菜单
这个仓库中的 skills
SkillsMP 已收集 merceralex397-collab/meta-skill-engineering 中的 606 个 Skill。打开任一 Skill 可查看来源和详情。
merceralex397-collab/meta-skill-engineering已展示 40 / 606 个已收集 Skill。
Designs database entities, relationships, constraints, and migration-safe schema evolution. Use when creating tables, defining foreign keys, choosing primary key strategies (UUID/ULID/auto-increment), adding indexes, implementing soft deletes, designing audit…
原文语言：英语
Covers schema design, migrations, query patterns, and persistence technology choices for the data layer. Trigger on 'schema design', 'database migration', 'choose database', 'add table', 'expand-contract migration'. DO NOT USE for query performance tuning…
原文语言：英语
Guides PostgreSQL schema design, index selection (B-tree/GIN/GiST), query optimization with EXPLAIN ANALYZE, connection pooling via pgbouncer, migration workflows (alembic/flyway/dbmate), transaction isolation levels, VACUUM tuning, table partitioning, and…
原文语言：英语
Guides SQLite configuration (WAL mode, PRAGMA tuning), concurrency patterns, file locking, application-level migrations, JSON1/FTS5 extensions, and backup strategies. Use when configuring SQLite for embedded apps, test harnesses, single-writer services, CLI…
原文语言：英语
Integrate Firebase Auth, Firestore, and FCM with React Native apps. Use when setting up Firebase in React Native, implementing auth flows with @react-native-firebase, reading/writing Firestore data with real-time listeners, or configuring push notifications…
原文语言：英语
Build reusable Shiny modules with proper namespace isolation using NS(). Covers module UI/server pairs, reactive return values, inter-module communication, and nested module composition. Use when extracting a reusable component from a growing Shiny app,…
原文语言：英语
Create R-based pictogram glyphs for skill, agent, or team icons in the visualization layer. Covers concept sketching, ggplot2 layer composition using the primitives library, color strategy, registration in the appropriate glyph mapping file and manifest,…
原文语言：英语
Create a Quarto document for reproducible reports, presentations, or websites. Covers YAML configuration, code chunk options, output formats, cross-references, and rendering. Use when creating a reproducible analysis report, building a presentation with…
原文语言：英语
Scaffold a new R package with complete structure including DESCRIPTION, NAMESPACE, testthat, roxygen2, renv, Git, GitHub Actions CI, and development configuration files (.Rprofile, .Renviron.example, CLAUDE.md). Follows usethis conventions and tidyverse…
原文语言：英语
Create interactive maps, elevation profiles, and spatial visualizations from GPX tracks, waypoints, or route data using R (sf, leaflet, tmap) or Observable (D3, deck.gl). Covers data import, coordinate system handling, map styling, and export to HTML or image…
原文语言：英语
Improve an existing R-based pictogram glyph for the visualization layer. Covers visual audit of the current glyph, diagnosis of specific issues (proportions, readability, glow balance), targeted modifications to the glyph function, re-rendering, and…
原文语言：英语
Generate publication-ready statistical tables using gt, kableExtra, or flextable. Covers descriptive statistics, regression results, ANOVA tables, correlation matrices, and APA formatting. Use when creating descriptive statistics tables, formatting regression…
原文语言：英语
Manage R package dependencies using renv for reproducible environments. Covers initialization, snapshot/restore workflow, troubleshooting common issues, and CI/CD integration. Use when initializing dependency management for a new R project, adding or updating…
原文语言：英语
Implement preference-based alignment using DPO, IPO, KTO, or ORPO with TRL's DPOTrainer. Covers preference data formatting (prompt/chosen/rejected), beta tuning, loss variants, and reference model management. Use when aligning a fine-tuned LLM with human or…
原文语言：英语
Diagnose and repair broken agent processes — doom loops, workflow stalls, status-over-evidence routing, context rot, conflicting instructions. Use when the user says "agent keeps failing", "workflow stalled", "process broken", "doom loop", "agent repeating",…
原文语言：英语
Simulate stochastic processes (Markov chains, random walks, SDEs, MCMC) with convergence diagnostics, variance reduction, and visualization. Use when generating sample paths for estimation, prediction, or visualization; when analytical solutions are…
原文语言：英语
Audits, designs, and restructures spreadsheet workbooks — validates data quality, traces and fixes formulas, designs pivot tables, and documents cross-sheet architecture. Trigger: "audit this spreadsheet", "fix this formula", "pivot table design", "data…
原文语言：英语
Use when tasks involve creating, editing, analyzing, or formatting spreadsheets (`.xlsx`, `.csv`, `.tsv`) with formula-aware workflows, cached recalculation, and visual review.
