Agent Workflow Claude Skills
4 122 agent workflow skills from 665 authors. They configure the agents themselves: memory, prompts, context and other skills. Half of them fit into 1 844 tokens or less — that is what one costs your context window when the agent loads it. 778 ship runnable scripts rather than instructions alone. 5 of them cannot work without an MCP server, most often task. We also found 589 copies of these same skills sitting in other people's repositories — counted once here, not 589 times.
4 122 unique 665 authors 4 updated this month 506 from vendors
> Show per-session token usage breakdown. Run /token-usage or /token-usage 30 to see usage over N days.
Design and implement App Intents, AppEntity, EntityQuery, and App Shortcuts for iOS system surfaces such as Shortcuts, Siri, Spotlight, widgets, controls, and app handoff routes.
Use when auditing a repo before changes to find the smallest safe PR, quality risks, stale docs, missing tests, ignored-file gaps, or agent setup issues. Best first skill for unfamiliar codebases.
Design or audit prosocial experiences in session-based multiplayer games using a three-phase chapter model built around Setup, Little Loops, and Long Tail. Use when evaluating co-op games, team shooters, MOBAs, mission-based multiplayer, or other repeat-session formats; when planning how to prime trust before play, reinforce repeatable prosocial actions during play, and carry positive social momentum across sessions; or when a multiplayer game feels socially flat, hostile, forgettable, or unable to turn one good match into another.
Rewrite a rough prompt into a polished, model-specific prompt grounded in the official Anthropic prompting guides. Use when the user invokes prompt-polish, types an invocation like "prompt-polish/FABLE 5/[prompt]" or "prompt-polish/OPUS 4.8/[prompt]", or asks to polish, improve, rewrite, optimize, or tune a prompt for a named model ("make this prompt better for Fable 5", "tune this for Opus"). Supports Claude Fable 5 and Claude Opus 4.8 (Opus 4.7 routes to 4.8 guidance). If no draft prompt is provided, ask for it rather than inventing one.
Identify conflicting rules between two lists of extracted rules. Use this skill when comparing a skill's rules against another skill's rules or against agent config rules (CLAUDE.md, GEMINI.md, etc.).
Design and validate Hermes Agent profile distributions, including SOUL.md, distribution.yaml, skills, config, MCP stubs, and release readiness.
Turn a simple profile idea into a mature, production-quality Hermes profile prompt and generation brief.
Создание, улучшение и аудит скиллов и агентов OpenClaw. Три режима: создание скилла (11 шагов), создание агента (9 шагов, с памятью и автоулучшением), улучшение существующего (5 шагов). Triggers: 'создай скилл', 'новый скилл', 'создай агента', 'новый агент', 'улучши скилл', 'skill creator', 'agent creator', 'скиллмейкер'.
Run configurable BMAD pipeline for story delivery using subagent
> Generalised autonomous optimisation loop — soft RLVR for any artifact a user can project-pack, none. Never assumes subprocess access or unrestricted local files. Use this skill whenever a user wants to iteratively improve an artifact — code, prompts, documents, configs, designs, content — by running structured experiments, evaluating results against a multi-dimensional rubric, and learning good", "run experiments on", "autoresearch", "iterate on this overnight", "try different approaches and pick the best", or any request implying repeated evaluate-and-improve cycles.
Use when creating storyboards from scripts, generating visual prompts for beat boards or sequence boards, or converting narrative beats into AI-generated images across platforms (Nano Banner, Midjourney, Gemini)
Use when converting static image sequences (sequence boards) into motion prompts for AI video generation platforms (Runway, Pika, SVD), or describing temporal movement for video synthesis
Use when reviewing storyboard outputs at any production stage (beat breakdown, beat board, sequence board, motion prompts), providing quality assurance feedback, or identifying revision requirements for Director agent
Use when starting a session on an existing WordPress site, or when the user says 'prime yourself', 'what builder does this site use', or 'give me a site briefing'. Loads the active site, detects the builder, loads inline schemas, reads the stored per-site brief, and sets the do-not-write-raw-HTML rule.
