ZooWork
ZooWork Market

发现 Skills

为真实工作流程挑选经过整理的 Skill,连接、安装并开始使用。

◇

slack-gif-creator

DP-Skills

Toolkit for creating animated GIFs optimized for Slack, with validators for size constraints and composable animation primitives. This skill applies when users request animated GIFs or emoji animations for Slack from descriptions like "make me a GIF for Slack of X doing Y."

◇

agent-harness-construction

dpthinh910

Design and optimize AI agent action spaces, tool definitions, and observation formatting for higher completion rates.

◇

enterprise-agent-ops

dpthinh910

Operate long-lived agent workloads with observability, security boundaries, and lifecycle management.

◇

chompute-shopify-inventory-forecast

dragonfruit-ai

Forecast Shopify stockout timing and reorder recommendations from 12 months of order history.

◇

learning-by-making

Dragoon0x

Build taste through volume of output, deliberate failure, and speed. Taste cannot be developed by watching. It's sharpened by making, failing, and making again. Use when designing practice routines, breaking through creative blocks, or helping someone move from analysis to execution.

◇

mcp-auth-exploitation

dreadnode

Exploit MCP authorization flows — CIMD SSRF via client_manifest_uri/logo_uri/jwks_uri, Dynamic Client Registration abuse, token scope inflation in multi-agent chains, confused deputy attacks. Use when target exposes MCP authorization, OIDC Dynamic Client Registration (RFC 7591), or multi-agent token delegation.

◇

web-cache-deception-path

dreadnode

Web cache deception via path delimiter confusion between CDN/cache and origin server. Use when CDN (Cloudflare, Akamai, Fastly, CloudFront) or cache layer detected.

◇

Skill: Clean Code Linter

DreamShip-Pirates

Run before every commit to ensure "Clean Code" principles.

◇

build-modify

dr-robert-li

Session-aware per-step execution engine for /modify — surgical theme edits, WP-CLI content/plugin changes, lazy Docker startup, and versioned output on session completion

◇

llm-wiki

drvoss

Use when research or domain knowledge keeps getting rediscovered across sessions — build a supplementary markdown wiki that compounds synthesized knowledge without replacing GitHub or committed project guidance

◇

git-workflow-and-versioning

dsj1984

Structures Git workflow practices. Use when making any code change—when committing, branching, resolving conflicts, or organizing work across multiple parallel streams.

◇

mobile-design

duclm1x1

A mobile-first design and engineering doctrine for iOS and Android apps. Covers touch interaction, performance, platform conventions, offline behavior, and mobile-specific decision-making. Teaches principles and constraints, not fixed layouts. Use for React Native, Flutter, or native mobile apps.

◇

nest-devices

duclm1x1

Control Nest smart home devices (thermostat, cameras, doorbell) via the Device Access API. Use when asked to check or adjust home temperature, view camera feeds, check who's at the door, monitor rooms, or set up temperature schedules.

◇

set-reminder

duclm1x1

Use when user wants to be reminded about something at a specific time or recurring schedule. Creates cron-based reminders delivered via iMessage, Discord, or other configured channels.

◇

Dzeder-grilling-chipmunks-benchmark

dzeder

../gstack/benchmark/SKILL.md

◇

Context Manager Skill

dzeder

Manage context window budgets per agent. Track token usage across prompts, tool results, and conversation history to prevent context overflow and optimize cost.

◇

Dzeder-grilling-chipmunks-prompt-loader

dzeder

../../../skills/claude/prompt-loader/SKILL.md

◇

sf-ai-agentforce-persona

dzeder

Deep persona design for Agentforce agents with 50-point scoring. TRIGGER when: user designs agent personas, defines agent personality/identity, creates persona documents, encodes persona into Agentforce Builder fields or Agent Script, translates brand guidelines to agent voice, or asks about agent tone/voice/register. DO NOT TRIGGER when: building agent metadata (use sf-ai-agentforce), testing agents (use sf-ai-agentforce-testing), or Agent Script DSL (use sf-ai-agentscript).

◇

sf-ai-agentforce-testing

dzeder

Agentforce agent testing with a dual-track workflow and 100-point scoring. TRIGGER when: user tests Agentforce agents, runs sf agent test commands, creates test specs, validates topic routing, or analyzes agent test coverage. DO NOT TRIGGER when: Apex unit tests (use sf-testing), building agents (use sf-ai-agentforce), or Agent Script DSL (use sf-ai-agentscript).

◇

valid-skill

DZMing

Duplicate of project-level skill; should be deduplicated

◇

gog-slides

echonoshy

用 gog 读/创建/改 Google Slides。**先读 gog-shared**。create/update/delete/find-replace/batch-update **必须先 AskUser 确认 + 优先 --dry-run**。典型:从 markdown 生成演示文稿骨架、按 template 替换占位符、导出 PDF。

◇

notion-shared

echonoshy

Notion CLI (ntn) 共享基础:鉴权状态检查、NOTION_API_TOKEN 来源说明、权限错误处理(Integration 未 share 到目标 page/database)、self-documenting 原则、安全规则。当用户第一次调用 ntn、遇到 401/403/object_not_found、需要新建 Notion Integration、首次使用 Notion skill 时触发。

◇

Agent Execution Manager

eclipse-du

Defines strict protocols for how the agent executes tasks and interacts with the user for approval.

◇

Customize Performance Criteria with Examples

ECNU-ICALK

Rewords or paraphrases performance criteria for training contexts and adds concrete, observable workplace examples to strengthen assessment context.

performance criteriacustomizationtrainingassessment
上一页第 756 / 1466 页下一页