision documents under .codestable/requirements/ across three modes (draft, backfill, update), triggered at design inception or acceptance completion to separate requirement intent from implementation detail.

cs-feat-ff streamlines small feature work by querying codestable knowledge before implementation, skipping design and checklist phases, then recording outcomes in a minimal note for traceability.

generates reference documentation for library public surfaces (components, functions, commands) by reading source code directly, with checklist tracking for single or batch entries. focuses on extracting type signatures and defaults rather than usage patterns.

cs-arch maintains a living, read-first system map in .codestable/architecture/ documenting current state across three modes (update, check, backfill). triggered by architecture refresh requests, the skill enforces that design stays grounded in implemented code rather than speculative futures.

cs-note appends project micro-knowledge to .codestable/attention.md via fixed sections, capturing short-lived-but-essential facts like build steps, service startup requirements, and command aliases that ai needs on every launch.

cs-feat routes new feature requests to appropriate sub-skills (brainstorm, design, fastforward, implement, acceptance) based on artifact state. pure router, no code or doc generation.

cs-feat-impl orchestrates feature implementation in paradigm-dimensional steps derived from design phase, enforcing checkpoint discipline through mandatory plan validation, reflection checks, and structured reporting to prevent scope creep and undocumented decisions.

cs-trick prescribes a workflow for capturing reusable code patterns, library usage, and techniques into a searchable reference indexed by type (pattern/library/technique). emphasis on code archaeology before documentation.

系统审计——从代码中主动发现 bug 隐患、安全漏洞、性能问题、可维护性债务和架构偏离，产出批量发现清单。触发：用户说"审查系统"、"审计代码"、"扫描问题"、"找找 bug"、"有什么可以优化的"。

把新仓库或有零散文档的仓库接入 CodeStable 体系，两条路径自动判断：空仓库从零搭骨架，已有文档走审计 + 迁移映射。触发：用户说"在这个项目里用 CodeStable"、"搭 CodeStable 结构"、"初始化 CodeStable"、"迁移到 CodeStable"。

feature 流程阶段 3——验收闭环：对照 design 核实现 + 回写 architecture / requirement / roadmap，最后产出 {slug}-acceptance.md。触发：用户说"功能写完了验收一下"、"做最后检查"、"准备 merge"、"出验收报告"。前置依赖…

想法还模糊时的讨论入口，做分诊后路由到 feature-design / feature-brainstorm / roadmap。AI 是思考伙伴不是记录员。触发：用户说"有个想法还没想清楚"、"先 brainstorm 一下"、"聊一聊这块"、"方向还在摇摆"。不处理 bug 和重构。

把"大到塞不进单个 feature"的需求做成完整事前规划：概设 + 接口契约 + 子 feature 拆解清单，放在 `.codestable/roadmap/{slug}/`。两种模式 new / update。触发：用户说"我想要一个 X 系统"、"帮我把这块需求拆一下"、"开一份 roadmap"，或…

feature 流程阶段 1——为新功能起草 {slug}-design.md 作为后续实现和验收的唯一输入，拍板后抽出 checklist。触发：用户说"开始设计方案"、"写 design doc"、"准备实现 XX"，前提是已知道做什么、为谁、怎么算成功。