原文语言：英语
Parse and validate PILES (Puzzle Input Line Entry System) notation for specifying piece fusion groups in jigsawR. Covers syntax validation, parsing into group lists, plain-language explanation, adjacency verification against puzzle results, and round-trip…
原文语言：英语
Version machine learning datasets using DVC (Data Version Control) with remote storage backends, build reproducible data pipelines with dependency tracking, integrate with Git workflows, and ensure data lineage for model reproducibility. Use when versioning…
原文语言：英语
Write roxygen2 documentation for R package functions, datasets, and classes. Covers all standard tags, cross-references, examples, and generating NAMESPACE entries. Follows tidyverse documentation style. Use when adding documentation to new exported…
原文语言：英语
Create R package vignettes using R Markdown or Quarto. Covers vignette setup, YAML configuration, code chunk options, building and testing, and CRAN requirements for vignettes. Use when adding a Getting Started tutorial, documenting complex workflows spanning…
原文语言：英语
Generate Excel (.xlsx) workbooks programmatically using openpyxl or xlsxwriter — create multi-sheet workbooks, apply cell formatting and conditional styles, insert formulas and charts, set print areas, and handle large datasets efficiently. Use when producing…
原文语言：英语
Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting,…
原文语言：英语
Plans and executes large refactors or migrations in bounded Strangler Fig stages with rollback awareness at each phase. Trigger on "migrate from X to Y", "strangler fig", "framework migration", "legacy replacement", "incremental migration". Do NOT use for…
原文语言：英语
Persistent browser and Electron interaction through `js_repl` for fast iterative UI debugging.
原文语言：英语
Use when the task requires automating a real browser from the terminal (navigation, form filling, snapshots, screenshots, data extraction, UI-flow debugging) via `playwright-cli` or the bundled wrapper script.
原文语言：英语
Run the jigsawR test suite via WSL R execution. Supports full suite, filtered by pattern, or single file. Interprets pass/fail/skip counts and identifies failing tests. Never uses --vanilla flag (renv needs .Rprofile for activation). Use after modifying any R…
原文语言：英语
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
原文语言：英语
Trigger — "verify this works", "run the tests", "check acceptance criteria", "QA this change", "validate the implementation", "does this pass", "regression check", "test coverage gaps". Skip — if the task is writing code (use an implementer skill), reviewing…
原文语言：英语
Test Shiny applications using shinytest2 for end-to-end browser tests and testServer() for unit-testing module server logic. Covers snapshot testing, CI integration, and mocking external services. Use when adding tests to an existing Shiny application,…
原文语言：英语
Choose and structure appropriate testing layers for the current stack — unit, integration, e2e, snapshot, or property-based. Trigger on "testing strategy", "add tests", "test pyramid", "test coverage", "flaky tests", "property-based testing", or "test…
原文语言：英语
Test React apps with Testing Library, MSW for API mocking, and Vitest. Use when writing component tests with Testing Library, mocking API calls with MSW, setting up Vitest for a React project, or testing hooks and async behavior. Do not use for E2E browser…
原文语言：英语
Extract maximum value from existing code — performance optimization, API surface refinement, and dead weight elimination. The art of turning base code into gold through systematic identification and amplification of value-bearing patterns. Use when optimizing…
原文语言：英语
Remove dead code, unused imports, fix lint warnings, and normalize formatting across a codebase without changing business logic or architecture. Use when lint warnings have piled up during rapid development, unused imports and variables clutter files, dead…
原文语言：英语
Perform a findings-first code review that prioritizes bugs, regressions, missing tests, unsafe changes, and misleading assumptions over summary fluff. Use when the user asks for a review of code, a patch, a PR, or a diff, especially when they want concrete…
原文语言：英语
Designs exception hierarchies, user-facing error formats, PII redaction, and structured logging conventions. Trigger on 'error handling strategy', 'exception hierarchy', 'structured logging', 'API error format', 'error boundary'. DO NOT USE for…
原文语言：英语
Maps current state against desired state to identify missing pieces, incomplete work, and unaddressed requirements. Trigger — "what's missing", "gap analysis", "compare current vs target", "what else do we need". Skip when the target state is undefined or…
原文语言：英语
Help address review/issue comments on the open GitHub PR for the current branch using gh CLI; verify gh auth first and prompt the user to authenticate if not logged in.
原文语言：英语
Establishes measurable performance baselines, regression thresholds, and CI gates using concrete profiling and benchmarking tools. Trigger on "performance baseline", "benchmark", "latency regression", "profiling", "load test". Do NOT use for…
原文语言：英语