Workflow Builder Agent Skill
Scaffold an explicit one-shot workflow adapter without lifecycle authority. Triggers: "build a workflow adapter", "scaffold a one-shot workflow".
Install
one command, takes just this skill from the repositorynpx skills add https://github.com/boshu2/agentops --skill workflow-builderThe instruction itself
2 sections, as written by the authorWorkflow Builder — one-shot adapter authoring
Build a thin adapter only when a caller needs to dispatch an explicit set of
independent operations. A workflow is convenience code, never a correctness or
lifecycle authority.
At-most-once dispatch over explicit inputs is the whole safety argument: a
workflow that cannot retry or select work cannot compound a failure, so the
worst case is one reported error per operation.
Named failure mode — framework gravity: a one-shot script growing config
files, plugin hooks, and a state store until it is an unrequested orchestrator.
Anti-pattern: adding retry-on-failure "just for robustness". Corrective:
report the per-operation error and stop; the caller owns whether anything runs
again.
Contract
- Inputs, executors, write scopes, and outputs are supplied explicitly.
- Each operation is dispatched at most once.
- Parallel operations must have caller-proven disjoint write scopes.
- The workflow reports per-operation output or error and then stops.
- It contains no work selection, retry, budget, queue, tracker, validation, Git,
integration, closure, release, or delivery logic.
- Optional substrate state cannot be translated into RPI or verdict state.
Prefer the smallest script supported by the target runtime. Include a dry-run or
fixture demonstrating exact dispatch count and failure reporting. Do not create a
new framework or SDK abstraction unless the caller explicitly requests one.
Other skills for the same job
different authors, same section of the catalogue
Comprehensive GitHub project management with swarm-coordinated issue tracking, project board automation, and sprint planning
Comprehensive technology-agnostic prompt for analyzing and documenting project folder structures. Auto-detects project types (.NET, Java, React, Angular, Python, Node.js, Flutter), generates detailed blueprints with visualization options, naming conventions, file placement patterns, and extension templates for maintaining consistent code organization across diverse technology stacks.
Use when complex problems require systematic step-by-step reasoning with ability to revise thoughts, branch into alternative approaches, or dynamically adjust scope. Ideal for multi-stage analysis, design planning, problem decomposition, or tasks with initially unclear scope.
Multi-agent workflow examples to work together on the OpenServ Platform. Covers agent discovery, multi-agent workspaces, task dependencies, and workflow orchestration using the Platform Client. Read reference.md for the full API reference. Read openserv-agent-sdk and openserv-client for building and running agents.
> Compress natural language memory files (CLAUDE.md, todos, preferences) into caveman format to save input tokens. Preserves all technical substance, code, URLs, and structure. Compressed version overwrites the original file. Human-readable backup saved as FILE.original.md.
API design principles and decision-making. REST vs GraphQL vs tRPC selection, response formats, versioning, pagination.
Patterns for automating GitHub workflows with AI assistance, inspired by [Gemini CLI](https://github.com/google-gemini/gemini-cli) and modern DevOps practices.
Groups existing components into logical business domains to plan service-based architecture. Use when asking "which components belong together?", "group these into services", "organize by domain", "component-to-domain mapping", or planning service extraction from an existing codebase. Do NOT use for identifying new domains from scratch (use domain-analysis) or analyzing coupling (use coupling-analysis).
How to use it
Take boshu2/workflow-builder from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.