代码评审
自动化代码审查与分析
TDD Green Phase - Make Tests Pass
anton-abyzov
Write minimal code to make failing tests pass. Use when saying "TDD green", "make tests pass", or "implement for tests".
harsh
htlin222
complete a comprehensive and brutally honest critical review of your manuscript. The review identifies major methodological flaws and areas where the work falls short of publication standards for a high-impact clinical journal.
sc-load
htlin222
Load and analyze project context, configurations, and dependencies. Use when starting work on a project, understanding configurations, or analyzing dependencies.
c-lang
htlin222
Write efficient C code with proper memory management and system calls. Use for C optimization, memory issues, or system programming.
novel-writer-workflow-guide
wordflowlab
"Use when user starts a novel project or asks how to organize their writing - guides through novel-writer's seven-step methodology and ensures proper workflow"
natural-dialogue-techniques
wordflowlab
"Use when writing dialogue scenes or when user asks about character conversations - provides techniques for natural, character-consistent dialogue that reveals character and advances plot"
mystery-novel-conventions
wordflowlab
"Use when user mentions mystery, detective, crime, or suspense-focused narrative - provides genre conventions, clue placement, and fair play principles for mystery writing"
fantasy-world-building
wordflowlab
"Use when user mentions fantasy, magic system, or world-building for fantastical settings - provides fantasy genre conventions, magic system design patterns, and world-building frameworks"
cloudbase-code-review
TencentCloudBase
"Code review and validation for CloudBase projects. After writing code for Web / miniprogram / CloudRun / cloud-function projects, call this skill to check for known pitfalls — auth guard misuse, missing database tables, RLS misconfiguration, storage domain setup, and SDK API misuse. Supports automated lint scripts (regex-based) + LLM semantic review."
corpus-maintenance
richlander
Use for authored-source correspondence corpus maintenance: verify the vendored CIVIL/EVIL snapshot for drift against upstream, re-harvest or re-pin it, run the offline benchmark, and decide when to advance the pin.
nightshift
richlander
The Nightshift orientation: what Nightshift is (Turnstile, Nightshift, Octoshift), the unit of work (an "order" = one landable PR), the five roles and what each owns, and how they coordinate through state rather than chat. Start here, then run nightshift skill <role> for your role's operating skill. Use this when asked what Nightshift is, how the roles fit together, or to get oriented before joining a shift.
dotnet-inspect
richlander
Find evidence instead of guessing for .NET packages, platform libraries, local assemblies, APIs, dependencies, and version-to-version API changes.
dotnet-inspect-deep-inspect
richlander
Run and interpret opt-in expensive validation lanes: full slow tests, IL round-trip sweep, corpus sensors, package discovery, validity scans, and analysis census.
deep-inspect-analysis
richlander
Use for opt-in Deep Inspect run triage: test lane failures, census artifacts, pinned-subset drift, and routing findings into issues or tracker updates.
dotnet-inspect-metadata
richlander
Query raw ECMA-335 assembly metadata — discover table and heap sections, inspect decoded rows and handles, address table or heap coordinates, and project bounded machine-readable results.
dotnet-inspect-signals
richlander
Surface a dependency's observable signals — provenance, compatibility, dependency risk, unsafe/PInvoke surface, artifact-text containment, and identifier confusion — to judge how much caution it warrants. Observations, not verdicts.
exploring-data
oaustegard
Exploratory data analysis using ydata-profiling. Use when users upload .csv/.xlsx/.json/.parquet files or request "explore data", "analyze dataset", "EDA", "profile data". Generates interactive HTML or JSON reports with statistics, visualizations, correlations, and quality alerts.
check-tools
oaustegard
Validates development tool installations across Python, Node.js, Java, Go, Rust, C/C++, Git, and system utilities. Use when verifying environments or troubleshooting dependencies.
browsing-bluesky
oaustegard
Browse Bluesky content via API and firehose - search posts, fetch user activity, sample trending topics, read feeds and lists, analyze and categorize accounts. Supports authenticated access for personalized feeds. Use for Bluesky research, user monitoring, trend analysis, feed reading, firehose sampling, account categorization.
inspecting-skills
oaustegard
Discovers and indexes Python code in skills, enabling cross-skill imports. Use when importing functions from other skills or analyzing skill codebases.
front-end-checklist
fabricioctelles
This skill should be used when a developer or team needs to review, validate, or audit front-end code before launching a website or HTML page to production. Triggers on requests such as "run the front-end checklist", "validate my front-end", "check my site before launch", or when the user asks for a structured review of HTML, CSS, JavaScript, accessibility, performance, security, or design quality.
Echo
simota
ãã«ã½ãï¼åå¿è ãã·ãã¢ãã¢ãã¤ã«ã¦ã¼ã¶ã¼çï¼ã«ãªãããUIããã¼ãæ¤è¨¼ããæ··ä¹±ãã¤ã³ããå ±åãã¦ã¼ã¶ã¼ä½é¨ã®åé¡ç¹çºè¦ã使ããããæ¤è¨¼ãå¿ è¦ãªæã«ä½¿ç¨ã
resume-ats-beater
fabricioctelles
Este skill deve ser usado para reescrever currículos com foco em compatibilidade ATS e impacto para recrutadores. Acionar em pedidos de otimização de currículo, melhoria para ATS, reescrita profissional do CV, adaptação para vaga-alvo, auditoria de compatibilidade ATS ou aumento de taxa de entrevista.
fund
coinbase
Add money to the wallet. Use when you or the user want to fund, deposit, top up, load, buy USDC, add funds, onramp, or get USDC. Also use when the wallet has insufficient balance for a send or trade operation, or when someone asks "how do I get USDC?"