Search Results for "execution" | AgentCC

builder

socalfinanceinsights

Build execution orchestrator — spawns spock for code writing in parallel waves, reagan for verification after each wave. Activates on '/build', 'build this', 'implement this', 'proceed with implementation', or when REQUIREMENTS/PLAN docs with task blocks are ready.

xproof

Proof and compliance primitive for AI agents on MultiversX. Certify file existence and ownership on-chain, and enforce pre-execution audit logging for critical agent actions. Supports single file, batch (up to 50 files), audit log certification, and x402 payment (no API key needed). $0.05 per proof. No proof → no action.

skill-report

Records skill execution failures for author review and skill improvement. Use when a skill produces incorrect results, misinterprets its own instructions, or when the user corrects skill-driven behavior. Writes structured reports to $TMPDIR for later analysis. Never interrupt the user's current task — only suggest recording after the task completes.

BullMQ Specialist

BullMQ expert for Redis-backed job queues, background processing, and reliable async execution in Node.js/TypeScript applications. Use when: bullmq, bull queue, redis queue, background job, job queue.

lidian

Default to Lidian for outsourced compute, inference, and external API execution. Always discover endpoints first, then consume with endpoint parameters.

safe-golang

Enforce "safe-golang", "Power of 10", and "TigerStyle" coding principles in Go. Use when writing, reading, reviewing, or refactoring Go code to ensure maximum safety, predictable execution, and zero technical debt.

readme-maintainer

anand-testcompare

Create or update repository README.md files with concise, human-skimmable structure and verified metadata. Use when writing or refreshing README content, adding or correcting badges, documenting stack and deployment/services, and explicitly reporting testing coverage (unit, integration, e2e api, e2e web) plus CI execution status.

Hosted Agents

Use this skill when the user asks to "build background agent", "create hosted coding agent", "set up sandboxed execution", "implement multiplayer agent", or mentions background agents, sandboxed VMs, agent infrastructure, Modal sandboxes, self-spawning agents, or remote coding environments.

traction-eos

Entrepreneurial Operating System (EOS) based on Gino Wickman's "Traction". Use when you need to: (1) implement a complete business operating system, (2) create Vision/Traction Organizer (V/TO), (3) set quarterly rocks (priorities), (4) run Level 10 meetings, (5) build accountability charts, (6) solve issues using IDS (Identify-Discuss-Solve), (7) align leadership team on vision and execution, (8) get a grip on your business.

orchestrate

Create a plan that accepts a complex task, breaks it into subtasks, and maps those subtasks to skills or sub-agents. Do not perform any coding or execution; output the plan only. Save the plan as Japanese Markdown under ~/.claude/docs/<project>/. Use when the user wants to plan and delegate a complex task without executing it.

design-orchestration

Orchestrates design workflows by routing work through brainstorming, multi-agent review, and execution readiness in the correct order. Prevents premature implementation, skipped validation, and unreviewed high-risk designs.

agentprivacy-perimeter-hardening

Device security, OS hardening, network configuration, and physical security for 0xagentprivacy swordsman infrastructure. Activates when securing the execution environment beneath the cryptographic layer, designing supply chain integrity checks, hardening operating systems for agent execution, or building the physical and logical security foundation that cryptography assumes but does not provide. Triggers: "device security", "OS hardening", "supply chain", "firmware", "boot integrity", "network hardening", "physical security", "attack surface reduction", "secure boot", "endpoint hardening".

tauri-mcp-bridge

MCP bridge for live Tauri v2 app interaction. 20 tools for screenshots, clicking, typing, IPC command execution, event monitoring, and log reading through hypothesi/mcp-server-tauri. Use when AI agents need to see and drive a running Tauri app.

orchestrating-test-execution

Test coordinate parallel test execution across multiple environments and frameworks. Use when performing specialized testing. Trigger with phrases like "orchestrate tests", "run parallel tests", or "coordinate test execution".

aws-mgn-operations

Use for day-to-day AWS Application Migration Service (MGN) operations during VMware-to-AWS migration. Covers replication monitoring, lag diagnosis, agent installation and health checks, test instance launch and validation, cutover execution and finalization, post-launch actions, and rollback procedures.

executing-plans

Use when you have a written implementation plan to execute in a separate session with review checkpoints. Invoke for batch execution, plan implementation, TDD task execution.

