自动化
工作流自动化与调度
google-zx-scripting
damusix
"Use when writing shell scripts, automation, build tools, file processing, CLI tools, deployment scripts, data pipelines, or batch operations with Google's zx library. Also covers piping, streams, parallel execution, retries, cross-platform scripting, built-in fs utilities, and minimist argument parsing."
Task Lifecycle — Agent PM System
Aura-Industry
Full spec: public/agent-project-management.md
ocas-finch
indigokarasu
'OCAS self-improvement orchestrator (Darwin''s finch — adaptive evolution).
ralph
snarktank
"Convert PRDs to prd.json format for the Ralph autonomous agent system. Use when you have an existing PRD and need to convert it to Ralph's JSON format. Triggers on: convert this prd, turn this into ralph format, create prd.json from this, ralph json."
prd
snarktank
"Generate a Product Requirements Document (PRD) for a new feature. Use when planning a feature, starting a new project, or when asked to create a PRD. Triggers on: create a prd, write prd for, plan this feature, requirements for, spec out."
human-writing
doodledood
'Research-backed principles for writing prose that avoids AI tells. Apply when writing articles, blog posts, emails, marketing copy, social media, or any prose content. Covers vocabulary, structure, tone, rhythm, and craft techniques that make writing feel authentically human. Not for code, commit messages, or technical documentation.'
phone-calls
Merit-Systems
Make AI phone calls, buy phone numbers, and get call transcripts via x402. USE FOR: - Making AI-powered outbound phone calls - Scheduling calls and getting transcripts - Buying and managing phone numbers - Leaving voicemails - Transferring calls to humans TRIGGERS: - "call", "phone call", "make a call", "dial" - "buy number", "phone number", "get a number" - "voicemail", "leave a message" - "transcript", "call recording", "call summary" - "AI call", "automated call", "bland" ALWAYS use agentcash.fetch for stablephone.dev endpoints. IMPORTANT: Use exact endpoint paths from the Quick Reference table below.
openclaw-auto-dream
LeoYeAI
"Automatic memory consolidation and maintenance for OpenClaw agents — the 'Auto-dream' system. Periodically reviews daily memory logs (memory/YYYY-MM-DD.md), extracts valuable insights, consolidates them into long-term memory (MEMORY.md), and prunes stale or redundant entries. Use when: (1) setting up automatic memory maintenance for an OpenClaw instance, (2) user asks for 'auto memory', 'memory cleanup', 'memory consolidation', 'dream', 'auto-dream', or 'memory maintenance', (3) agent needs to run a scheduled memory review cycle, (4) user wants to configure how their agent manages long-term memory. Powered by MyClaw.ai (https://myclaw.ai) — the AI personal assistant platform that gives every user a full server with complete code control."
atelier-spec-methodology
martinffx
AgentOS 3-layer context, orchestrated delegation, and OpenSpec living specifications. Use when explaining how context flows through layers, how agents collaborate, or how specs evolve.
model-evaluation-benchmark
rysweet
Automated reproduction of comprehensive model evaluation benchmarks following the Benchmark Suite V3. Auto-activates for model benchmarking, comparison evaluation, or performance testing between AI models.
default-workflow
rysweet
Development workflow for features, bugs, refactoring. Auto-activates for multi-file implementations.
investigation-workflow
rysweet
6-phase investigation workflow for understanding existing systems. Auto-activates for research tasks. Optimized for exploration and understanding, not implementation. Includes parallel agent deployment for efficient deep dives and automatic knowledge capture to prevent repeat investigations.
docx
rysweet
Create, edit, and analyze Word documents with tracked changes support
knowledge-extractor
rysweet
Extracts key learnings from conversations, debugging sessions, and failed attempts. Use at session end or after solving complex problems to capture insights. Stores discoveries in memory (via amplihack.memory.discoveries), suggests PATTERNS.md updates, and recommends new agent creation. Ensures knowledge persists across sessions via Kuzu memory backend.
meeting-synthesizer
rysweet
Processes meeting notes or transcripts to extract structured information. Use after meetings to quickly generate action items, capture decisions, and create follow-up tasks. Extracts: action items with owners, decisions made, key discussion points, follow-up tasks with priorities.
learn-this
michalparkola
Unified content extraction and action planning. Use when user says "learn-this <URL>", "learn this <URL>", "weave <URL>", "help me plan <URL>", "extract and plan <URL>", "make this actionable <URL>", or similar phrases indicating they want to extract content and create an action plan. Automatically detects content type (YouTube video, article, PDF) and processes accordingly.
skill-name
AgentSecOps
[REQUIRED] Comprehensive description of what this skill does and when to use it. Include: (1) Primary functionality, (2) Specific use cases, (3) Security operations context. Must include specific "Use when:" clause for skill discovery. Example: "SAST vulnerability analysis and remediation guidance using Semgrep and industry security standards. Use when: (1) Analyzing static code for security vulnerabilities, (2) Prioritizing security findings by severity, (3) Providing secure coding remediation, (4) Integrating security checks into CI/CD pipelines." Maximum 1024 characters.
recon-nmap
AgentSecOps
Network reconnaissance and security auditing using Nmap for port scanning, service enumeration, and vulnerability detection. Use when: (1) Conducting authorized network reconnaissance and asset discovery, (2) Enumerating network services and identifying running versions, (3) Detecting security vulnerabilities through NSE scripts, (4) Mapping network topology and firewall rules, (5) Performing compliance scanning for security assessments, (6) Validating network segmentation and access controls.
begin-implementation
leeovery
"Bridge skill for the feature pipeline. Runs pre-flight checks for implementation and invokes the technical-implementation skill. Called by continue-feature — not directly by users."
technical-implementation
leeovery
"Orchestrate implementation of plans using agent-based TDD workflow with per-task review and approval gate (auto mode available). Use when: (1) Implementing a plan from .workflows/planning/{topic}/plan.md, (2) User says 'implement', 'build', or 'code this' with a plan available, (3) Ad hoc coding that should follow TDD and quality standards, (4) Bug fixes or features benefiting from structured implementation. Dispatches executor and reviewer agents per task, commits after review approval."
start-planning
leeovery
"Start a planning session from an existing specification. Discovers available specifications, gathers context, and invokes the technical-planning skill."
migrate
leeovery
"Run migrations to keep workflow files in sync with the current system design. This skill is mandatory before running any workflow skill."
technical-review
leeovery
"Validate completed implementation against plan tasks and acceptance criteria. Use when: (1) Implementation is complete, (2) User wants validation before merging/shipping, (3) Quality gate check needed after implementation. Reviews ALL plan tasks for implementation correctness, test adequacy, and code quality. Produces structured feedback (approve, request changes, or comments) - does NOT fix code."
start-implementation
leeovery
"Start an implementation session from an existing plan. Discovers available plans, checks environment setup, and invokes the technical-implementation skill."