18 skills found
openclaw / taskflowCoordinate multi-step detached tasks as one durable TaskFlow job with owner context, state, waits, and child tasks.
openclaw / browser-automationUse when controlling web pages with the OpenClaw browser tool, especially multi-step flows, login checks, tab management, or recovery from stale refs/timeouts.
openclaw / lobsterLobster executes multi-step workflows with approval checkpoints. Use it when: - User wants a repeatable automation (triage, monitor, sync) - Actions need human approval before executing (send, post, delete) - Multiple tool calls should run as one deterministic operation | User intent | Use Lobster?
SolaceLabs / solace-agent-meshAn event-driven framework designed to build and orchestrate multi-agent AI systems. It enables seamless integration of AI agents with real-world data sources and systems, facilitating complex, multi-step workflows.
0xSteph / pentest-aiOffensive-security MCP server with 205 wrapped tools, 17 specialist agents, and 60 SPA-aware probes for OWASP Top 10. CLI + MCP, BYO LLM. No API key needed on MCP path.
sbhooley / ainativelangAINL helps turn AI from "a smart conversation" into "a structured worker." It is designed for teams building AI workflows that need multiple steps, state and memory, tool use, repeatable execution, validation and control, and lower dependence on long prompt loops.
microsoft / DebugMCPGift your VS Code agent a real debugger: breakpoints, stepping, inspection.
Hainrixz / the-architectA Claude Code plugin that interviews you, designs the whole architecture, and writes a self-contained blueprint another Claude Code instance builds from with zero context — EARS acceptance criteria and a runnable verify command on every build step. 14 project shapes, greenfield and brownfield.
KbWen / agentic-osGovernance framework for AI coding agents. It runs them through a five-step workflow (plan, build, review, test, ship) where no step counts as done without evidence. Drop-in rules and guardrails for Claude Code, Codex, Cursor, Copilot, and Antigravity, via AGENTS.md.
Alorse / cc-compatible-modelsComplete guide for using alternative AI models with Claude Code — including DeepSeek, Qwen, MiniMax, Kimi, GLM, MiMo, StepFun, and more. Pricing, configs, and coding plans.
StephanSchmidt / loupeOpen-source CLI that measures AI coding-assistant impact (Claude Code, Copilot, Cursor, Aider) across Bitbucket+Jira, GitHub, GitLab, Azure DevOps, or Linear — and renders a reveal.js exec deck. Runs locally, no SaaS, no data leaves your environment.
nikkoxgonzales / crash-mcpMCP server for structured and efficient reasoning with step validation, branching, and revisions.
zakirkun / guardian-cliGuardian is a production-ready AI-powered penetration testing automation CLI tool that leverages Google Gemini and LangChain to orchestrate intelligent, step-by-step penetration testing workflows while maintaining ethical hacking standards.
antosubash / ciRun all CI checks locally, mirroring the GitHub Actions CI pipeline. This catches issues before creating a PR. Execute these steps in order, stopping on first failure. Report results as a summary table at the end. Run `npm run check` from the project root.
benjam3n / deExtract dependencies between steps, tasks, or items. Identifies what must happen before what, enabling proper sequencing. Read and execute `/home/ben/Documents/projects/reasoningtool/claude-code-plugin/skills/de/SKILL.md`, applying it to this input: $ARGUMENTS
benjam3n / opDetermine the correct execution order for a set of steps based on dependencies and constraints. Read and execute `/home/ben/Documents/projects/reasoningtool/claude-code-plugin/skills/op/SKILL.md`, applying it to this input: $ARGUMENTS
juzser / add-block-actionAdd a new block action handler for the Slack poll bot. The user will describe what the new action should do. Use $ARGUMENTS as the description. Steps: 1. Read `src/index.ts` to understand the existing `handleBlockAction()` function and how actions are routed by `action.action_id`. 2.
SassaGold / rollout-vegvisirExecute the Vegvísir rollout. Everything is pre-staged and verified (349 tests pass on the branch); your job is to ship it in order, verifying each step before the next. Report progress as you go. If any step fails, stop and explain — do not improvise around failures.
