Code Review
Automated code review and analysis
rpi
by firede
通用 RPI（调研、计划、实施、迭代）执行技能。用于用户要求“先调研、再计划、再实施、最后迭代”的工程任务，或任务复杂度高、风险高、影响面不清晰时。该技能不依赖特定命令行工具或平台，适用于任意支持技能机制的 AI 代理。
tokencostscope
by krulewis
Automatically estimates token usage and dollar cost when a development plan is created. Triggers when: a pipeline plan is finalized, an implementation plan is produced, an architecture decision is made, or step counts and file lists are discussed. Reads the plan from conversation context to infer size, file count, complexity, and steps. Loads learned calibration factors from prior sessions to improve accuracy over time.
playwriter
by SebastiaanWouters
Controls Chrome browser via Playwright MCP for web automation, testing, screenshots, and scraping. Use when explicitly asked to "use playwriter".
data-analyst
by k1lgor
Use this for exploratory data analysis (EDA), generating visualizations, finding trends, and deriving insights from datasets using Python (Pandas/Seaborn/Plotly) or SQL.
aico-subagent-driven
by yellinzero
Execute implementation plan by dispatching fresh subagent per task. Each task gets: Implementer → Spec Review → Quality Review. Two-stage review ensures both correctness and quality. Use this skill when: - Have implementation plan with multiple independent tasks - Want automated execution with quality gates after each task - Tasks are mostly independent (not tightly coupled) - User asks to "execute the plan", "run the tasks", "auto implement" Prerequisites: Must have plan from aico-frontend-plan, aico-backend-plan, or aico-*-task-breakdown skill. Process: For each task: Dispatch Implementer → Spec Review (passes?) → Quality Review (passes?) → Next task Review order: ALWAYS spec compliance first, THEN code quality.
job-application-agent-suite
by HyunWoo9930
Build and run a multi-agent workflow for Korean job applications, especially self-introduction essays and cover letters. Use when users ask to analyze a target company/role, extract and map personal experiences, draft application answers, rewrite tone for a specific company, detect AI-like writing patterns, and run final submission checks.
astral-ty
by fredericosantos
Guide for using ty, the extremely fast Python type checker and language server. Use this when type checking Python code or setting up type checking in Python projects.
pr-onboarding
by CAPHTECH
PR作成時に生成AIがPR本文にオンボーディングを記述するスキル。変更の契約を、レビューア・将来の自分・障害対応者に渡す。理解の再現性・反証可能性・運用可能性を同時に成立させる。 トリガー条件: - PRを作成する時（「PRを作成して」「プルリクを書いて」） - PR本文を充実させたい時（「PR説明を書いて」「PRオンボーディングして」） - 変更の影響を整理したい時（「この変更の影響範囲を整理して」） - レビューの準備をする時（「レビュー用に変更をまとめて」）
recursive-handoff
by SebastiaanWouters
"Execute the same task repeatedly with clean context via handoff. Triggers on: recursive loop, repeat until, keep doing until, loop until done. REQUIRES a finish condition to stop."
impeccable-critique
by SebastiaanWouters
"Skills-only equivalent of impeccable.style /critique. Evaluate design effectiveness from a UX perspective. Assesses visual hierarchy, information architecture, emotional resonance, and overall design quality with actionable feedback. Use for frontend and UI design tasks."
test
by iamladi
Write or review tests following Kent C. Dodds testing principles - flat structure, composable setup, disposable fixtures. Use when the user asks to write tests, review tests, or convert legacy tests.
my-voice
by srobinson
Write content in Stuart's voice for social media, GitHub, essays, or any public-facing writing. Use when asked to draft posts, write tweets, compose replies, create threads, write copy, or generate any content that should sound like Stuart — not like an AI. Also use when the user says "my voice", "draft a post", "write a tweet", "compose a reply", or "help me write".
hardening
by Cholulaa
"Complete security hardening of a Linux server based on CIS Benchmarks, NIST 800-123, and ANSSI BP-028. Smart service discovery to avoid disruption. 4 hardening levels (minimal/standard/enhanced/paranoid). Installs open-source security tools, hardens SSH/kernel/firewall/systemd/permissions, runs all scans, generates a compliance report."
observation-minimum-set
by CAPHTECH
"観測の最小セットを適用。6つの失敗モード（仕様誤解/境界条件/依存/セキュリティ/並行性/運用）を継続可能なコストで網羅。Use when: プロジェクト開始、リリース前チェック、品質改善振り返り、観測が足りているか確認したい。"
app-audit
by chen-ye
Analyzes installed Termux packages and Android apps to identify redundancies, categorize usage, and suggest cleanups. Use when the user asks to audit apps, check for bloatware, or analyze installed software.
yeet
by lgariv-dn
"Use only when the user explicitly asks to stage, commit, push, and open a GitHub pull request in one flow using the GitHub CLI (gh)."
code-review
by SebastiaanWouters
Comprehensive code review covering functionality, testing, QA, and AGENTS.md compliance. Triggers on "review code", "code review", "review this", "check my code". Validates correctness, test coverage, test quality, and guideline adherence.
gemini
by iamladi
Use when the user asks to run Gemini CLI for code review, plan review, or big context (>200k) processing. Ideal for comprehensive analysis requiring large context windows. Uses Gemini 3 Pro by default for state-of-the-art reasoning and coding.
ratatouille
by SebastiaanWouters
"Implement one prd.json task per iteration using tracer-bullet + compound mindset. Triggers on: ratatouille:."
data-qc
by smestern
Performs systematic data quality control checks before analysis — missing values, outliers, distributions, unit validation, duplicates, and structural integrity assessment with severity-rated reporting.
figure-plot
by ustc-ai4science
Generate publication-quality AI/ML paper figures from CSV, inline tables, or clearly described experiment results. Trigger this skill when the user asks to plot, draw, visualize, or turn results into a figure, especially for: - ablations, method comparisons, training curves, hyperparameter sensitivity, stability plots, tradeoff plots - bar charts, line charts, heatmaps, box plots, scatter plots - NeurIPS / ICML / ICLR / CVPR / IEEE / camera-ready / publication-quality figures - pasted numeric markdown tables, CSV text, or file paths such as .csv / .xlsx / .json
story-naming
by peterknezek
Use when creating Storybook stories, naming story exports, organizing story files, or reviewing story naming conventions. Ensures story names describe user scenarios and component states rather than implementation details.
context-engineering
by justgetAI
Human-readable context management for AI coding agents. Filesystem-based specs, tasks, and foundation docs. Ships features with full traceability via native Teams.
gt
by wiseiodev
Create Graphite stacked PRs from staged git changes. Use when user says "/gt", "create a PR", "submit PR", or wants to commit and create a pull request using Graphite. Optionally accepts a Linear issue ID (e.g., "/gt A-35") to auto-close issues on merge.