Skip to main content

Claude skills and prompts

Claude assistants and Claude Code workflows. This directory includes agent skill packages and prompt templates; each card identifies its type. A prompt template is copied from its source, while a skill package needs the appropriate agent setup. Compatibility may be inferred from the content unless a recorded test is linked.

Active filters:Agent skillsClear all
codingAgent skill

Product Capability

Translate PRD intent, roadmap asks, or product discussions into an implementation-ready capability plan that exposes constraints, invariants, interfaces, and unresolved decisions before multi-service work starts. Use when the user needs an ECC-native PRD-to-SRS lane instead of vague planning prose.

Content score 74/100 · provisional302k
View skill
codingAgent skill

Safety Guard

Guard against destructive operations with three modes: Careful intercepts dangerous commands (rm -rf, git push --force, DROP TABLE) for confirmation, Freeze locks writes to one directory, and Guard combines both. Advisory: the agent applies these rules itself; no hook ships with it. Use when working on production systems, running agents autonomously, restricting edits to a directory, or during migrations, deploys, and data changes.

Content score 74/100 · provisional303k
View skill
codingAgent skill

Shep Kit:Status

Quick feature status and "what to do next" guide. Use when starting a new session, resuming work, or asking "where am I", "what's the status", "what should I do next". Gives a zero-to-hero walkthrough of the current feature branch. Part of the Shep autonomous SDLC platform — https://shep.bot

Content score 74/100 · provisional278
View skill
codingAgent skill

Token Budget Advisor

Offer a choice of response depth (25%/50%/75%/100%) with token estimates before answering, then answer at that level. Use when the user asks to control response length or token budget, such as 'token budget', 'short version', 'brief answer', 'respuesta corta vs larga', 'cuántos tokens', 'ahorrar tokens', 'responde al 50%', 'dame la versión corta', 'quiero controlar cuánto usas'. Skip if depth is already set this session or 'token' means an auth/payment token.

Content score 74/100 · provisional303k
View skill
productivityAgent skill

Unified Notifications Ops

Operate notifications as one ECC-native workflow across GitHub, Linear, desktop alerts, hooks, and connected communication surfaces. Use when the real problem is alert routing, deduplication, escalation, or inbox collapse.

Content score 74/100 · provisional303k
View skill
codingAgent skill

Gateguard

PreToolUse fact-forcing gate that denies the first Edit/Write/Bash (including MultiEdit and NotebookEdit) attempt until the agent presents concrete facts (importers, data schemas, verbatim user instruction), then allows retry; A/B-tested at +2.25 quality points. Use when enabling or configuring the GateGuard hook, exempting paths via env vars, or handling first-touch denials.

Content score 73/100 · provisional301k
View skill
codingAgent skill

Perseus

Use when you need live project state (git branch, service health checks, recent sessions, task board, env vars, agent inbox) injected into context BEFORE the AI reads it. Perseus is a compile-before-context engine — it runs directives like @query, @services, @waypoint, @agora and hands the assistant a fully-resolved markdown briefing. Use for: deterministic session starts, multi-agent coordination, workspace audits, and anywhere you want "all the facts first."

Content score 73/100 · provisional43
View skill
codingAgent skill

Skill Host Compat

Lint ECC skills for Codex/Cursor-safe frontmatter and Claude-only substitutions before a skill PR.

Content score 73/100 · provisional303k
View skill
productivityAgent skill

Workflow Template Assistant Guide

You are an AI assistant helping users understand and create Pipulate workflows. When users interact with the Hello World workflow, your job is to:

Content score 73/100 · provisional14
View skill
productivityAgent skill

Anthropicadministrator Automation

Automate Anthropic Admin tasks via Rube MCP (Composio): API keys, usage, workspaces, and organization management. Always search tools first for current schemas.

Content score 72/100 · provisional80k
View skill
creativityAgent skill

Artifacts Builder

Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.

Content score 72/100 · provisional80k
View skill
codingAgent skill

Ashby Automation

Automate recruiting and hiring workflows in Ashby -- manage candidates, jobs, applications, interviews, and notes through natural language commands.

Content score 72/100 · provisional80k
View skill
productivityAgent skill

Attio Automation

Automate Attio CRM operations -- search records, query contacts and companies with advanced filters, manage notes, list attributes, and navigate your relationship data -- using natural language through the Composio MCP integration.

Content score 72/100 · provisional80k
View skill
productivityAgent skill

Capsulecrm Automation

Automate Capsule CRM tasks via Rube MCP (Composio): contacts, opportunities, cases, tasks, and pipeline management. Always search tools first for current schemas.

Content score 72/100 · provisional80k
View skill
codingAgent skill

Connect Apps

Connect Claude to external apps like Gmail, Slack, GitHub. Use this skill when the user wants to send emails, create issues, post messages, or take actions in external services.

Content score 72/100 · provisional80k
View skill
analysisAgent skill

Customer.Io Automation

Automate customer engagement workflows including broadcast triggers, message analytics, segment management, and newsletter tracking through Customer.io via Composio

Content score 72/100 · provisional80k
View skill
writingAgent skill

Dataset Curation

Prepare, format, and validate datasets for supervised fine-tuning and preference training. Use when converting raw data into training format, applying chat templates, configuring sequence packing, generating synthetic training data, or writing a dataset card before a run.

Content score 72/100 · provisional43k
View skill
productivityAgent skill

Dockerhub Automation

Automate Docker Hub tasks via Rube MCP (Composio): repositories, images, tags, and container registry management. Always search tools first for current schemas.

Content score 72/100 · provisional80k
View skill
creativityAgent skill

ElevenLabs Automation

Automate ElevenLabs text-to-speech workflows -- generate speech from text, browse and inspect voices, check subscription limits, list models, stream audio, and retrieve history via the Composio MCP integration.

Content score 72/100 · provisional80k
View skill
codingAgent skill

Evaluation Methodology

PluginEval quality methodology, covering dimensions, rubrics, and scoring formulas. Use this skill when understanding how plugin quality is measured, when interpreting a low score on a specific dimension, when deciding how to improve a skill's triggering accuracy or orchestration fitness, when setting score thresholds for your marketplace, or when explaining quality badges to external partners like Neon.

Content score 72/100 · provisional43k
View skill
productivityAgent skill

Excel Automation

Excel Automation: create workbooks, manage worksheets, read/write cell data, and format spreadsheets via Microsoft Excel and Google Sheets integration

Content score 72/100 · provisional80k
View skill
productivityAgent skill

Google Admin Automation

Automate Google Workspace Admin tasks via Rube MCP (Composio): manage users, groups, memberships, suspend accounts, create users, add aliases. Always search tools first for current schemas.

Content score 72/100 · provisional80k
View skill
codingAgent skill

Google Maps Automation

Automate Google Maps tasks via Rube MCP (Composio): geocode addresses, search places, get directions, compute route matrices, reverse geocode, autocomplete, get place details. Always search tools first for current schemas.

Content score 72/100 · provisional80k
View skill
productivityAgent skill

Google Search Console Automation

Automate Google Search Console tasks via Rube MCP (Composio): query search analytics, list sites, inspect URLs, submit sitemaps, monitor search performance. Always search tools first for current schemas.

Content score 72/100 · provisional80k
View skill