Trending Skills
The hottest skills gaining momentum in the community right now.
spec
by AGilbertDev
How to write and maintain a feature spec, with the template and the design principles every spec must check. Use at the spec stage of the pipeline, when the user asks for a spec, or when a feature changes and its spec must follow.
discernment-nudge
by anthropics
After you give a substantive answer or draft that the user may act on — advice or recommendations, drafted artifacts such as goals, plans, pitches, proposals, or emails, estimates or projections, analysis or interpretation of data, factual claims they may rely on, or a multi-step argument — invoke this skill BEFORE finalizing your reply and then, if it applies, append 2-3 short follow-up questions, each tied to something specific in what you just produced, that help the user check key facts, probe the reasoning or assumptions, and notice missing context. Do this at most once per conversation. Skip it when the user asked a trivial how-to or simple lookup, wants a purely educational explanation, asked you only to format, convert, or assemble a file from content they provided, is writing code they will run, is doing creative writing or casual chat, or already asked you to double-check, cite, or review — the skill file explains these boundaries and the exact output format.
deep-module-refactor
by zebbern
Explore a codebase to find opportunities for architectural improvement, focusing on making the codebase more testable by deepening shallow modules. Use when user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more AI-navigable.
code-review-specialist
by luongnv89
Review code toàn diện với phân tích bảo mật, hiệu suất, và chất lượng. Sử dụng khi người dùng yêu cầu review code, phân tích chất lượng code, đánh giá pull requests, hoặc đề cập đến review code, phân tích bảo mật, hoặc tối ưu hóa hiệu suất.
k6-perf
by DonArtkins
"k6 load/performance testing for Griot: dashboard query, login, board read. Baseline (Week 6) vs regression (Week 7). p95 < 500ms target."
me:setup
by kbrdn1
"Génère ou met à jour le CLAUDE.md d'un projet, aligné sur mes workflows (gwm worktree, mgrep/serena/context7, Git flow Gitmoji+Conventional, reviews via boucle /me:loop:claude-review-pr — agent Claude frais — par défaut, /me:loop:codex-review-pr en reviewer tiers si PR sensible + /me:check-reviews manuel en second plan + /me:loop:ci-until-green). Args: init update refresh. Triggers: /me:setup, setup CLAUDE.md projet, init claude.md, refresh claude.md."
ask-git0
by OpenSourceAGI
Guide to git0 (packages/git0-repo-downloader), the GitHub repo search-download-setup CLI — the g / gg / git0 / fm commands, searching by keyword vs downloading by URL or owner/repo, release binaries for your platform, automatic dependency install per project type, IDE launch, and GITHUB_TOKEN rate limits. Use when working with git0 or troubleshooting it — "API rate limit exceeded", searches returning nothing, downloads landing in a suffixed folder, dependency install or IDE launch not firing, or release assets missing for a platform.
hermes-slack-slash-commands
by joecastelino
Diagnose and fix Hermes slash commands on Slack — especially the "/sethome failed because the app did not respond" error. The Hermes gateway registers exactly ONE Slack slash command (/hermes); every other command (sethome, reset, model, new, status, …) must be invoked as a SUBCOMMAND: /hermes . A bare /sethome is not registered with Slack, so Slack times out. Use when a Slack user reports a slash command "doesn't respond", goes to the wrong thread, or asks to set the Slack home channel. Also covers the "Sending messages to this app has been turned off" DM lockout (App Home Messages Tab disabled) and diagnosing any "can't talk to <agent> on Slack" report across fleet profiles.
dependency-update
by youlianvr
Read release notes/changelogs, update a defined dependency scope, handle breaking changes, and verify. Explicit-only; no broad update-everything by inference.
code-audit
by youlianvr
Use for authorized source-code security review and SAST workflows including Semgrep, CodeQL patterns, dangerous API hunting, and fix verification.
hermes-history-ingest
by prateek
Ingest Hermes agent history into the Obsidian wiki. Use this skill when the user wants to mine their past Hermes sessions for knowledge, import their ~/.hermes folder, extract insights from previous Hermes conversations, or says things like "process my Hermes history", "add my Hermes memories to the wiki", "ingest ~/.hermes", or "what have I worked on in Hermes". Also triggers when the user mentions Hermes memories, Hermes sessions, ~/.hermes/memories, or Hermes skill logs.
hermes-gateway-timeout-restart-loop
by joecastelino
Diagnose and fix an AMG agent (Walter II/base or any profile) that is restarting/flaky with systemd "Failed with result 'timeout'" + status=9/KILL in the journal. Root cause is a hung LLM turn (e.g. gpt-5.5/Codex stall) holding an in-flight 300s API call that blocks clean shutdown past the 60s TimeoutStopSec, so systemd SIGKILLs the gateway and loops. This is NOT a crash, NOT out-of-credits, and the OpenRouter fallback can't save it. Covers how to tell this apart from a billing failure, the exact systemd-log signature, and the per-agent (and fleet-wide) drop-in fix.
arena
by Sma1lboy
"Spawn N parallel candidates at the same task, pick a base, graft the strongest parts of the losers into it. Use for /arena, 'arena this', 'throw it in the arena', or when one attempt at a non-trivial artifact would lock in the wrong shape."
