AGENT SKILLS · ミッション装備

実際に使われている Agent Skills

公開リポジトリの検証済み Skills を比較し、機能、内容、導入状況、出典を確認してから追加できます。

掲載範囲: 検証済み
Skills: 23,007
リポジトリ: 3551
最終同期: 2026/11/04

23,007 Skills

tek-scan-skills

Scan the open repo, installed skills, and skills.sh. Recommend general skills that sharpen tek-skill and repo skills for code review in the loop. Use when the user runs /tek-scan-skills. Do not install or invoke any skill.

1時間の導入数: 1
GitHub Stars: 1
更新日: 10月2日

unopim-standards

Use when writing or changing any UnoPim code — the canonical rules for Laravel 13 and PHP 8.4 idiom, security, performance, scale, extensibility, localization and comments. Trigger phrases include "best practice", "standards", "laravel 13", "security", "performance", "scalable", "localization", "comments".

1時間の導入数: 1
GitHub Stars: 1
更新日: 7月31日

pc-sync

Use this skill when the user asks to check pc-sync status, pc-sync device state, or whether pc-sync is running. Triggers: pc-sync status, check pc-sync, pc-sync running.

1時間の導入数: 1
GitHub Stars: 0
更新日: 10月2日

codex-review-loop

Self-review the current branch with OpenAI Codex's local CLI (codex review) in a review→fix loop, without polluting this thread's context. Runs codex review locally (no GitHub round-trip), fixes the issues here, and repeats until no blocking issues remain. The Codex peer to pr-review-loop — run both for independent Claude + Codex perspectives. Use when the user says "run the codex review loop", "review with codex until clean", or wants Codex's perspective on the branch.

1時間の導入数: 1
GitHub Stars: 0
更新日: 10月2日

seo-backlinks

Backlink profile analysis: referring domains, anchor text distribution, toxic link detection, competitor gap analysis. Works with free APIs (Moz, Bing Webmaster, Common Crawl) and DataForSEO extension. Use when user says backlinks, link profile, referring domains, anchor text, toxic links, link gap, link building, disavow, or backlink audit.

1時間の導入数: 1
GitHub Stars: 0
更新日: 9月30日

seo-cluster

SERP-based semantic topic clustering for content architecture planning. Groups keywords by actual Google SERP overlap (not text similarity), designs hub-and-spoke content clusters with internal link matrices, and generates interactive visualizations. Optionally executes content creation if claude-blog is installed. Use when user says "topic cluster", "content cluster", "semantic clustering", "pillar page", "hub and spoke", "content architecture", "keyword grouping", or "cluster plan".

1時間の導入数: 1
GitHub Stars: 0
更新日: 9月30日

seo-google

Google SEO APIs: Search Console (Search Analytics, URL Inspection, Sitemaps), PageSpeed Insights v5, CrUX field data with 25-week history, Indexing API v3, and GA4 organic traffic. Provides real Google field data for Core Web Vitals, indexation status, search performance, and organic traffic trends. Use when user says "search console", "GSC", "PageSpeed", "CrUX", "field data", "indexing API", "GA4 organic", "URL inspection", "google api setup", "real CWV data", "impressions", "clicks", "CTR", "p

1時間の導入数: 1
GitHub Stars: 0
更新日: 9月30日

seo-images

Image optimization analysis for SEO and performance. Checks alt text, file sizes, formats, responsive images, lazy loading, CLS prevention, image SERP rankings (via DataForSEO), and image file optimization (WebP/AVIF conversion, IPTC/XMP metadata injection). Use when user says "image optimization", "alt text", "image SEO", "image size", "image audit", "optimize images", "image metadata", "image SERP", "convert to webp", or "image file optimize".

1時間の導入数: 1
GitHub Stars: 0
更新日: 9月30日

seo-sitemap

Analyze existing XML sitemaps or generate new ones with industry templates. Validates format, URLs, and structure. Use when user says "sitemap", "generate sitemap", "sitemap issues", or "XML sitemap".