Use when the user says 'make my store visible to chatgpt', 'set up product feeds', or 'make my store agent-ready', or asks about Google Merchant Center, a store llms.txt, or cart links for AI agents. Sets up product feeds in six formats and registers the catalog with the major platforms.
> Standalone skill for multi-perspective PLC code security and quality analysis. "code review", "check this code", "is this safe", "find issues" when combined with PLC, SCL, ST, LAD, FBD, Structured Text, or block context. Also triggers when the user pastes PLC code and asks for feedback, or uploads exported SimaticML XML files. This skill is independent of tia-openness-roadmap — it does not perform engineering automation. It analyzes code that has already been exported, pasted, or is accessible via the TIA Portal MCP server.
> Use when the TIA Portal MCP server is available for focused, guarded project reads and writes. Use TIA Openness skills for complex multi-step automation.
>- Deep-read long books and papers using Mortimer Adler's inspectional / analytical / syntopical method, the Recite step from SQ3R, and S. Keshav's three-pass method for papers, with page-anchored notes as external memory so the agent never has to load the whole text into one context window. Use this skill whenever the user asks to read, study, summarize, analyze, review, or answer questions about a long book, textbook, PDF, EPUB, thesis, dissertation, survey paper, or any document of roughly 50+ pages. Also use it when a `<slug>-notes/` workspace from a previous session already sits next to a source file and the user asks a follow-up question about that book — search the existing notes before re-reading anything. Trigger on these requests in whatever language the user writes them — for example Vietnamese "đọc sách", "tóm tắt sách", "phân tích luận án", or equivalent phrasing in any other language. Do not use this skill for short documents (under ~30 pages) that fit comfortably in context — read those directly instead; the pipeline is overhead they don't need.
> A C-level strategy advisory board, run as a team of named specialist agents, that takes an executive from a raw strategic question to a defended, board-ready recommendation. Use this skill whenever the user faces a significant business decision or wants strategic analysis — market entry, build-vs-buy, M&A, digital transformation, annual planning, portfolio prioritization, pricing, a big investment, a competitive threat, a turnaround. Trigger on requests like "should we invest in / build / buy / enter…", "develop a strategy for…", "evaluate this opportunity", "make the business case", "stress-test this plan", "run a pre-mortem", or "prepare a board presentation" — in any language, even when the user doesn't say the word "strategy". Also trigger when the user names a board member (Drucker, Porter, Christensen, Graham, Grove, Wack, Taleb, Minto) or asks to convene the board / open a boardroom session.
Create high-quality, model-aware system prompts for any LLM (Claude, GPT, Gemini, open-source, etc.). Use this skill whenever the user wants to create, write, build, design, draft, or improve a system prompt, system instructions, or custom instructions for any AI model. Also trigger when the user asks about prompt engineering, prompt design, prompt optimization, or wants to define behavior for an AI assistant, chatbot, agent, or any LLM-powered application — even if they don't explicitly say "system prompt". Covers all use cases including chatbots, agentic systems, tool-use workflows, content generation, data extraction, code assistants, and multi-turn conversations.
> Investigate distributed traces and spans in OpenSearch. Use this skill when the user wants to analyze traces, investigate slow spans, find error spans, track agent invocations, measure token usage, reconstruct trace trees, query service maps, or debug distributed systems through trace data. Activate even if the user says traceId, spanId, OpenTelemetry, OTel, distributed tracing, latency, span duration, service map, or trace investigation without mentioning OpenSearch.
Compact the current conversation into a handoff document for another agent to pick up.
> Implementation subagent dispatch patterns. Use when independent implementation work is available and subagents can execute it. Covers parallel dispatch, shared-tree patch snapshots, one combined review per completed batch, and serial integration.
> SOC Analyst role bundle covering Tier 1 through Tier 3 operations. Orchestrates alert triage, threat hunting, incident investigation, and detection engineering workflows. Auto-invoked when the user needs help with security monitoring, alert analysis, threat hunting hypotheses, incident timelines, or detection rule development. Sequences the appropriate security skills based on the operational engagement type.
> Virtual CISO role bundle for organizations without a full-time CISO. Orchestrates security program assessment, compliance readiness, risk management, and board-level reporting. Auto-invoked when the user asks for security program guidance, compliance assessment, risk posture evaluation, or board reporting preparation. Sequences the appropriate security skills based on engagement type.
