Pick a design language from a categorized offline catalog of 151 entries (84 brand-inspired DESIGN.md files and 67 generic styles), write it as DESIGN.md in the project root, then implement or restyle production UI from that file and verify it in a running…
Researcher-profile-driven paper intake and literature workbench for academic workflows. Use whenever the user wants to skim, deep-read, card, compare, synthesize, map research gaps, or build a literature review from papers, arXiv/AlphaXiv links, DOIs, PDFs,…
Write, debug, and validate ast-grep structural code search rules. Use for syntax-aware code search, AST pattern matching, structural refactor discovery, or searches plain text tools like rg can miss — functions with particular descendants, calls inside…
Audit and improve the Claude Code context layer — CLAUDE.md guidance files, .claude/rules/ path-scoped rules, and companion code_map.md navigation maps — against Claude 5 context-engineering rules (judgement over rules, progressive disclosure, no cross-layer…
Use when the user explicitly asks to coordinate worker agents in Herdr, delegate tasks across Herdr panes, or collect and compare their results; 支持 Herdr 多 Agent 编排、分工、交叉核验和结果收集。Do not use for ordinary local subagents, simple pane inspection, documentation…
Use when the user needs text or regex content search with ripgrep: composing rg commands, choosing flags, glob/type filtering, multiline or PCRE2 searches, pipeline output, grep-to-rg migration, or diagnosing why rg missed a file (gitignore, hidden, binary…
Use when a coding agent needs to run Python code, modules, one-liners, tools, tests, or standalone scripts through uv, or create and maintain PEP 723 scripts with uv init/add/remove --script. Avoid direct python/python3 shell entrypoints.
Independent pre-merge review of a git diff, PR, or named files. Use when the user asks to review a PR, inspect current git changes, or hunt functional regressions, missed scenarios, wrong assumptions, concurrency bugs, and test gaps as an independent reviewer…
Run a maintainability and structure review focused on abstraction quality, branching complexity, file growth, canonical ownership, duplication, and refactoring opportunities. Use when the user asks for code quality review, maintainability review, 代码质量审查,…
Implement safe, behavior-preserving code refactors after inspecting the existing project. Use when the user asks to refactor, split large files, extract methods, reduce duplication, rename, clean dead code, or says 重构代码, 拆分模块, 提取方法, 优化命名, 优化注释, 删除未调用代码. For…
Use when the user asks an Agent inside Herdr to start Codex for an independent review through herdr-orchestra, or invokes codex-review with established Herdr task context; 支持在 Herdr 中让 Codex 审查改动、提交、文件或计划。Do not use for generic review, direct non-Herdr Codex…
Use when the user asks where tests live, which test directory holds them, how complete the tests are, or which tests are not collected by CI. 测试放在哪、测试目录、测试完善程度、哪些测试没进 CI. Inventory test location, runner collection, and completeness. Do not use for a diff…
Use when a Rust or Cargo build is slow and the user wants it diagnosed or sped up: profiling compile times with cargo --timings or -Zself-profile, finding whether the bottleneck is dependencies, codegen/LLVM, linking, or one oversized crate, and applying…
Modify the Beautiful Mermaid live editor itself rather than writing ordinary Mermaid diagrams. Use when the task mentions the Beautiful Mermaid repo, editor.ts, generated editor.html, config panel, themes or dark mode, zoom, PNG/SVG export, sample presets, or…
Write or update technical documentation grounded in the real codebase. Use when the user asks for README, API docs, architecture guides, user guides, CONTRIBUTING docs, migration notes, or JSDoc/code comments, or wants technical docs rewritten into natural…
Chinese public-writing editor for AI/tech posts, X/Twitter threads, product notes, and public technical essays. Use for 去AI味, 改得像本人, 写推特post, 精修中文AI技术文章 — removes AI-flavored shells while preserving facts, judgment, technical terms, and author voice. Not for…
Author Typst slide decks with the Touying package. Use when creating or editing .typ presentations: applying or building Touying themes (e.g. metropolis), turning headings or #slide into slides, incremental reveals (#pause, dynamic content), speaker notes via…
Initialize GitHub repository configuration from vetted upstream templates. Use when setting up repository automation, issue and PR templates, CI workflows, or baseline GitHub project files for a new or existing repo.
Register-aware academic language polisher for English journal articles and Chinese doctoral dissertations: removes AI-writing tells while keeping academic norms. Use whenever the user wants to polish, 降AI味, 润色, or norm-check an academic draft, paper section,…
Create, advise on, or audit academic figures in four modes. advise profiles the data and recommends a chart type when none is fixed. journal-spec creates or reviews publication-ready figures for journal submission specs using matplotlib, seaborn, plotly,…
Use when the user explicitly asks to use Goal mode or to author, save, or manage a Goal for Claude Code, Codex, Grok Build, Oh My Pi, or Kimi Code. Requests may say `/goal`, Goal 指令, 目标指令, Goal 模式, "用 Goal 模式完成", or "写成 Codex 目标指令"; the literal command is not…
Independent review of Trellis task planning artifacts. Treats the selected task and its recursive current or archived children as one review scope, verifies repository claims and path:line citations against code, traces every acceptance-criterion clause to a…
Analyze how an existing agent skill was used in past Claude Code, Grok, Codex, and Oh My Pi conversations. Use when the user asks to 分析某 skill 的使用情况, 这个 skill 用着有什么问题, 根据历史对话反馈改进 this skill, review skill sessions, or write a session-review report. Writes…
Safely orchestrate Conventional Commits for staged Git changes, or all working-tree changes when the user explicitly asks to include everything. Use when asked to write a commit message, split staged or working-tree changes, organize a messy index, or draft…
Use when the user wants a read-only disk/storage analysis on macOS or Windows: 磁盘满了, C盘满了, 空间不够, 存储分析, 占空间, 清缓存, storage analysis, disk cleanup, or Chinese 内存满了 when they mean disk space. Scans known hotspots, classifies cache vs user data vs keep, and writes…
Use when the user wants to categorize, sort, organize, or suggest renames for files in a local folder such as Downloads, or for files that share one parent directory. Builds a review plan with stable file-family categories, optional whitelist, project-root…
Manage isolated Git worktrees under one repository convention root. Create a new-branch worktree, list trees, remove an owned tree, or show prune candidates after authorization. Before any git worktree add, ensure the repo .gitignore excludes the convention…
Draft an evidence-grounded literature review or related-work section from both a user-provided idea, argument, reasoning outline, 思路, 框架, or 论证主线 and one or more supplied BibTeX .bib files. Use when the job is to write 文献综述, 综述, or 相关工作 while preserving…
Create self-contained HTML artifacts (single-file by default, split bundles when oversized) for complex, reviewable, or shareable work outputs. Use for an HTML artifact, browser-viewable report, implementation plan, PR/code-review report, dashboard, or mini…
Audit and safely clean Windows dev-process trees and UWP app background-task pileups, including orphan npm/npx, leaked Playwright MCP workers, workspace dev servers, IDE services, Phone Link, Dolby Access, and backgroundTaskHost.exe. Use for Task Manager…