write-agents-md
Use this skill when the user asks to "write AGENTS.md", "create AGENTS.md", "update AGENTS.md", "maintain agent docs", "set up CLAUDE.md", or needs to keep agent instructions concise. Enforces research-backed best practices for minimal, high-signal agent documentation.
review-code
>-
debug
>-
ailss-prometheus-agent
Obsidian vault notes (AILSS): search/summarize/edit (frontmatter, tags/keywords, typed links/backlinks, broken links; retrieval-first MCP; gated writes)
KOReader Plugin Development
This skill should be used when the user asks to "create a koreader plugin", "add a menu item", "create a widget", "save settings", "koreader ui", "lua widget", "koreader api", "dispatcher action", or is working on KOReader e-reader plugin development. Provides comprehensive guidance for KOReader's Lua plugin architecture.
diagnostic-meta-analysis
Teach meta-analysis of diagnostic test accuracy studies including sensitivity, specificity, SROC curves, and bivariate models. Use when users need to synthesize diagnostic accuracy data, understand SROC curves, or assess quality with QUADAS-2.
bayesian-meta-analysis
Teach Bayesian approaches to meta-analysis including prior specification, MCMC methods, and interpretation of posterior distributions. Use when users want to incorporate prior knowledge, need probabilistic interpretations, or are working with sparse data.
forest-plot-creation
Generate and interpret forest plots for meta-analysis visualization using R and the metafor package. Use when users need to create forest plots, understand visual representation of pooled effects, or interpret study weights and confidence intervals.
data-extraction
Extract and prepare study data for meta-analysis including effect size calculation, variance estimation, and handling missing data. Use when users need to convert reported statistics into analyzable format or calculate effect sizes from raw data.
socratic-teaching
Apply Socratic teaching methodology to guide users through meta-analysis concepts using questions, scaffolding, and discovery-based learning. Use when teaching meta-analysis to students or researchers who want to deeply understand the methodology.
trial-sequential-analysis
Teach Trial Sequential Analysis (TSA) for controlling type I and II errors in cumulative meta-analyses. Use when users need to assess if meta-analysis has sufficient information, want to avoid premature conclusions, or need to plan future trials.
r-code-generation
Generate R code for meta-analysis using the metafor package, including data preparation, model fitting, visualization, and sensitivity analyses. Use when users need executable R code for their meta-analysis workflow.
grade-assessment
Apply the GRADE framework to assess certainty of evidence in systematic reviews. Use when users need to rate evidence quality, create Summary of Findings tables, or understand the factors that affect confidence in effect estimates.
network-meta-analysis
Teach network meta-analysis (NMA) for comparing multiple treatments simultaneously. Use when users need to compare more than two interventions, understand indirect comparisons, or create network plots and league tables.
publication-bias-detection
Detect and assess publication bias in meta-analysis using funnel plots, Egger's test, trim-and-fill, and selection models. Use when users need to evaluate whether missing studies might affect their conclusions.
ipd-meta-analysis
Teach Individual Patient Data (IPD) meta-analysis methods for analyzing raw participant-level data from multiple studies. Use when users have access to original datasets, need to explore treatment-effect modifiers, or want to conduct time-to-event analyses.
heterogeneity-analysis
Assess and interpret between-study heterogeneity in meta-analysis using I², Q statistic, tau², and prediction intervals. Use when users need to evaluate consistency across studies, understand sources of variation, or decide if pooling is appropriate.
meta-analysis-fundamentals
Teach the foundational concepts of meta-analysis including effect sizes, statistical models, and evidence synthesis. Use when users ask about meta-analysis basics, want to understand pooled effects, or need guidance on fixed vs random effects models.
evolve
自我進化 Agent - 已遷移至原子化架構
ios-input-hints
Ensure iOS/iPadOS-friendly form inputs (keyboard type, inputmode, autocomplete, autocapitalize/autocorrect, enterkeyhint) when editing or reviewing UI forms in web apps. Use when adding or modifying form fields (Svelte/HTML/TSX/etc.), auditing form UX, or fixing mobile Safari keyboard issues.
ui-token-first
Enforce UI token usage for Espresso Engineered frontend work. Use when editing Svelte/SvelteKit UI, styling typography, voice lines, headers, cards, surfaces, or layout so styles come from frontend/src/lib/ui tokens instead of app.css or ad-hoc CSS.