1時間の導入数: 1
GitHub Stars: 0
更新日: 9月30日

seo-content-brief

- Turns a keyword, topic or existing page into a complete, intent-first SEO content brief and on-page optimization plan. Maps search intent (informational, commercial, transactional, navigational, local) into topic clusters, then specifies the angle, H1/H2 structure, entities and questions to cover, internal links, CTA, and the E-E-A-T / people-first evidence the content must demonstrate. Also reviews and optimizes existing on-page elements: title, meta description, headings, slug, internal link

1時間の導入数: 1
GitHub Stars: 0
更新日: 5月29日

seo-orchestrator

- Plans and routes SEO work for AI agents. Takes a URL or site plus a business goal, language, market and competitors, then produces a prioritized, impact/effort/risk-ranked SEO plan and dispatches the right specialist skills (technical audit, content brief, schema, AI-search, quality gates). Use this first whenever someone asks to "do SEO", "audit my site", "improve rankings", "optimize a page", "rank in AI / ChatGPT / AI Overviews", or when the request spans more than one SEO discipline. Coord

1時間の導入数: 1
GitHub Stars: 0
更新日: 5月29日

events-bus

Provide a reusable event protocol and bus integration for orchestrators, sub-agents, and background jobs so users can see live progress instead of waiting on a black box. Strongly recommended as a bootstrap skill for any agent system that delegates work. When installing it, strongly prefer adding a mandatory rule to the global AGENTS.md (or the platform-equivalent global system/custom instructions) that points to this skill's references/protocol.md; if no global instruction file exists, add the

1時間の導入数: 1
GitHub Stars: 0
更新日: 10月2日

regression-notes

Record bug-fix decisions as Agent Notes bound to regression tests so AI-driven code changes cannot silently regress. Use when fixing a bug, reviewing a fix, verifying a notes tree, or asking when to write a postmortem. Do not use for general feature docs or changelogs.

1時間の導入数: 1
GitHub Stars: 0
更新日: 9月16日

llmem

Manage LLMem — structured memory system with SQLite-backed factual memory, semantic search, and background dreaming (decay, boost, promote, merge). Use when the user wants to: (1) add, search, update, or delete memories, (2) generate context for injection, (3) check memory stats, (4) run background consolidation/dream. Triggers on: "memory", "remember", "recall", "llmem", "memories", "forget", "consolidate memories", "dream".

1時間の導入数: 1
GitHub Stars: 0
更新日: 6月2日

llmem-setup

Install and configure LLMem for an agent harness. Handles CLI install, plugin deployment, skill registration, and provider setup. Triggers on: "install llmem", "set up memory", "configure memory", "add llmem to harness", "memory setup".

1時間の導入数: 1
GitHub Stars: 0
更新日: 6月2日

engineer

This skill describes a workflow for a software engineer. Use when asked to research and implement a new feature.

1時間の導入数: 1
GitHub Stars: 0
更新日: 10月2日

research-design

Research how to implement a project, feature, or task before planning or implementing.

1時間の導入数: 1
GitHub Stars: 0
更新日: 10月2日

pixelforge

Image generation/editing with PixelForge API (by Pixazo) via the Pixazo API. TRIGGER when the user mentions "Pixelforge" or "PixelForge API", or when the user asks to generate / make / create / edit / restyle an image and Pixelforge is named or implied. DO NOT TRIGGER for video / music / voice / 3d / try-on — each has its own skill.

1時間の導入数: 1
GitHub Stars: 0
更新日: 10月2日

bro

Restate the last message in plain human language, with no jargon.

1時間の導入数: 1
GitHub Stars: 0
更新日: 10月2日

create-verification-skill

Generate a project-local verification skill that drives your app the way a user does — any language, framework, or platform. Use for /create-verification-skill, \"make a control skill for this repo\", or when a project has no scripted way to prove UI/CLI/service behavior.

1時間の導入数: 1
GitHub Stars: 0
更新日: 10月2日

facts

Brief a capable engineer on the few facts and consequences that materially affect the current effort.

1時間の導入数: 1
GitHub Stars: 0
更新日: 10月2日

figure-it-out

Design an auditable playbook when no narrower one fits: a large migration, an ambitious multi-part change, or work a human reviews after stepping away. Scales rigor to the task, runs a hypothesis loop, and logs decisions via show-me-your-work. Use for /figure-it-out, 'figure it out', a large migration, or when no narrower playbook applies.

1時間の導入数: 1
GitHub Stars: 0
更新日: 10月2日

go-best-practices

Go engineering practices. Use when reading or editing .go files, designing Go packages or APIs, handling errors or context, writing concurrent Go, or reviewing Go code.

1時間の導入数: 1
GitHub Stars: 0
更新日: 10月2日

how

Use for \"how does X work\", code walkthroughs before changing something, and placement / ownership / layering questions (\"where should this live\", \"which package owns this\", \"is this the right layer\"). Explains subsystem architecture, runtime flow, onboarding mental models. Use why for motivation.

1時間の導入数: 1
GitHub Stars: 0
更新日: 10月2日

MIT3 ファイル

詳細を見る →