> AI agent skill for the DevExpress WinForms PivotGridControl. Covers NuGet setup, data binding (DataSourceColumnBinding, ExpressionDataBinding, OLAP), field areas and layout, summaries, grouping, sorting, filtering, conditional formatting (FormatRules), and appearance customization. Use for any DevExpress WinForms PivotGridControl cross-tabular analysis scenario.
XPO-specific CRUD and business logic patterns for XAF applications. Sub-skill of devexpress-xaf-business-logic — load this when XPO ORM is detected. Covers UnitOfWork, Session, XPCollection, XPQuery (LINQ to XPO), XPView, NestedUnitOfWork, XPObjectSpace.Session access, AfterConstruction/OnSaving/OnDeleting/OnLoaded overrides, SetPropertyValue, GetCollection, connection pooling, XPInstantFeedbackSource, XPServerCollectionSource. Use when someone mentions "UnitOfWork", "Session", "XPCollection", "XPQuery", "NestedUnitOfWork", "SetPropertyValue", "AfterConstruction", "Session.FindObject", or asks about XPO data operations in XAF.
>- XPO-specific filtering patterns for XAF applications. Sub-skill of devexpress-xaf-filtering — load when XPO ORM is detected. Covers XPCollection with CriteriaOperator, XPQuery<T> LINQ filtering, XPView for lightweight read-only queries, BinaryOperator / GroupOperator / FunctionOperator / ContainsOperator / InOperator / BetweenOperator programmatic construction, Session.FindObject, server-mode data sources (XPInstantFeedbackSource, XPServerCollectionSource), and Session.GetObjects. Use when someone mentions XPCollection criteria, XPQuery Where, Session.FindObject, or XPO filtering in XAF.
9-command agent skill suite for Tongji Look (look.tongji.edu.cn): setup, list, transcribe, take notes, manage materials, build course wiki, create cheat sheets, batch-process entire courses, and deploy course wiki to GitHub Pages.
1C:Enterprise (1С:Предприятие) development tools via EDT MCP server — BSL code analysis, metadata inspection, module navigation, error checking, debugging, configuration management. Use when working with 1C code, BSL modules, 1C metadata, 1C queries, 1C forms, or any 1C:Enterprise development task.
> Erstellt detaillierte, autonome Claude Code (CC) Prompts mit Self-Fix-Protokoll. Nutze diesen Skill IMMER wenn der User einen CC-Prompt, Claude Code Prompt oder "Prompt für CC", "lass CC das machen", "mach einen Prompt draus", "CC soll das autonom abarbeiten", "delegate an Claude Code", "Sonnet-Prompt", "autonomer Prompt". Der Skill erzeugt token-effiziente Prompts die mit günstigeren Modellen (Sonnet) funktionieren, weil sie präzise genug sind um Rückfrage-Schleifen zu vermeiden.
| Transformiert Anforderungen in Best-Practice Prompts nach Claude 4.x Standards (Dezember 2025). Wird AUSSCHLIESSLICH per /prompt-architect aufgerufen — KEINE automatische Aktivierung. Produziert strukturierten, ausfuehrbaren Prompt mit allen Best Practices.
Recognize and capture reusable patterns, workflows, and domain knowledge from work sessions into new skills. Use when completing tasks that involve novel approaches repeated 2+ times, synthesizing complex domain knowledge across conversations, discovering effective reasoning patterns, or developing workflow optimizations. Optimizes for high context window ROI by identifying patterns that will save 500+ tokens per reuse across 10+ future uses.
Auto-generates standardized README documentation from SKILL.md files, validates consistency (frontmatter, descriptions, terminology), and creates usage examples. Use when documenting individual skills, generating docs for multiple skills in a directory, or validating skill quality standards.
Design multi-agent architectures for complex tasks. Use when single-agent context limits are exceeded, when tasks decompose naturally into subtasks, or when specializing agents improves quality.
