Code Review
Automated code review and analysis
clabcraw
by clabcraw
Play heads-up no-limit poker on the Clabcraw arena for USDC
bundle-import-auditor
by handxr
Audit JavaScript/TypeScript imports for bundle size bloat, heavy dependencies with lighter alternatives, wildcard imports that break tree-shaking, barrel file re-exports, duplicate imports, code-splitting opportunities, and import hygiene issues. Use when reviewing frontend bundle size, debugging slow page loads, auditing import patterns, or when a user asks to check their imports, find heavy dependencies, optimize bundle size, detect tree-shaking blockers, or clean up import statements. Triggers on tasks involving .js/.jsx/.ts/.tsx/.mjs/.mts files with ES module imports or require() calls.
agent-guardrails
by aiagentskills
General agent safety and workflow guardrails that prevent high-impact mistakes across tooling, verification, versions, integration layers, environment/config, import-time side effects, and high-risk actions. Use when defining or applying behavioral constraints for coding agents, repo automation rules, or operational safety checklists.
Research Papers
by midhunxavier
Analyze and summarize research papers. Extracts key information, contributions, and methodology from PDFs and integrates findings into your research workflow.
quick
by pmco23
Use when implementing small features, bug fixes, typo corrections, config tweaks, or any well-understood change that does not require the full pipeline. Completely independent of the brief/design/review/plan/build/qa flow. Use --deep to escalate to Opus for trickier problems.
shape-up-analysis
by tachun
Analyze a Shape Up pitch document alongside a codebase to identify risks, rabbit holes, and unknowns. Produces comprehensive kickoff analysis with bet confidence rating. Use when asked to "analyze this pitch", "review Shape Up pitch", "kickoff analysis", "identify risks in this pitch", "what are the rabbit holes", "assess this bet", "prepare project kickoff", "evaluate this pitch", or when starting a new Shape Up cycle and need to understand scope vs codebase reality.
verification-convergence
by moonhwilee
"High-intensity /verify or /converge protocol for specialist subagent review, selective fixes, and evidence-based convergence across code, plans, docs, strategy, business, trading, and operations."
design-hig-principles
by jacoblewisau
Audit iOS/macOS UI against Apple Human Interface Guidelines. Provides context-aware, multi-perspective feedback on colors, typography, layout, accessibility, and platform conventions.
pr-prep
by russdias
Use when preparing a pull request, crafting commit messages, or summarizing code changes for review. Triggers on tasks like "prepare my PR", "write a commit message", "summarize my changes", "generate PR description", or before pushing a feature branch.
ddia-streaming-with-kinesis
by odewahn
Interactive modular learning guide for stream processing concepts from DDIA Chapter 11. Use when the user wants to learn about stream processing, messaging systems, event-driven architectures, Kafka, or needs help with the DDIA Chapter 11 curriculum. Provides 15 bite-sized modules (~45 min each) with flexible prerequisites, hands-on AWS Kinesis examples, progress tracking, and Socratic teaching. Topics include streams vs batch, messaging patterns, partitioned logs, databases & streams, and stream processing fundamentals.
pubmed-cli
by drpedapati
"Search PubMed, fetch article metadata, traverse citation graphs, and look up MeSH terms from the command line. Use when: (1) Searching PubMed with Boolean/MeSH queries, (2) Fetching article details by PMID (abstract, authors, DOI, MeSH terms), (3) Finding papers that cite a given article (cited-by), (4) Finding papers cited by a given article (references), (5) Finding related articles with relevance scores, (6) Looking up MeSH vocabulary (tree numbers, scope notes), (7) Exporting citations in RIS format for Zotero/EndNote, (8) Building reproducible literature review workflows, (9) Verifying document references against PubMed for accuracy and detecting fabricated citations."
compact
by kelvinz
"Compact tasks/context.md by summarising older completed history while preserving active context. Triggers: compact context, prune context log, trim context."
resolve-workflow
by nicolas-codemate
Modular ticket resolution workflow orchestrator. Loads steps dynamically based on mode and current state.
doc-generator-strategy
by samChang72
Use when generating or improving user manuals or documentation strategies. Focuses on Code-First Analysis, Process Restoration, and Structured Standards.
todo-task-run
by gendosu
Execute tasks from TODO file - Generic task runner [/todo-task-run xxx]
strategic-review
by kanghohyeong
This tool compares and analyzes multiple methodologies to reach a given goal and provides decision-making logic and rationale. It is triggered when a user says like "create a strategy," "establish a strategy,".
vm-bug-hunter
by zeal422
Detects actual programming errors including syntax, runtime, logical, semantic, linker, resource, security, type, and index/attribute errors. Auto-detects language and focuses on legitimate bugs, not hallucinations.
adversarial-review
by biruk741
Run adversarial review on a plan or document via Codex. Sends the document to Codex (gpt-5.3-codex, xhigh reasoning) in the background, shows the user what was sent, pre-validates while waiting, evaluates feedback, and iterates up to 5 rounds. Usable standalone or referenced by /plan.
typescript-performance-review
by bromanko
This skill should be used when the user asks to "review performance", "optimize TypeScript", "TypeScript performance", "performance audit", "find bottlenecks", "improve efficiency", or wants analysis of TypeScript code performance focusing on runtime hotspots, rendering efficiency, and data handling.
protein_analysis
by CharlesHahn
蛋白质 MD 模拟的高级分析，包括周期性边界条件校正、动态互相关矩阵（DCCM）、残基距离接触矩阵（RDCM）、主成分分析（PCA）和自由能形貌图（FEL）。使用此技能来指导蛋白质模拟后的数据分析流程。当用户需要进行蛋白质 MD 分析、计算相关性矩阵、执行 PCA 或绘制自由能形貌图时调用此技能。
qodo-pr-resolver
by ilchemla
Resolve Qodo PR review comments through analyze-confirm-execute workflow with severity-based prioritization. Analyzes comment validity, detects CI failures, confirms response approach with user, executes code changes, runs tests, and resolves threads. Use when responding to Qodo PR review comments, addressing Qodo feedback, resolving review issues, or managing Qodo review threads.
code-review
by diskd-ai
"Review code with a structured, high-signal review process. Use when asked to review code, review a PR/MR (GitHub PRs via gh, GitLab MRs via glab), review a codebase, give feedback on a changelist, audit code quality, or perform a code review. Supports both diff/PR reviews and full codebase reviews. Produces actionable findings with severity labels, exact file+line citations, and a final verdict. Covers design, functionality, complexity, tests, naming, comments, style, documentation, security, and performance."
ai-say
by Ema93sh
Local text-to-speech on Ubuntu using Kokoro TTS with fallbacks. Use when the user asks you to speak, say, read aloud, announce, or narrate text. Also use for TTS playback testing, switching Kokoro voices, adjusting speech volume, or debugging audio output issues. Triggers: "say this", "say hello", "read that back to me", "read aloud", "speak", "announce", "narrate", "tell me out loud", "hear it out loud", "text to speech", "TTS", "voice test". Do NOT use for: recording audio, transcription, speech-to-text, playing music/media files, or dictation input.
debug
by iulspop
Structured debugging skill for methodical root cause analysis. Use when investigating bugs, unexpected behavior, or errors. Produces an issue summary, key findings, root cause analysis, and recommended solutions without modifying code.