create-commit
Gitの変更をステージしてコミットする。「コミットして」「コミットしたい」「変更をコミット」といったリクエストで使用。差分を分析し、whatとwhyを含む適切なコミットメッセージを自動生成する。
create-branch
現在の変更内容を確認し、適切なブランチ名を提案してブランチを作成するときに使う。ユーザーが「ブランチ作って」「作業用ブランチ切りたい」「変更に合わせてブランチ名を決めて」と言ったとき、または新規作業を始める前にブランチを作りたいときに適用する。git status / diff を確認し、プレフィックス規則（feat/fix/release/epic）に従ってブランチ名を提案し、ユーザー確認後に git checkout -b で作成する。
coderabbit-review
Use CodeRabbit CLI to receive external code review feedback and address identified issues. Invoke this skill when the user requests CodeRabbit review, or proactively after implementing significant code changes to get feedback and improve code quality.
anthropic-skill-creator
Create and iteratively improve Cursor Agent Skills using the Anthropic skill-creator workflow. Use when the user wants to create a skill from scratch, refine an existing skill with test prompts and feedback, or follow a structured draft→test→review→improve loop for skills.
commit
Use only when explicitly invoked for Git commit workflows: stage intended changes, craft Conventional Prefix Format messages by default, Natural Language messages with --natural or configured repos, commit, and optionally --all, --staged, --close, or --push.
coingecko-historical
Use to open CoinGecko historical-data pages in the default browser for a coin/date or to show historical price on date X.
Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.
todo-archive
Use only when explicitly asked to archive/prune/compact/roll over checked tasks from TODO.md into `.ai/todos/TODO_UNTIL_YYYY_MM_DD.md`, leaving unchecked tasks.
vitest
Use for Vitest in TypeScript React/Next.js: write, run, or debug unit/component tests, mocks, testing utilities, and coverage.
tailwind-css
Use for Tailwind v4 styling: add/fix classes, configure or migrate Tailwind, use tailwind-variants, or tw-animate-css.
find-skills
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
evm-atlas
Use for targeted EVM chain, account, transaction, RPC, explorer, and bridge data: chain name/ID, native symbol, RouteMesh, balances, token/NFT holdings/transfers, tx history, funding origin via Etherscan/Blockscout/Chainscout; Bungee, LayerZero, LI.FI, Socket enrichment.
effect-ts
Use for nontrivial Effect-TS work including services/layers, typed errors, Schema/JSONSchema, Config, runtime/concurrency, @effect/vitest, @effect/ai, @effect/sql, or @prb/effect-next.
debrief
Use for debriefs or saved findings/reports from the current task. Creates `.ai/debriefs/<slug>/index.html`; `--md` writes `index.md` instead.
create-skill
Use to create/scaffold/init a new agent skill in `.agents/skills` by default or `~/.agents/skills` with `--global`.
coingecko-cli
Use for CoinGecko/cg CLI crypto market data: prices, market cap, trending coins, top gainers/losers, coin search, historical data, or OHLC.
code-polish
Use to polish recently changed code: simplify for readability/maintainability and run a risk-profiled review that autonomously applies fixes. Default runs both passes; pass --simplify or --review for one. Covers code/PR review, audits, bug/security checks, reviewing diffs or changes, cleanup, refactoring, and reducing complexity.
cli-just
Use for just/justfile task automation: create justfiles, write recipes, configure settings, add modules/attributes, or set up command-runner workflows.
cli-gh
Use for GitHub CLI automation: gh commands, repo info, workflow triggers, GitHub search, codespaces, PR status, issues, repo browsing, or command-line GitHub tasks.
cli-cast
Use for Foundry cast/on-chain actions: send tx, call contract, sign message, cast send/call/wallet, encode/decode ABI/calldata, or RPC interactions. For read-only balances/history, prefer evm-atlas.
bump-release
Use for release versioning: bump/cut/tag a release, bump version, create a release, changelog updates, or version tagging.
bump-deps
Use for dependency updates: update/bump deps, npm/pnpm/yarn/bun package upgrades, outdated checks, package.json updates, or taze.
autoresearch
Use for autoresearch, autonomous experiments, optimization loops, "optimize X overnight/in a loop", or "experiment loop"; sets up iterative trials for an optimization target.
find-tool
Use to find, compare, and recommend current tools, packages, libraries, CLIs, VSCode extensions, agent skills, databases, or infrastructure options for a development task.
git-squash
Use to squash a feature branch into one commit and rebase onto base: squash commits/branch, clean up commits, flatten branch history, prepare clean PR commit.
grill-me
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".
loop-skill
Explicit-only meta skill for running another agent skill repeatedly, defaulting to 3 iterations, with one final net report.
notion-cli
>-
playground
Use to create interactive single-file HTML playgrounds/explorers/tools with visual controls, live preview, and prompt copy-out.
repo-rename
Use only when explicitly invoked to rename a GitHub upstream repo and matching local project folder, update the local origin remote, and preserve Codex CLI and Claude Code thread continuity references.
skill-doctor
Use to audit Agent Skills catalogs or installed skill roots: validate SKILL.md frontmatter, Codex openai.yaml metadata, README catalog coverage, cli-* version pins, and relative resource links; optionally apply conservative --fix-safe metadata repairs.
