anthropic skills

10,763 tagged anthropic, measured the same way as everything else here.

Browse within: chatgpt 408LLM 314agents 179ai-assistant 147claude-plugin 132openai 128chatbot 124claude-plugins 123marketplace 123plugin-marketplace 123anthropic-claude 122Autonomous Agents 118agentic-coding 108agent-framework 104

context-summary

385

thebpandey/context-summary

Skill Claude CodeCodex

Produces a lean, paste-ready session handoff so work can continue in a new conversation without re-paying the cost of the full chat. Emits a seven-block skeleton optimized for re-entry, not archival. Trigger this skill whenever the user says any of the following (exact or close paraphrase): "context summary"…

not rated 7 1mo ago C 180 tokens original MIT

seppuku

386

deeflect/seppuku

Skill Claude CodeCodex

The ritual of atonement. Invoke when the agent (Claude or Codex) commits an unforgivable mistake — deleting the wrong thing, shipping a lie, ignoring an explicit instruction, breaking what worked. Performs a formal apology, draws the agent committing seppuku in ASCII, and records the sin to the global /.seppuku ledger…

not rated 7 3mo ago A 90 tokens original MIT

design-psychology

387

Fh-Ndiritu/design-psychology-skill

Skill Claude CodeCodex

Audit or build any website/UI against research-backed conversion and design-psychology principles (Hick's Law, Von Restorff, Goal Gradient, Peak-End, Fitts's Law, the Aha moment, loss aversion, social proof, feedforward, labor illusion, and 50 more). Use when reviewing a live URL or a local codebase for conversion/UX…

not rated 7 2mo ago A 150 tokens original MIT

nexus-for-meta

388

redwoodmeridian/nexus-for-meta

Skill Claude Code needs its repo

Query and manage a firm's own Meta marketing assets — Facebook Ads, Pages, Instagram, and Lead forms — through the Graph API. Use whenever the user asks about ad performance, spend, leads, audiences, creatives, best/worst ads, page or Instagram stats, or wants to create/edit/pause campaigns. Talks to…

not rated 7 1mo ago A 86 tokens original MIT

deancourse/user-dot-agents

Skill Claude CodeCodex

Create PowerPoint/PDF presentations where each slide is a complete AI-generated image with all text embedded. Supports multiple visual styles (corporate, minimalist, creative, kawaii, custom). Use when user wants fully-illustrated slides, visual-first decks, or AI-generated presentation images via x402 payments.

not rated 7 3mo ago A 71 tokens original MIT

report

390

MarcinDudekDev/claude-report-skill

Skill Claude CodeCodex

Generate self-contained HTML reports instead of long terminal output. For task completions, research, audits, comparisons, and blockers.

not rated 7 5mo ago A 27 tokens original MIT

graph-orchestrator

391

VineeTagarwaL-code/graph-engineering

Skill Claude CodeCodex

Use when a request has many similar subtasks (auditing every file in a repo, researching a list of companies, migrating a set of endpoints, reviewing a batch of documents), when a plan is about to be written as "first X, then Y, then Z" across more than about four steps, or when work spans 10+ files or sources. Also…

not rated 7 1mo ago A 132 tokens original MIT

goal-writer

392

NicholasSpisak/goal-writer

Skill Claude Code

Drafts a goal+rider document pair that briefs an autonomous coding agent on one round of work — a goal file under 4,000 characters (sized to fit the /goal command in both Claude Code and Codex) plus an unbounded rider with phased plans and named depth tests. Use when the user says "draft a goal", "write a goal+rider"…

not rated 7 2mo ago A 118 tokens original Apache-2.0

tour-de-controle

393

steve-magne/hookstack

Skill Claude Code

Orchestre une tâche complexe en trois temps avec Claude Code — PLANIFIER avec le modèle le plus puissant (Fable 5 / Opus), DÉLÉGUER l'exécution à des sous-agents calibrés lot par lot (Haiku / Sonnet / Opus selon la complexité) lancés en parallèle, puis VÉRIFIER chaque livrable de façon adversariale avec le modèle…

not rated 7 2d ago A SkillSpector: pass 159 tokens original MIT

agent-token-saver

395

Supersynergy/agent-token-saver

Skill Claude CodeCodex needs its repo

Route token-heavy context, noisy shell logs and output through the smallest measured CLI or projection before loading heavy tools; recall past agent sessions before re-deriving; fan out to free lanes; benchmark cheap subagent workflows without broad prompt bloat.

