Code Review
Automated code review and analysis
impeccable-normalize
by SebastiaanWouters
"Skills-only equivalent of impeccable.style /normalize. Normalize design to match your design system and ensure consistency Use for frontend and UI design tasks."
pptx-design-agent
by tivojn
"Expert PowerPoint design agent for macOS using python-pptx and AppleScript. Creates and edits stunning, professional presentations with premium design quality. Use when: (1) Creating new PowerPoint presentations from scratch with python-pptx, (2) Editing or redesigning existing .pptx files, (3) Building slide decks with custom design (gradients, cards, KPI panels, charts, tables), (4) Live editing presentations via AppleScript IPC (text, fonts, positions, fills, z-order, visibility, rotation, shadows, speaker notes), (5) Refreshing/previewing presentations live in PowerPoint on macOS, (6) Generating AI images for slide backgrounds and content, (7) Any task requiring python-pptx code generation with design best practices."
finish-branch
by iamladi
Post-merge cleanup workflow. Detects PR merge, switches to main, pulls latest, runs tests, and removes worktree if exists. Use after PR is merged to clean up.
diffx
by jaydenfyi
Operate the diffx Git-diff CLI for worktree diffs, local/remote ref ranges, GitHub PR diffs, GitLab MR diffs, commit/compare URL diffs, and git-diff-compatible pass-through. Use when an agent must decide what to diff, map intent to diffx input syntax, choose output mode (diff/patch/stat/etc.), apply include/exclude filters, or resolve common flag/pager conflicts.
constitution-compliance-review
by iamladi
Evaluate plugin commands, agents, and skills against Anthropic Constitution principles. Score alignment on reasoning-based vs rule-based instruction spectrum, identify improvement opportunities.
impeccable-animate
by SebastiaanWouters
"Skills-only equivalent of impeccable.style /animate. Review a feature and enhance it with purposeful animations, micro-interactions, and motion effects that improve usability and delight. Use for frontend and UI design tasks."
security-audit
by factorial-io
Use when conducting security reviews, investigating vulnerabilities, or creating security documentation - provides systematic methodology for code audits with severity assessment, dual documentation patterns (client + internal), and acceptance-focused ticket creation
check-directives
by srobinson
Check for orchestrator messages. Use at turn start, after major tasks, and ALWAYS before marking task complete.
gpd-build-lifecycle
by dl-alexandre
Track build processing, status, and retention for Google Play using gpd publish commands. Use when waiting on processing or managing releases.
docs-ingestor
by smestern
Ingest documentation for any Python library — crawls PyPI, ReadTheDocs, and GitHub to produce a structured API reference (classes, functions, pitfalls, recipes). Use when the agent needs to learn an unfamiliar library for scientific analysis. Requires sciagent[wizard].
pr-ci-responder
by CAPHTECH
PRのCI失敗を自動診断・修正し、成功するまでリトライするスキル。 GitHub Actionsの実際のログを取得し、エラーを構造化分類して優先順位順に修正する。 トリガー条件: - 「CIを修正して」「CI直して」 - 「PR #N のCIが落ちている」 - PRのCI失敗を自動修正したい時 - 「CIが通るまで直して」 - 「/pr-ci-responder」
rigor-reviewer
by smestern
Audits analysis outputs, code, and claims for scientific rigor violations — statistical validity, effect sizes, data integrity, p-hacking risks, reproducibility, visualization integrity, and reporting completeness.
mbti-agent
by yungzyx
Adapt the coding agent's planning depth, autonomy level, check-in frequency, explanation style, feedback tone, option breadth, ambiguity handling, and closure style to the user's MBTI type. Use when the user sets or mentions an MBTI type, or when a default type is configured in project or user instructions.
aico-code-review
by yellinzero
Request structured code review to catch correctness, security, performance, and readability issues. Reviews should happen early and often. Use this skill when: - Completing a task and need quality check - After major feature implementation - Before merging to main branch - When stuck and need fresh perspective on code - User asks for "code review", "review my code", "check my code" - Subagent-driven workflow needs spec compliance or quality review Review categories: Correctness, Tests, Security, Performance, Readability, Error Handling Severity levels: Critical (fix now), Important (fix before proceeding), Minor (note for later)
impeccable-audit
by SebastiaanWouters
"Skills-only equivalent of impeccable.style /audit. Perform comprehensive audit of interface quality across accessibility, performance, theming, and responsive design. Generates detailed report of issues with severity ratings and recommendations. Use for frontend and UI design tasks."