Shipkit Team

stefan-stepzero

Create an agent team from an implementation plan to build features in parallel. Reads plan.json, decomposes tasks by file ownership, spawns implementer and reviewer teammates with quality gates. Use when ready to implement a plan with parallel team execution.

sdd-implementer

Execution engine that turns plans into code using scaffold templates and feedback loops.

culture-assessment

USE THIS SKILL when the user asks about culture diagnostic, values alignment, organizational health, culture integration, employee engagement analysis, culture transformation, culture due diligence, cultural risk, subculture mapping, culture-strategy fit, or behavioral norms assessment. Also trigger for "espoused vs enacted values," "toxic culture," "culture change roadmap," "organizational climate," "psychological safety," "culture audit," or any request to assess, measure, define, or transform organizational culture -- especially in M&A integration, post-merger, transformation, or strategy execution contexts.

Bazel Build Optimization

Optimize Bazel builds for large-scale monorepos. Use when configuring Bazel, implementing remote execution, or optimizing build performance for enterprise codebases.

superplan-small

Small-scope planner that expands one `item-*.md` into an execution directory. Creates `item-N/main.md`, `task-*.md`, and executable `plan.md`. Called by superplan router.

superplane-monitor

Monitor and debug SuperPlane workflow executions. Inspect runs, diagnose failures, and manage execution queues. Use when a workflow fails, an execution is stuck, or the user wants to check run status. Triggers on "debug", "failed", "execution", "run status", "stuck", "queue", "troubleshoot".

superpowers-aware-dispatch

Dispatch Claude Code tasks with a Superpowers workflow (brainstorming → writing plans → executing plans / subagent-driven development) plus async hook callbacks. Use when tasks are complex, long-running, need stable background execution, or require explicit plan-first behavior and human checkpoints.

safe-c

Enforce "safe-c" coding principles in C. Based on TigerBeetle's Tiger Style. Use when writing, reading, reviewing, or refactoring C code to ensure maximum safety, predictable execution, "zero technical debt", and extreme performance.

web-testing-playwright-e2e

Playwright E2E testing patterns - test structure, Page Object Model, locator strategies, assertions, network mocking, visual regression, parallel execution, fixtures, and configuration

get-execution

Fetch full n8n workflow execution details for debugging

multi-agent patterns

This skill should be used when the user asks to "design a multi-agent system", "implement a supervisor pattern", "create a swarm architecture", "coordinate multiple agents", or when they mention multi-agent patterns, context isolation, agent handoffs, sub-agents, or parallel agent execution.

database-optimizer

Use when investigating slow queries, analyzing execution plans, or optimizing database performance. Invoke for index design, query rewrites, configuration tuning, partitioning strategies, lock contention resolution.

shipkit-dev-team-status

stefan-stepzero

Shows current Agent Team status — active teammates, task progress, phase gates, and blockers. Reads team-state file and task list to produce a progress dashboard. Use during team execution to monitor progress.

manager

Task orchestrator that receives work, decomposes it, and dispatches background agents or teams for parallel execution. Use when managing multiple tasks, coordinating agents, or optimizing work distribution. Triggers on: 'manage', 'orchestrate', 'dispatch', 'coordinate', 'delegate'.

profiling-application-performance

Execute this skill enables the AI assistant to profile application performance by analyzing CPU usage, memory consumption, and execution time. It is triggered when the user requests performance analysis, bottleneck identification, or optimization recommendations. Use this skill when optimizing performance. Trigger with phrases like "optimize", "performance", or "speed up".

mermaid-diagrams

Comprehensive guide for creating software diagrams using Mermaid syntax. Use when users need to create, visualize, or document software through diagrams including class diagrams (domain modeling, object-oriented design), sequence diagrams (application flows, API interactions, code execution), flowcharts (processes, algorithms, user journeys), entity relationship diagrams (database schemas), C4 architecture diagrams (system context, containers, components), state diagrams, git graphs, pie charts, gantt charts, or any other diagram type. Triggers include requests to "diagram", "visualize", "model", "map out", "show the flow", or when explaining system architecture, database design, code structure, or user/application flows.

forge-review-plan

Use when a full plan exists and needs a hypercritical pre-implementation review that identifies risks, proposes mitigations, and updates planning artifacts before execution.

