Trending Skills
The hottest skills gaining momentum in the community right now.
newman-api
by DonArtkins
"Newman CLI runs of the Postman collection in CI: API contract + regression suite, JSON schema assertions, chained tokens."
playwright-skill
by zebbern
Battle-tested Playwright patterns for E2E, API, component, visual, accessibility, and security testing. Covers locators, fixtures, POM, network mocking, auth flows, debugging, CI/CD (GitHub Actions, GitLab, CircleCI, Azure, Jenkins), framework recipes (React, Next.js, Vue, Angular), and migration guides from Cypress/Selenium. TypeScript and JavaScript.
autonomous-work
by youlianvr
REAL autonomous work mode for [HEARTBEAT] / unattended / night shifts. NOT a "check everything" skill. Focuses on ONE task until it's polished to perfection, then moves to the next. Critical self-review every cycle. Triggers on: [HEARTBEAT], unattended, cron, night shift, nighttime, autonomous, background, self-heal, while I sleep, go work, do something, autonomous. IMPORTANT: do NOT spread across many tasks. Pick ONE, polish it, then move on. Never say "nothing to do" — always find the next thing.
autorun
by youlianvr
Judge system prompt for autonomous goal completion. Receives a global goal, directs the agent through the workflow, consolidates lessons into memory. Focus: self-improvement over testing. Use when: "autonomously", "goal mode", "keep at it until you finish", "work until done", "judge loop".
executing-plans
by youlianvr
"Full planning-to-execution pipeline: write an implementation plan from a spec, persist it as files, execute tasks with verification, and report. Combines plan writing, file-based context management (Manus-style), and plan execution. Use when starting a multi-step task that needs a written plan."
review-checklist
by AGilbertDev
How to review a diff against the Nuxt-stack conventions, with the severity scheme and the review-only quality items. Use alongside /code-review before a pull request, or when the user asks whether Nuxt code looks right.
unslop
by Sma1lboy
Strip AI writing tells from Rove's user-facing prose — README, the docs/ pages that sync to docs.rove.run, landing copy, and release notes. Use when the user says "unslop", "洗一下文案", "这读起来像 AI 写的", or after drafting any user-facing page. Adapted for this repo from cursor/plugins pstack/skills/unslop.
session-handoff
by taika-izumi
"セッション間で作業を継続するためのハンドオフファイル（docs/working/handoff/<branch>.md）を読む・作成する・更新する・確定する・サイクル完了時にリセット（cycle-reset）する。マイルストーン到達時・セッション終了時・retrospective 完了時に呼ばれる。"
codex-history-ingest
by prateek
Ingest Codex CLI conversation history into the Obsidian wiki. Use this skill when the user wants to mine their past Codex sessions for knowledge, import their ~/.codex folder, extract insights from previous coding sessions, or says things like "process my Codex history", "add my Codex conversations to the wiki", or "what have I discussed in Codex before". Also triggers when the user mentions .codex sessions, rollout files, session_index.jsonl, or Codex transcript logs.
claude-md
by luongnv89
Tạo hoặc cập nhật các file CLAUDE.md theo các thực hành tốt nhất để onboarding tác nhân AI tối ưu
hyperframes-registry
by Sma1lboy
"Install and wire registry blocks and components into HyperFrames compositions. Use when running hyperframes add, installing a block or component, wiring an installed item into index.html, or working with hyperframes.json. Covers the add command, install locations, block sub-composition wiring, component snippet merging, registry discovery, and authoring a new block or component to contribute upstream (idea → scaffold → validate → PR)."
watch-ci
by kbrdn1
Monitor CI pipeline and automatically fix failures until green
decision-log
by taika-izumi
"重要な意思決定をADR（Architecture Decision Record）として記録・管理する。設計判断、プロセス決定、スコープ決定、方針決定を構造化して記録する。意思決定を検出した瞬間に呼ぶこと。実行中の他スキルの完了を待ってはならない。"
speckit.converge
by kbrdn1
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new, traceable tasks to tasks.md so speckit.implement can complete it. Append-only — never rewrites spec/plan or existing tasks, never edits code.
data-viz-renderer
by zebbern
"Generate self-contained HTML/SVG infographics from JSON data, including stat cards, bar charts, flow diagrams, and mixed dashboards. Offers 8 color palettes and built-in icons with no external dependencies. Triggered when users request data visualization, infographics, charts, or dashboards."
shell-conventions
by AtomiCloud
Shell script conventions. Use when writing or modifying shell scripts in scripts/.
コードレビュー・スキル
by luongnv89
A visual, example-driven guide to Claude Code — from basic concepts to advanced agents, with copy-paste templates that bring immediate value.
brainstorm
by kbrdn1
Interactive requirements discovery through Socratic dialogue and systematic exploration
writing-template-javascript
by AtomiCloud
Write or modify CyanPrint template code in JavaScript. Use when the user asks to add prompts, change template logic, modify the entry point, add processors/plugins/resolvers, or change generated output for a JavaScript template. Covers IInquirer question types (text, select, checkbox, confirm, password, dateSelect), processor configuration, and IDeterminism for non-deterministic values.
hyperframes-design
by Sma1lboy
"Non-animation creative direction for HyperFrames videos. Use for design spec (frame.md / design.md) handling, palettes, typography, beat planning, composition patterns, and brand / style decisions. For atomic motion patterns and scene blueprints, use hyperframes-motion."
pipeline
by AGilbertDev
Build one feature through the spec-driven pipeline. Use for any feature, page, route, or non-trivial fix in a personal project. Spec approved in plan mode, then tests first, a hands-off build, browser verification, review, and an open pull request. Not for small fixes.
remotion-best-practices
by Sma1lboy
Best practices for Remotion - Video creation in React
chart-image
by zebbern
"Generate publication-quality PNG chart images from data, supporting line, bar, area, candlestick, pie, and heatmap charts. Triggers when the user asks to visualize data, create a graph, plot a time series, or generate a chart for a report, alert, or dashboard. Runs as a lightweight, headless Node.js process without a browser."
pre-action-review
by taika-izumi
"不可逆操作や重要な変更の前に、実行内容のサマリーとリスク評価をユーザーに提示する。リスクレベルに応じてログのみ・サマリー表示・承認必須を切り替える。"