automate a workflow
846 capabilities · page 9 of 15
Individual capabilities
- new-rfc
Draft an answer-first RFC in docs/rfc/: research and resolve the proposal before writing it, then give a reviewer a concise, decidable argument rather than an audit trail.
- workspace-status
Read the local workspace.toml and surface the current queue state across all active initiatives.
- ship
Manual invocation: When ready to release a new version - After feature completion: Before tagging and publishing - Before version…
- bottleneck-hunter
The publisher’s description is only a heading. Open the skill to read what it does.
- verification-gates
Creates explicit validation checkpoints (verification gates) between project phases to catch errors early and ensure quality before proceeding.
- map-codebase
Bootstrap LID in an existing (brownfield) codebase.
- create-agent-template
Generate Harness Agent Template files for AI-powered automation agents.
- manage-roles
Manage Harness RBAC roles, role assignments, permissions, and resource groups via MCP v2 tools.
- analyst-research
End-to-end research workflow skill for investment analysts and policy researchers.
- adequacy-assessment
Guides assessment of third-country adequacy decisions under GDPR Article 45 for international data transfers.
- age-verification-methods
Evaluates and implements age estimation and verification technologies for online services.
- ai-dpia
Conducts Data Protection Impact Assessments for AI and ML systems per EDPB Guidelines 04/2025 on AI processing.
- ai-federated-learning
Implements federated learning architecture patterns for GDPR compliance.
- ai-model-privacy-audit
Conducts privacy auditing of AI models including training data extraction testing, membership inference attacks, model inversion testing,…
- ai-privacy-assessment
Guides the combined DPIA and AI Act conformity assessment for AI systems processing personal data.
- ai-training-data-class
Classifies sensitive data in AI/ML training datasets including bias detection for Art.
- ai-training-lawfulness
Assesses lawful basis for AI training data processing per EDPB April 2025 report on LLMs and general-purpose AI.
- ai-transparency-reqs
Implements AI transparency requirements under EU AI Act Arts.
- ai-vendor-privacy-due
Determines controller-processor relationships for AI services and conducts privacy due diligence.
- anonymization-alternative
Evaluates anonymization as a retention alternative under GDPR Recital 26, applying the WP29 Opinion 05/2014 techniques including…
- applying-privacy-design-patterns
Systematic application of the eight privacy design patterns per Hoepman: minimize, hide, separate, abstract, inform, control, enforce, and…
- auto-deletion-workflow
Implements automated data deletion workflows for GDPR Article 17 right to erasure and retention period expiry.
- litestar-autowire
Auto-activate for litestar_autowire, AutowirePlugin, AutowireConfig, domain_packages, AutowireIntegration, AutowireLoader, or…
- mk:fix
Diagnoses and fixes bugs, type errors, lint failures, CI/CD issues, and runtime errors via root-cause-first investigation.
- mk:playwright-cli
Session-persistent browser automation via Playwright CLI — form filling, screenshots, data extraction, multi-step flows.
- mk:ship
Ship workflow with explicit scopes: prepare stages and commits locally; release pushes and creates a PR; publish manages issues and versioning.
- gentech-blockrun
GenTech Labs' integration patterns for BlockRun MCP from Hermes Agent.
- higgsfield-recall
Higgsfield Recall — Pre-Generation Memory Check
- gallery-scraper
Bulk download images from login-protected gallery websites using an attached browser session.
- gsc
Query Google Search Console for SEO data - search queries, top pages, CTR opportunities, URL inspection, and sitemaps.
- hr-talent
HR and talent management expertise for talent acquisition, performance management, compensation strategy, organizational design, culture building,…
- leadership
Executive leadership expertise for decision-making, change management, crisis management, stakeholder management, team building, and organizational…
- rd-management
R&D management expertise for R&D portfolio management, technology roadmapping, research methodology, patent strategy, lab management, academic…
- answer-memory
Manage Job Apply's local profile, reusable answers, application history, and resumable sessions.
- paper-reading-zh
中文论文精读工作流。Use when the user provides a paper anchor such as a PDF, arXiv/OpenReview/ACM/IEEE/venue page link, paper title, abstract/full…
- company-diligence
The publisher’s description is only a heading. Open the skill to read what it does.
- prospect-researcher
Research a target company or person deeply enough to craft outreach that demonstrates genuine understanding — not generic "I saw your profile and thought we'd be a great fit." Produce actionable intelligence: what they care about, what prob
- mk:autobuild
mk:autobuild — Autonomous Multi-Hour Build Orchestration
- mk:bootstrap
End-to-end project orchestrator: research → design → plan → scaffold → implement → docs.
- mk:evaluate
Experimental behavioral evaluator.
- mk:figma
Read-first Figma gateway via Figma MCP: analyze designs, implement Figma-to-code for 1–3 screens, extract design tokens, produce a Figma…
- mk:investigate
Systematic debugging with root cause investigation.
- mk:jira
Routing skill — recommends the correct mk:jira-* leaf for any Jira task.
- ponytail-gain
Show ponytail's measured impact as a compact scoreboard: less code, less cost, more speed, from the benchmark medians.
- gws-shared
gws CLI: Shared patterns for authentication, global flags, and output formatting
- daily-trending
Fetch today's trending topics from tophub.today across multiple platforms.
- robot-bringup
Bringing up a complete ROS2 system on a robot's onboard computer: systemd services, launch file composition, ordered startup, and production monitoring.
- robot-perception
Comprehensive best practices for robot perception systems covering cameras, LiDARs, depth sensors, IMUs, and multi-sensor setups.
- robotics-design-patterns
Architecture patterns, design principles, and proven recipes for building robust robotics software.
- robotics-software-principles
Foundational software design principles applied specifically to robotics module development.
- ros1
Best practices, design patterns, and common pitfalls for ROS1 (Robot Operating System 1) development.
- ros2
Comprehensive best practices, design patterns, and common pitfalls for ROS2 (Robot Operating System 2) development.
- ros2-web-integration
Patterns and best practices for integrating ROS2 systems with web technologies including REST APIs, WebSocket bridges, and browser-based robot interfaces.
- amq-spec
Parallel-research-then-converge design workflow between two agents.
- at-email-cli
Use the AgentTeam Email CLI command at-email to operate an agent mailbox.
- changelog-scan
Scan recent merges to main (and noteworthy direct commits) since a given window (last tag or date in state).
- loop-constraints
Read loop-constraints.md at the start of every run and enforce every rule.
- pr-review-triage
Triage open pull requests for CI status, review comments, and merge readiness.
- cron-manager
The publisher’s description is only a heading. Open the skill to read what it does.
- daily-brief
Operational knowledge for the daily-brief digest pipeline (this project).