backend-build-check
Ensure backend build readiness for Espresso Engineered. Use when backend code/config changes are made or when a feature/task is wrapping up to suggest running `npm run build:backend` (and tests only if requested).
design-system-token-enforcer
Enforce design system token usage in espresso-engineered-1 frontend UI work. Use when creating or editing Svelte components, layout sections, typography, spacing, colors, surfaces, or buttons, especially when introducing new UI components or section headers.
translate-image
Translate text in images, extract text via OCR, and remove text using TranslateImage AI. Use when user says 'translate image', 'OCR image', 'extract text from image', 'remove text from image', 'manga translate', or wants to process images with foreign-language text.
plan-replayer-testing
Expertise in adding new test cases for the TiDB plan replayer. Use when the user provides a plan replayer zip file and wants to create a new test.
context-management
Use for projects, tasks, or code that involve context engineering and context management for AI agents: keep prompt prefixes stable for KV-cache, use append-only context, prefer tool masking over tool removal, offload large observations into filesystem memory, recite goals/todos to control attention, preserve errors for recovery, and avoid few-shot pattern lock-in. Use when building or debugging agent loops, prompt/context schemas, memory strategies, or tool-availability policies.
bugfix
Fix software bugs with root-cause analysis, minimal diffs, regression tests, and a mandatory self-check loop. Use for general bugfix work that is not covered by a more specific domain skill.
tidb-profiler-analyzer
Processes and analyzes TiDB profiler zip packages (CPU or heap) for components like TiDB, TiKV, PD, or TiFlash. It unzips, aggregates the profiler data, and uses `go tool pprof` to report on the most time-consuming functions (CPU) or highest memory allocations (heap).
pr-review-helper
Gather PR review context: all comments (including review suggestions), diff context, and CI status; download GitHub Actions logs on failures. Prefer GitHub MCP for reads, fall back to gh CLI when needed.
tidb-doc-finder
TiDB-specific documentation lookup guided by this repo's llms.txt hub: read llms.txt, pick the best linked source (tidb-dev-guide llms-full.txt, TiDB user guide llms.txt, or Uber Go style guide), fetch it, then search within it to answer with precise references. Use when asked to find docs, research, or provide doc-grounded answers about TiDB development or usage.
tidb-optimizer-bugfix
Fix TiDB optimizer bugs with minimal diffs, hypothesis-driven validation, and regression tests. Use the bundled issue precedents only to avoid re-fixing already solved bugs or inspect suspect historical fixes.
containerization
Docker and Kubernetes deployment patterns for Elixir/Phoenix applications
distributed-systems
Distributed systems patterns for BEAM/OTP including clustering, supervision, and multi-region deployment
liveview-patterns
Phoenix LiveView UI and real-time feature patterns
nx-patterns
Nx and Livebook patterns for machine learning in Elixir
elixir-architect
Use when designing or architecting Elixir/Phoenix applications, creating comprehensive project documentation, planning OTP supervision trees, defining domain models with Ash Framework, structuring multi-app projects with path-based dependencies, or preparing handoff documentation for Director/Implementor AI collaboration
graphql-patterns
GraphQL patterns with Absinthe framework for Elixir/Phoenix applications
observability
Telemetry, metrics, tracing, and observability for Elixir/BEAM applications
otp-patterns
Implements OTP design patterns including GenServer, Supervisor, and Application behaviors.
api-versioning
API versioning strategies including URL-based, header-based, and breaking change management
data-pipeline
GenStage, Broadway, and Flow for Elixir data pipelines
nerves-patterns
Nerves embedded development patterns for Elixir/Nerves systems
test-generation
Generates comprehensive Elixir tests using ExUnit following TDD principles.
elixir-scribe
Single Responsibility Code in Self-Documented Folder Structure
resilience-patterns
Resilience and error recovery patterns including circuit breaker, retry strategies, and graceful degradation
elixir-guidelines
Official Elixir community standards, naming conventions, and best practices
git-workflow
Git and GitHub workflow automation skills for OpenCode agents
ai-orchestration
LLM keyring management, multi-provider support, and AI agent orchestration
ecto-query-analysis
Analyzes Ecto queries for N+1 problems, missing preloads, and performance issues.
performance-profiling
Performance profiling and optimization for Elixir/BEAM applications
Page 1410 of 1712 · 85581 results
