Loading...
Loading...
Found 20 Skills
Audit an ENTIRE codebase with multiple agents in parallel — map the repo, partition it into review slices, fan out one (or more, multi-lens) reviewer subagent per slice, reduce with a cross-cutting/architecture critic + a completeness check, then triage, fix, and report with an honest coverage ledger. Use when asked to 'audit the whole codebase', 'full security/quality review of the repo', 'review the entire project', 'do a deep/comprehensive code audit', 'scan everything for bugs or vulnerabilities', when onboarding/inheriting an unfamiliar repo, or for a periodic deep sweep. Whole-repo scoped and scales agent count to repo size — NOT a diff review (for changed lines use dual-agent-review).
Diff the codebase against existing PRODUCT horizons; do not invent a backlog.
Survey an existing codebase for the structural change worth making, whether shallow interfaces, adapter sprawl, poor locality, or untested coupling, then rank the candidates, crown one, and write it up as a reviewable proposal. Use when the user says "where should I refactor", "what's wrong with this codebase's structure", "find refactoring opportunities", "this code is hard to change", "improve our architecture", "audit the module boundaries", or "/refactorkit". It proposes and never edits code.
Run the ECC engineering process retroactively against an existing project slice. Audit current state, reconstruct past decisions, produce a four-axis gap register (thinking, coding practice, missing features, technology selection), then execute fixes forward through the plan-TDD-review pipeline. Use when adopting ECC mid-project, taking over an inherited codebase, or asking what was missed and what would have been built differently from day one.
Use when someone asks what is true of a whole project: finished, half-built, broken, unexplored ('project audit', 'аудит проекта'). Discovers the project, runs probes, reads production evidence, leaves a JSON sidecar, an HTML report on request. Read-only: proposes board rows, commits nothing. Not for: one deliverable inside a run, a diff review, a skill's construction; 'без диагностики' opts out.
Kiểm 'phủ hết' bằng diff với BỀ MẶT THẬT đọc từ code (trang, route, module API, lệnh CLI, cron, tool MCP) thay vì đếm số artefact: liệt kê bề mặt tất định ra surface.json @commit, giữ sổ phủ coverage.json (mục → artefact giải thích hoặc loại trừ có lý do), gác bằng test đỏ khi có mục mới chưa phủ, báo 'N/M mục'. Gọi khi user hỏi 'đã phủ hết chưa', 'có đủ chưa', 'tương ứng hết chức năng chưa', 'vét cạn', 'không lọt chức năng', 'coverage', 'sổ chức năng', khi sinh bài học/flow/docs cho một codebase, hoặc khi sắp báo một con số (19 bài, 18 flow) như thể đã đủ.
Reviews a change, a session or a whole codebase against every skill in this collection and returns one ranked, numbered report.
Extract a comprehensive design system (DESIGN.md) directly from frontend source code — React, Vue, Svelte, Angular, plain HTML/CSS, or any web framework. Analyzes component files, stylesheets, Tailwind configs, theme definitions, and design tokens to produce a rich, Stitch-compatible design system document. Use this skill whenever the user wants to reverse-engineer a design system from an existing codebase, audit the visual language of a project, extract design tokens from source files, or understand the styling patterns in a frontend repo — even if they just say "what does this app look like?" or "pull out the design from this code."