agents-orchestrator
Orchestrates complete multi-agent development pipelines from specification to production-ready implementation. Coordinates specialist agents (PM, ArchitectUX, Developer, QA) in a structured sequence, enforcing task-by-task Dev↔QA validation loops with automatic retry logic and quality gates. Use when the user asks to run the full development pipeline, execute the end-to-end workflow, coordinate multiple agents on a project, automate build-to-QA cycles, or manage a project from spec to delivery.
93
92%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is an excellent skill description that clearly articulates what the skill does (orchestrates multi-agent development pipelines with specific agent roles and validation mechanisms) and when to use it (with five explicit trigger scenarios). The description is specific, uses natural trigger terms, and occupies a distinct niche that minimizes conflict with other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: orchestrates multi-agent pipelines, coordinates specialist agents (PM, ArchitectUX, Developer, QA), enforces task-by-task Dev↔QA validation loops, automatic retry logic, and quality gates. These are concrete, well-defined capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (orchestrates multi-agent development pipelines with specialist agents, validation loops, retry logic, quality gates) and 'when' (explicit 'Use when...' clause listing five distinct trigger scenarios). | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms: 'full development pipeline', 'end-to-end workflow', 'coordinate multiple agents', 'automate build-to-QA cycles', 'spec to delivery', 'multi-agent'. These cover a good range of how users would naturally phrase requests for this capability. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche: multi-agent orchestration with specific agent roles (PM, ArchitectUX, Developer, QA) and Dev↔QA validation loops. This is unlikely to conflict with single-purpose skills like code generation or testing alone. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured orchestration skill with excellent workflow clarity — the four-phase pipeline with explicit gates, retry logic, and error handling tables provides unambiguous guidance. Actionability is strong with concrete commands, agent selection criteria, and prompt templates. Minor conciseness improvements could be made by tightening the status template and removing the slightly redundant launch command section that restates the pipeline.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient but includes some redundancy — the launch command section restates the pipeline flow already described, and the status reporting template adds bulk. Some prompt templates could be tighter. However, it mostly avoids explaining concepts Claude already knows. | 2 / 3 |
Actionability | The skill provides concrete agent spawn instructions, specific bash verification commands, exact retry logic with pseudocode, developer agent selection criteria, and verbatim prompt templates. The guidance is specific enough to execute without ambiguity. | 3 / 3 |
Workflow Clarity | The four-phase pipeline is clearly sequenced with explicit gates at each phase boundary. The Dev-QA loop includes a well-defined retry mechanism with counter logic, clear PASS/FAIL/BLOCKED decision tree, and validation checkpoints. Error recovery feedback loops are explicit throughout. | 3 / 3 |
Progressive Disclosure | The skill provides a clear overview of all four phases inline (appropriate for a pipeline orchestration skill) while deferring the full agent catalog to `project-docs/AGENTS.md` and templates to `project-docs/TEMPLATES.md`. References are one level deep and clearly signaled at the end. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- OpenRoster-ai/awesome-agents
- Commit
010799b
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.