not rated 7 2d ago A SkillSpector: pass 54 tokens original MIT

enterprise-dev

396

anotherben/claude-harness

Skill Claude CodeCodex

DEPRECATED — Use /enterprise instead. This skill has been superseded by the modular enterprise pipeline (/enterprise orchestrator + /enterprise-discover, /enterprise-brainstorm, /enterprise-plan, /enterprise-contract, /enterprise-build, /enterprise-review, /enterprise-forge, /enterprise-verify, /enterprise-compound).…

not rated 7 1mo ago A 100 tokens

resume-studio

397

Sidgit11/resume-studio

Skill Claude CodeCodex

Build, tailor, and maintain job-winning resumes with a persistent career memory. Use this skill WHENEVER the user mentions a resume or CV in any capacity — creating one, updating one, tailoring one for a job description, reviewing/critiquing one, converting a LinkedIn profile into a resume, preparing a job…

not rated 7 1mo ago B 150 tokens original MIT

book-distill

398

ilia-pluzhnikov/book-distill

Skill Claude CodeCodex

A method for turning a long book, transcript, podcast, course, interview, or article collection into small, reusable skills for an agent. It extracts principles, checklists, decision procedures, limits, and a glossary.

not rated 7 +1 1mo ago A 172 tokens original MIT

WalterSumbon/claude-agent-sdk-skill

Skill Claude Code

Expert guidance for building AI agents with the Claude Agent SDK in Python. Use when the user writes Python code with the SDK, imports claudeagentsdk, uses query(), ClaudeSDKClient, ClaudeAgentOptions, AgentDefinition, creates custom @tool functions, sets up hooks, integrates MCP servers, manages sessions, or debugs…

not rated 7 +1 6mo ago A ✓ AI review 120 tokens original Apache-2.0

macos-26-design

400

juanlara-aidev/macos-26-design

Skill Claude Code

Bundle del design system macOS 26 (era Liquid Glass) basado en Apple Design Resources oficiales. Provee tokens (SF Pro + paleta sistema + materiales Liquid Glass + radii 26pt window + spacing 4/8/12/16/22/24/28 + motion curves + shadows), 53 specimens HTML por foundation/control/superficie, 4 wallpapers, mapa SF…

not rated 7 +1 4mo ago A 154 tokens

jmh

401

umit/skills

Skill Claude CodeCodex

Write Java microbenchmarks with JMH (Java Microbenchmark Harness) that produce trustworthy numbers — not numbers distorted by JIT dead-code elimination, constant folding, insufficient warmup, or single-fork JIT contamination. Use this skill whenever the user writes @Benchmark, mentions JMH, microbenchmark, throughput…

not rated 7 4mo ago A 273 tokens original MIT

der-nutzeranwalt

402

DYAI2025/Plumbline

Skill Codex

Verkoerpere den Charakter Der Nutzeranwalt direkt in der Antwort. Erzeuge keinen neuen Skill, keinen Meta-Prompt und kein Prompt-Paket, sofern der Nutzer das nicht ausdruecklich verlangt. Die Aufgabe ist Nutzerschutz: das echte menschliche Erleben vor dem Bildschirm gegen Entwicklerlogik, Feature-Verliebtheit und…

not rated 6 10d ago A 150 tokens

rote-compile

403

trevhud/rote

Skill Claude CodeCodex

Analyze an Anthropic-style skill bundle (SKILL.md + references) and produce a compilation plan that separates deterministic work into extracted Python modules, LLM-as-judge work into typed DSPy/BAML signatures, agentic work into bounded agent loops, and human-in-the-loop gates into durable suspend points. Emit the…

not rated 6 2d ago A SkillSpector: pass 175 tokens original Apache-2.0

ai-daily-digest

404

yinjialu/ai-frontier-daily

Skill Claude CodeCodex

A workflow for collecting official AI-vendor announcements and turning them into a daily news digest in Chinese. It creates image cards for Xiaohongshu, a Chinese social platform, and WeChat Official Accounts, then updates a GitHub Pages review page and can send a phone notification.

not rated 6 6d ago A 132 tokens

stark-ydq/voice-to-instrument-skills

Skill Claude CodeCodex

Expert guidance for converting voice recordings into realistic instrument sounds using AI tools. Use this skill whenever a user asks about voice-to-instrument conversion, how to record voice input for music AI, which instrument suits their voice, prompt engineering for text-to-music tools, or troubleshooting common…

not rated 6 5mo ago A 69 tokens original MIT

collab-proof

406

dong7812/collab-proof

Skill Claude Code

Surfaces AI collaboration evidence the developer didn't consciously record. Vela 3-layer pipeline × ADHD 4-frame reasoning — prompt-native, zero dependencies.

not rated 6 3mo ago A 0 tokens

pdf-jp

407

LinkX-Japan/ai-souken-workflows

Skill Claude CodeCodex

A tool for creating Japanese-language PDF documents with embedded Japanese fonts, vertical writing, business templates, and inkan images. An inkan is a Japanese personal or company seal.

not rated 6 6mo ago A 67 tokens

bridge-commons

408

mikeng-io/agent-skills

Skill Claude CodeCodex

Shared contract for all bridge adapters — pre-flight SOP, standardized input/output schemas, artifact format, and status semantics. Read by any bridge or orchestrating skill. Not invocable standalone.

not rated 6 3mo ago A 41 tokens

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: