Tools & Automation

Instantly.ai cold email outreach API - manage campaigns, leads, accounts, and analytics. Use for cold email automation, lead management, campaign creation/monitoring, and email account warmup.

Digital Audio Workstation usage, music composition, interactive music systems, and game audio implementation for immersive soundscapes.

Group related keywords into topic clusters. Create content hub architecture recommendations and internal linking strategies.

Track competitor blog posts, whitepapers, and content strategy. Identify content gaps in your strategy.

Audit web pages for accessibility issues in a real browser. Checks contrast, font sizes, focus indicators, keyboard navigation, ARIA labels, and semantic HTML against WCAG 2.1 AA. Reports findings with screenshots and specific remediation steps. Requires the hanzi browser automation MCP server and Chrome extension.

Instrument any external AI agent with OpenTelemetry to send traces, logs, and metrics to DataRobot for monitoring, observability, and governance. Use when adding observability to external agents or sending telemetry data to DataRobot.

A skill at the standard flat depth

A skill nested two levels deep under a category directory

A test skill with miscased filename

Validates code against known design patterns and architectural best practices.

A skill that has disable-model-invocation set but no agent references it.

Helps with deployment validation and CI/CD checks.

Performs automated code review checking for style violations and potential bugs.

This skill has frontmatter but is missing both required fields: - No `name` field - No `description` field Has optional `license` and unknown `priority` field.

Execute ONE test level (L1/L2/L3/L4) from subtask verification plan. Only run tests, do not record results. Called by autoworker:dispatch with level argument. Ends by calling autoworker:checkpoint.

Sync tracking documents based on current conversation results. Updates subtask, progress, findings, task_plan, project CLAUDE.md. Use when finishing a task or reaching a milestone.

Update subtask with fixes or new steps. Two trigger modes: (A) Auto-called by autoworker:gate-check on FAIL — reads FAIL info, adds supplementary steps. (B) User calls with a finding/bug during testing — diagnoses, fixes, updates subtask. Both modes end by invoking autoworker:dispatch to re-enter the loop.

Complete subtask verification plan: upstream traceability table + L1-L4 test plan + self-check. Call after autoworker:subtask-init. Makes subtask ready for code implementation.

Create subtask document (first half): user confirmation, goals, assumptions. Auto-runs assumption verification experiments and fills in results. Call after Gate 1.1 (user confirmation) is done, before writing any code.

Final quality gate before reporting task completion (Gate 3). Fills confidence assessment, runs supplementary verification for <95% items, completes self-check checklist. Writes PASS/FAIL result to subtask.md, then calls autoworker:dispatch for routing.

Read subtask.md checkbox state and route to next skill. The ONLY routing point in the execution loop. Called after autoworker:checkpoint, autoworker:gate-check, autoworker:subtask-update, autoworker:subtask-plan, or when resuming after context loss. When lost, call autoworker:dispatch.

Structured deep discussion for Plan Mode. Runs inside EnterPlanMode to ensure thorough questioning before writing a plan. Covers motivation, assumptions, design, acceptance criteria. Call this immediately after entering Plan Mode for any non-trivial task.

Implement ONE pending Phase from subtask plan. Only write code, do not mark checkboxes or run tests. Called by autoworker:dispatch. Ends by calling autoworker:checkpoint.

Record progress to subtask: Phase completion (from autoworker:code) or test results (from autoworker:test). Auto-detects upstream type from conversation context. Ends by calling autoworker:dispatch.

Connect any tool you use at work to your agent — including internal company tools, custom-built systems, deployment portals, incident trackers, internal knowledge bases, HR systems, and commercial tools like Slack, Confluence, Jira, Linear, GitHub, Outlook, Datadog, and PagerDuty. Use when the user wants to set up a tool connection, connect an internal or custom-built tool, or add a new tool integration from scratch.

This skill reviews Dapr Workflow code for non-determinism hazards that would cause stuck workflows on replay. Use this skill when the user asks to "review workflow for determinism", "check non-determinism in workflow", "audit Dapr workflow replay safety", or similar.

This skill reviews Dapr Workflow activity implementations for idempotency, retries, error boundaries, and convention violations. Use this skill when the user asks to "review workflow activities", "check activity idempotency", "audit Dapr activities", or similar.

This skill checks prerequisites for building Dapr Workflow apps in Python. Use this skill when the user asks to "check prerequisites for Python", "verify Python environment", or "check Python setup".

This skill checks prerequisites for building Dapr Workflow apps in .NET. Use this skill when the user asks to "check prerequisites for .NET", "verify .NET environment", or "check .NET setup".

This skill checks prerequisites for building Dapr Workflow apps with .NET Aspire. Use this skill when the user asks to "check prerequisites for Aspire", "verify Aspire environment", or "check Aspire setup".

Automated pipeline for capturing application screenshots, compositing them into device frames, and generating animated GIFs for marketing materials and landing pages.

Deep reasoning mode. Exhaustive analysis with stress-tested assumptions. Triggers: "ultrathink", "/ultrathink", "think deeply", "подумай глубоко"

Push current branch and create a pull request. Rebase workflow, auto-PR, merge prompt after checks pass. Triggers: "push-and-pr", "/push-and-pr", "push and pr", "create pr", "сделай пр", "запушь"

Manually sync brain with remote. Exports local state, pushes to remote, pulls updates from other machines, merges, and applies.

Show brain inventory, sync status, and network info across all machines.

List all shared skills, agents, and rules in the brain network.

Share a skill, agent, or rule with the team by copying it to the shared namespace

Show brain sync and evolution history.

Join an existing brain sync network from another machine. Pulls the consolidated brain and merges with any local state.

Initialize brain sync network. Creates a Git remote for your brain and exports your current Claude Code state.

Analyze accumulated brain memory and propose promotions to CLAUDE.md, rules, or new skills. Makes your brain smarter over time.

Review and resolve unresolved brain merge conflicts.

Create or reuse Hugging Face dataset PRs for `harborframework/parity-experiments` and upload Harbor parity/oracle result folders efficiently with sparse checkout, raw git pushes, and Git LFS.

Write Harbor task verifiers using Reward Kit. Use when creating or editing a

Publish a Harbor task or dataset to the registry. Use when the user wants to upload, publish, or share tasks or datasets/benchmarks on the Harbor registry.

Create a new Harbor task for evaluating agents. Use when the user wants to

Scaffold a new Harbor benchmark adapter by running `harbor adapter init` and then guide implementation using the Adapters Agent Guide as the authoritative spec.

Generate a greeting message and write it to a file.

Write the proof file for the Harbor runtime skill injection example.

Existing task skill that should remain after job-level skill injection.