Automation
Task automation and scripting
model-evaluation-benchmark
by 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
by rysweet
Development workflow for features, bugs, refactoring. Auto-activates for multi-file implementations.
investigation-workflow
by 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
by rysweet
Create, edit, and analyze Word documents with tracked changes support
knowledge-extractor
by 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
by 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
by 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
by 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
by 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
by 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
by 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
by leeovery
"Start a planning session from an existing specification. Discovers available specifications, gathers context, and invokes the technical-planning skill."
migrate
by 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
by 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
by leeovery
"Start an implementation session from an existing plan. Discovers available plans, checks environment setup, and invokes the technical-implementation skill."
status
by leeovery
"Show workflow status - what exists, where you are, and what to do next."
start-review
by leeovery
"Start a review session from an existing plan and implementation. Discovers available plans, validates implementation exists, and invokes the technical-review skill."
view-plan
by leeovery
"View a plan's tasks and progress, regardless of output format."
wix-cli-embedded-script
by wix
Use when adding tracking code, advertising pixels, third-party integrations, or client-side JavaScript to sites. Triggers include embed, inject, script, third-party integration, DOM injection.
link-dependencies
by leeovery
"Scan all plans and wire up cross-topic dependencies. Finds unresolved external dependencies, matches them to tasks in other plans, and updates both the plan index and output format."
mesh-generation
by HeshamFS
Plan and evaluate mesh generation for numerical simulations. Use when choosing grid resolution, checking aspect ratios/skewness, estimating mesh quality constraints, or planning adaptive mesh refinement for PDE discretization.
time-stepping
by HeshamFS
Plan and control time-step policies for simulations. Use when coupling CFL/physics limits with adaptive stepping, ramping initial transients, scheduling outputs/checkpoints, or planning restart strategies for long runs.
background-job-processing
by aj-geddes
Implement background job processing systems with task queues, workers, scheduling, and retry mechanisms. Use when handling long-running tasks, sending emails, generating reports, and processing large datasets asynchronously.
batch-processing-jobs
by aj-geddes
Implement robust batch processing systems with job queues, schedulers, background tasks, and distributed workers. Use when processing large datasets, scheduled tasks, async operations, or resource-intensive computations.