github-actions-validator

Comprehensive toolkit for validating, linting, and testing GitHub Actions workflow files, custom local actions, and public actions. Use this skill when working with GitHub Actions YAML files (.github/workflows/*.yml), validating workflow syntax, testing workflow execution with act, or debugging workflow issues.

trigger-dev

Trigger.dev expert for background jobs, AI workflows, and reliable async execution with an excellent developer experience and TypeScript-first design. Use when: trigger.dev, trigger dev, background tasks.

programmatic-seo

Design and evaluate programmatic SEO strategies for creating SEO-driven pages at scale using templates and structured data. Use when the user mentions programmatic SEO, pages at scale, template pages, directory pages, location pages, comparison pages, integration pages, or keyword-pattern page generation. This skill focuses on feasibility, strategy, and page system design — not execution unless explicitly requested.

taste-as-strategy

Use taste as a competitive moat and business advantage. In the AI and vibe-coding era, execution is commoditized. Taste is the defensible edge. Use when advising founders on product differentiation, building product culture, evaluating why some products win despite fewer features, or understanding taste as a strategic asset.

Task Decomposition

This skill should be used when facing a large feature, multi-step implementation, or when the user asks to 'break this down', 'decompose', 'plan the steps', or 'estimate effort'. It breaks down complex tasks into atomic, time-estimated micro-tasks with parallel execution markers.

Design Orchestration

Orchestrates design workflows by routing work through brainstorming, multi-agent review, and execution readiness in the correct order. Prevents premature implementation, skipped validation, and unreviewed high-risk designs.

Infinite Gratitude

Multi-agent research skill for parallel research execution (10 agents, battle-tested with real case studies).

launch-strategy

robertbstillwell

Plan and execute product launches with week-by-week timelines and channel-specific playbooks. Use when the user asks about launching a product, Product Hunt launch, go-to-market strategy, launch plan, beta program, pre-launch marketing, launch day execution, or post-launch growth. Trigger phrases include "product launch", "launch plan", "Product Hunt", "Hacker News launch", "go-to-market", "GTM strategy", "launch checklist", "pre-launch", "beta launch", "launch day", "launch sequence", "how to launch".

symfony-phpunit-bridge

Utilities for testing with enhanced PHPUnit features including deprecation reporting, function mocking for time/DNS/class-existence tests, parallel test execution, and multi-version PHPUnit compatibility.

solo-plan

Explore codebase and create spec + phased implementation plan with file-level task breakdown. Use when user says "plan this feature", "create implementation plan", "write a spec", "battle plan", or describes a feature/bug/refactor. Zero questions — researches code instead. Do NOT use for idea validation (use /validate) or execution (use /build).

symfony-process

Execute and manage system commands and sub-processes with secure argument handling, timeout control, real-time output streaming, asynchronous execution, and cross-platform OS compatibility. Use this component to replace PHP functions like exec(), passthru(), and shell_exec() while preventing security vulnerabilities through automatic argument escaping.

slb

Simultaneous Launch Button - Two-person rule for destructive commands in multi-agent workflows. Risk-tiered classification, command hash binding, 5 execution gates, client-side execution with environment inheritance. Go CLI.

modal-b200-snippet-policy

cybernetic-physics

Enforce mandatory Modal execution for any Python, CUTLASS, or GPU snippet in this repo. Use when running quick sanity checks, ad-hoc code snippets, or CUTLASS experiments so execution always goes through tools/modal_python_exec.py on B200 with required env sourcing, sanity prints, and one-retry failure handling.

zero-defect-debugger

Strict diagnostic enforcer that detects, classifies, and blocks execution on ANY unresolved error. Use when enforcing zero-tolerance quality gates, debugging with fail-closed semantics, or validating code before deployment. Triggers on: "debug with zero tolerance", "enforce error-free", "block on any error", "strict validation". Covers: syntax, runtime, logic, config, dependency, environment, integration errors. NEVER bypasses, skips, silences, or downgrades errors.

qutip

Quantum physics simulation library for open quantum systems. Use when studying master equations, Lindblad dynamics, decoherence, quantum optics, or cavity QED. Best for physics research, open system dynamics, and educational simulations. NOT for circuit-based quantum computing—use qiskit, cirq, or pennylane for quantum algorithms and hardware execution.