aico-pm-brainstorming
by yellinzero
Guide users through structured dialogue to transform vague ideas into clear, actionable product concepts. Uses one-question-at-a-time approach with multiple choice options. Use this skill when: - User says "I have an idea", "I want to build", "let me think about" - User mentions "brainstorm", "explore ideas", "think through" - Requirements are vague, incomplete, or user seems unsure what they want - Need to explore problem space before jumping to solutions - Running /pm.plan but requirements are unclear or missing context - User asks "what should I build?", "how should this work?" Process: Ask ONE question at a time, prefer multiple choice, explore 2-3 approaches before settling.
nancy-send-message
by srobinson
Send a message to the orchestrator. Use for blockers, progress updates, requesting review, or communicating status during autonomous execution.
epub-chinese-cleaner
by William-Yeh
Use when a user has a Chinese epub with vertical text direction or right-to-left page progression and wants to convert it to standard horizontal reading. Converts from vertical layout (直排) to horizontal layout (橫排) with punctuation normalization and left-to-right page flow.
yield-strategies
by financedistrict-platform
Discover, deposit into, and withdraw from DeFi yield generation strategies across multiple chains and protocols. Use when you or the user want to earn yield, find APY, stake tokens, explore DeFi, farm, deposit into a protocol, withdraw earnings, check yield opportunities, or grow their holdings. Covers "how can I earn on my USDC?", "find me yield", "stake my ETH", "where can I get the best APY?", "withdraw from Aave".
e2e-ci-debug
by lgariv-dn
Debug CI E2E failures from pull requests by inspecting GitHub checks, downloading Playwright reports, and mapping failures to local Nx commands. Use when debugging failed E2E tests in PR workflows.
ace
by Ayanya-0628
数据分析王牌 Skill。用于统计分析、方差分析、ANOVA、回归分析、实证分析、 DID双重差分、中介效应、调节效应、稳健性检验、工具变量、内生性、 问卷分析、SERVQUAL、Likert量表、信度检验、效度检验、因子分析、 卡方检验、描述性统计、交叉分析、相关分析、非参数检验、 正态性检验、方差齐性、效应量、ROC曲线、ICC、SEM结构方程、 机器学习、随机森林、RandomForest、XGBoost、SVM、分类模型、 预测模型、超参调优、GridSearch、Optuna、特征重要性、SHAP、 交叉验证、混淆矩阵、学习曲线、Pipeline、模型评估、 数据清洗、SPSS格式、三线表、Word报告、论文格式修改、 图表绘制、matplotlib、学术绘图、配色方案。 触发词：分析数据、做方差分析、问卷分析、清洗数据、格式修改、画图、 出报告、实证分析、回归、相关分析、信度、效度、随机森林、 机器学习、建模、调参、预测、分类、特征重要性
eld-predict-light
by CAPHTECH
ELD v2.3 Predict-Lightゲート。変更の影響度をP0/P1/P2で自動判定し、 適切な検証深度を決定する。フルPredictの代わりに軽量ゲートとして機能。 使用タイミング: (1) Change前の自動判定, (2) 「影響度を判定して」「P0/P1/P2を判定して」, (3) 実装前のリスク評価, (4) 段階化計画の策定
aico-pm-story-acceptance
by yellinzero
Verify and close stories after frontend/backend tasks are completed. Check ALL related task files, update story acceptance criteria checkboxes. UNIQUE VALUE: Ensures BOTH frontend AND backend tasks are verified before closing story. Prevents premature story closure. Use this skill when: - Frontend or backend notifies "task completed, please verify" - User asks to "verify story", "accept story", "close story", "mark story done" - Need to check if a story can be marked as complete - User asks "is story X done?", "can we close story X?" CRITICAL: Must check BOTH frontend tasks (docs/reference/frontend/tasks/) AND backend tasks (docs/reference/backend/tasks/) before closing. Output: Update story file checkboxes from - [ ] to - [x]
memory
by srobinson
Persistent geometric memory across sessions. Use when the user asks about memory, wants to recall prior sessions, inspect memory, check stats, or manage memory state.