skill-map
Use to find agent skill installs, duplicate skills, cross-dependencies, invocations, and cross-references across the local machine. Scans broadly while ignoring macOS protected home paths, agent home install/state directories (~/.agents, ~/.claude, ~/.codex, ~/.local/state/skills), transcript/history/state directories, dependency folders, and backups.
agents-introspection
Use to retrospect on a task against historical Codex and Claude Code chat transcripts in the current project, identify recurring agent mistakes, and recommend or apply durable fixes such as AGENTS.md updates or new skills.
yeet
Use for GitHub PR/issue/discussion workflows: create/update PRs or issues, post comments, start discussions; triggers include create/open PR, file/update issue, yeet.
agents-context-management
Use to create or polish repo agent context files: README.md, AGENTS.md/CLAUDE.md symlinks, and existing project .agents/skills/SKILL.md files. Updates existing skills only; do not create skills.
work
Run only on explicit invocation. Orchestrates end-to-end implementation, scales from direct work to subagents, and finishes with code-polish.
spreadsheets
Use when CSV, TSV, or Excel (.xlsx) is the primary input/output: inspect, clean, transform, dedupe, merge, validate, convert, recalc formulas, or create/fix spreadsheets. Do not trigger when tabular data is incidental.
summarize
Summarize or transcribe URLs, YouTube/videos, podcasts, articles, transcripts, PDFs, and local files.
observability-setup
Guide for implementing metrics, logs, and traces in applications. Use when setting up monitoring, adding instrumentation, configuring dashboards, implementing distributed tracing, or designing alerts and SLOs.
runbook-creator
Templates and patterns for creating operational runbooks and playbooks. Use when creating runbooks, writing operational documentation, playbook creation, or documenting procedures for on-call teams.
production-readiness
Comprehensive checklist for production deployment readiness covering reliability, observability, security, and operational requirements. Use when preparing for go-live, launch readiness review, production deployment checklist, or assessing if a service is ready for production.
kubernetes-troubleshooting
Systematic debugging workflows for Kubernetes issues including pod failures, resource problems, and networking. Use when debugging CrashLoopBackOff, OOMKilled, ImagePullBackOff, pod not starting, k8s issues, or any Kubernetes troubleshooting.
incident-response
Guide systematic investigation of production incidents including triage, data gathering, impact assessment, and root cause analysis. Use when investigating outages, service degradation, production errors, alerts firing, or when the user mentions incident, outage, downtime, or production issues.
realistic-ugc-video
Create realistic long-form AI talking head/UGC videos that don't look AI-generated. Use when user wants to make "realistic AI video", "UGC video", "talking head video", "AI spokesperson", "AI ad content", "video that looks real", "human-looking AI video". Orchestrates Nano Banana for base images and Kling AI for video generation with natural pacing.
nano-banana
Generate images using Google's Nano-Banana (Gemini 2.5 Flash Image) model. Use when the user asks to generate, create, or make an image, picture, or illustration.
action-cable
Expert guidance for implementing real-time features with Action Cable in Rails applications. Use when working with websockets, channels, subscriptions, broadcasting, live updates, push notifications, or Solid Cable. Covers connection authentication, channel creation, streaming, client-side JS, testing, and deployment. Clarifies when to use Action Cable directly vs Turbo Streams broadcasting.
action-controller
Expert guidance for writing Rails controllers with Action Controller. Use when writing controller actions, strong parameters, before_action filters, rendering responses, redirects, flash messages, sessions, cookies, rescue_from error handling, streaming, CSRF protection, or HTTP authentication. Covers params permitting (especially nested params — the #1 source of agent bugs), callbacks, request/response objects, and security. Trigger on "controller", "action", "strong parameters", "params", "before_action", "redirect", "render", "flash", "session", "cookies", "rescue_from", "CSRF", "permit", "expect", "filters", "callbacks".
action-mailbox
Expert guidance for receiving and processing inbound emails with Action Mailbox in Rails. Use when setting up inbound email processing, routing emails to mailboxes, configuring ingress providers (Mailgun, SendGrid, Postfix, etc.), handling attachments, bouncing emails, or testing with fixtures. Covers "action mailbox", "inbound email", "receive email", "process email", "email routing", "mailbox", "incoming email", "email processing", "ingress", "InboundEmail".
action-mailer
Expert guidance for Action Mailer in Rails applications. Use when creating mailers, sending emails, building email templates, configuring delivery, writing mailer previews, or working with transactional email. Triggers on "mailer", "email", "send email", "action mailer", "mail template", "deliver_later", "email notification", "transactional email", "mailer preview", "welcome email", "notification email".
active-record-associations
Expert guidance for defining and using Active Record associations in Rails. Use when creating associations, defining model relationships, troubleshooting foreign keys, fixing N+1 queries, setting up belongs_to, has_many, has_one, has_many :through, polymorphic associations, self-referential joins, join tables, counter caches, dependent options, inverse_of, eager loading, or any question about how models relate to each other.
Page 1215 of 1635 · 81720 results