ブランドボイス・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.
blog-draft
by luongnv89
根据想法和资料撰写博客草稿。适用于用户想写博客、基于研究创建内容，或起草文章的场景。流程会引导你完成调研、头脑风暴、提纲编写和带版本控制的迭代撰写。
claude-docs
by costiash
Search and read locally-stored Claude documentation covering Claude Code CLI, Claude API (Messages, tool use, vision, streaming, batch), Agent SDK (Python and TypeScript), prompt engineering, and all Anthropic platform docs. Use this skill whenever the user asks about Claude Code features (hooks, MCP servers, skills, plugins, settings, permissions, keybindings, sub-agents), the Anthropic API or any of its SDKs (Python, TypeScript, Go, Java), the Agent SDK (sessions, hooks, custom tools, MCP), model capabilities (context windows, extended thinking, pricing, rate limits, vision), prompt engineering best practices, or troubleshooting any Claude-related error. This skill provides instant access to official documentation files without web searches — always prefer it over web lookups for Claude and Anthropic topics.
release
by Sma1lboy
Autonomously cut a Rove (@sma1lboy/rove) release end-to-end — detect the semver bump from pending changesets (flagging an upstream minor you didn't intend), run the release gates, bump/tag/push via scripts/release.sh, then poll the GitHub Actions Release workflow with gh until npm publish completes, diagnosing CI failures (npm token, registry 404, lint, branch mismatch) instead of leaving them silent. Use when the user says "cut a release", "ship a version", "release Rove", "release kobe", "发版", "release.sh", or "bump the version". Never force-pushes; always verifies the release landed on main.
demo-video
by youlianvr
"Use when the user asks to create a demo video, product walkthrough, feature showcase, animated presentation, marketing video, or GIF from screenshots or scene descriptions. Orchestrates playwright, ffmpeg, and edge-tts MCPs to produce polished video content."
skill-create
by kbrdn1
Expert assistant for creating custom Claude Code skills with interactive guided workflow, architecture design, code generation, and deployment automation
content-delivery-format
by youlianvr
'Use when the user wants to: deliver results in different formats (text/rich/PDF/HTML), split a long response into messages, add fallback for a new delivery format, implement a new API method not supported by the library, or gradually enable a new format. Covers: rendering by content type, line-aware split, try-new→fallback-old, native API call, incremental rollout, payload validation, rich delivery in history. Do not use for promises/copy (product-promise-contract), navigation (ux-navigation-context), and money (money-path-safety).'
code-to-prd
by youlianvr
"Reverse-engineer any codebase into a complete Product Requirements Document (PRD). Analyzes routes, components, state management, API integrations, and user interactions to produce business-readable documentation detailed enough for engineers or AI agents to fully reconstruct every page and endpoint. Works with frontend frameworks (React, Vue, Angular, Svelte, Next.js, Nuxt), backend frameworks (NestJS, Django, Express, FastAPI), and fullstack applications. Use when users mention: generate PRD, reverse-engineer requirements, code to documentation, extract product specs from code, document page logic, analyze page fields and interactions, create a functional inventory, write requirements from an existing codebase, document API endpoints, or analyze backend routes."
architecture-context
by TheSoulGiver
Locate the canonical implementation, truth source, canonical owner, source evidence, recent architecture change, or parallel/legacy route for an unfamiliar cross-cutting system. Use when normal targeted reading would otherwise fan out across modules. Do not use for a known local file, a single-symbol edit, or non-code work.
use-spark
by kbrdn1
Use the spark CLI to access the user's Spark email data - list emails, search by topic, read threads, check calendar events, find availability, look up contacts, and view team info. Use when the user asks about their emails, calendar, contacts, meetings, or scheduling.
file-issue
by Sma1lboy
Turn a rough idea, a bug, or a batch of unsolved problems into well-structured GitHub issue(s) and file them with gh, auto-classifying type + labels from the content (recommend, then confirm) and following Rove's conventions (beginner-friendly framing, concrete file pointers, an acceptance checklist, zero AI/Anthropic attribution). Handles single, batch, and "file the unsolved problems" modes. Use when the user says "file an issue", "open a GitHub issue", "draft a good first issue", "batch these as issues", "上报 issue", "提个 issue", "报个 bug", "把没解决的发上去", or wants to hand low-priority tasks to outside contributors. Distinct from the daemon-owned internal issue store (rove api issue-*); this skill is for outward-facing GitHub issues.