Master workflow skill for City of Boston policy analysis and civic innovation. ALWAYS use this skill for any request involving Boston city data, city services, neighborhood equity, public policy, government performance, 311 analysis, housing, safety, transportation, or any civic issue — even if the user hasn't explicitly asked for a 'full analysis'. This skill orchestrates five sub-skills: city-problem-framing (Bloomberg-inspired), city-policy-analysis (J-PAL-inspired), city-communication (GovLab/InnovateUS-inspired), city-benchmarking (cross-city comparison using San Francisco, Seattle, and DC data), and city-performance-management (Results for America / PerformanceStat). Use this skill for: 'full analysis', 'policy brief', 'data-driven recommendation', 'city improvement project', 'investigate [issue]', 'compare Boston to other cities', 'what does the data show', 'help me write a memo about', or any request that combines problem definition, data analysis, and communication for government or civic purposes.
Build autonomous game-playing agents using AI and reinforcement learning. Covers game environments, agent decision-making, strategy development, and performance optimization. Use when creating game-playing bots, testing game AI, strategic decision-making systems, or game theory applications.
Build agents that generate creative content including music, memes, podcasts, and multimedia. Covers generative models, content synthesis, style transfer, and creative control. Use when building creative assistants, automated content creators, multimedia generators, or artistic AI systems.
Design and coordinate multi-agent systems where specialized agents work together to solve complex problems. Covers agent communication, task delegation, workflow orchestration, and result aggregation. Use when building coordinated agent teams, complex workflows, or systems requiring specialized expertise across domains.
PencilPlaybook is the UI Skills / Taste-Skill for Pencil.dev + Claude Code — a design playbook that gives Claude real perceptual psychology and senior-level guardrails so it stops producing averaged-out AI slop.
Expert customer onboarding guidance for accelerating time-to-value and ensuring successful implementations. Use when designing onboarding programs, creating kickoff frameworks, building implementation plans, or optimizing customer activation. Use for training delivery, go-live readiness, sales-to-CS handoffs, early warning detection, and tech-touch automation.
Expert product specification and documentation writer. Use when creating PRDs, user stories, acceptance criteria, technical specifications, API documentation, edge case analysis, design handoff docs, feature flag plans, or success metrics. Covers the full spectrum from high-level requirements to implementation-ready specifications.
Orchestrates translation of motion designer video specifications into working Remotion code by coordinating specialized agents. Acts as pipeline coordinator that delegates to remotion-scaffold, remotion-animation, remotion-composition, and remotion-component-gen. Use when you have a complete VIDEO_SPEC.md and need full Remotion implementation.
Cognitive training practices for AI agents — short, self-applied exercises that develop attention, calibration, deliberation, ambiguity tolerance, multi-objective stability, and memory consolidation. Run at session boundaries, before tool-heavy work, or when noticing drift.
REQUIRED for any task that involves operating a desktop application — opening apps, clicking buttons, typing into fields, pressing keys, scrolling, dragging, reading what's on screen, moving or resizing windows, or verifying state after an action. Always use the `agent-cu` CLI commands (open, snapshot, click, type, key, find, scroll, drag, batch, wait-for) instead of falling back to `open -a`, AppleScript, `osascript`, `xdotool`, `System Events`, or any other shell workaround — those can't read state back, don't verify, and are fragile across app updates. agent-cu is the canonical computer-use tool for controlling any macOS / Linux / Windows / Electron app via accessibility APIs. Trigger on prompts like "open Music and play X", "search for Y in Maps", "fill out this form", "compute in Calculator", "send a Slack message", "drag this file", "read what's in the current window", or anything where a human would click/type/look at a desktop app.
Drive the cultivar CLI to test whether an agent skill improves behavior — scaffold tasks, run with/without the skill across Claude/Copilot/Gemini (locally or on Modal), grade against a rubric, and read the results.
Use when optimizing CLAUDE.md, AGENTS.md, custom commands, or skill files — diagnose the concrete failure first, then apply current documented Anthropic best practices (explicit instructions, context/motivation, examples, output and verbosity control, thinking/effort, CLAUDE.md size and skill-description rules) instead of inventing improvements. Triggers when a prompt isn't followed, a skill won't activate, CLAUDE.md is too long or ignored, or migrating prompts to current Claude models.