bmad-orchestrator

Orchestrates BMAD workflows for structured AI-driven development. Routes work across Analysis, Planning, Solutioning, and Implementation phases with TEA (Task-Execute-Architect) cycles for structured execution.

Quality

32%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./.agent-skills/bmad-orchestrator/SKILL.md

Quality

Discovery

17%

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 description relies heavily on proprietary jargon (BMAD, TEA) without explaining what these mean or when a user would need them. It lacks natural trigger terms users would actually say and completely omits explicit guidance on when Claude should select this skill. The abstract phase names don't translate to concrete actions users can understand.

Suggestions

Add a 'Use when...' clause with natural trigger terms like 'project planning', 'development workflow', 'structured development process', or 'phased implementation'

Replace or supplement jargon (BMAD, TEA) with plain-language descriptions of what users actually get, e.g., 'breaks down complex projects into analysis, planning, and implementation steps'

Include concrete actions users would request, such as 'create project plans', 'define architecture', 'track development phases'

Dimension	Reasoning	Score
Specificity	Names the domain (BMAD workflows, AI-driven development) and mentions phases (Analysis, Planning, Solutioning, Implementation) and TEA cycles, but these are abstract concepts rather than concrete user-facing actions like 'create', 'analyze', or 'generate'.	2 / 3
Completeness	Describes what it does (orchestrates workflows, routes work across phases) but completely lacks a 'Use when...' clause or any explicit trigger guidance. The 'when' is entirely missing.	1 / 3
Trigger Term Quality	Uses technical jargon ('BMAD', 'TEA cycles', 'Solutioning') that users would not naturally say. No common user-facing keywords are included - a user would likely say 'plan my project' or 'help me develop' rather than 'orchestrate BMAD workflows'.	1 / 3
Distinctiveness Conflict Risk	The BMAD acronym and TEA cycles are distinctive terminology that would reduce conflicts, but 'AI-driven development' and 'structured execution' are generic enough to potentially overlap with other development or planning skills.	2 / 3
	Total	6 / 12 Passed

Implementation

47%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This skill excels at workflow clarity with explicit TEA cycles, validation checkpoints, and clear phase transitions, but suffers from severe verbosity. The content explains concepts Claude already understands (what phases are, how workflows work) rather than providing lean, actionable instructions. The monolithic structure with inline schemas, patterns, and extensive tables would benefit from progressive disclosure to separate reference files.

Suggestions

Reduce content by 60-70% by removing explanatory text about what BMAD/SSD/TEA are and focusing only on commands and their usage

Move the detailed TEA per-phase mapping tables, fabric pattern code, and JSON schema to separate reference files (e.g., TEA-PHASES.md, FABRIC-PATTERNS.md, STATE-SCHEMA.md)

Replace the verbose 'SSD vs Standard BMAD' comparison table with a single sentence noting SSD adds TEA cycles

Convert the lengthy ASCII flow diagram to a simple numbered list of steps with validation checkpoints

Dimension	Reasoning	Score
Conciseness	Extremely verbose at 400+ lines with extensive tables, diagrams, and explanations that Claude doesn't need. Explains concepts like TEA cycles, SSD vs Standard BMAD comparisons, and workflow concepts in excessive detail rather than providing lean, actionable instructions.	1 / 3
Actionability	Contains concrete commands and some executable code (bash scripts, fabric patterns), but much of the content is conceptual explanation rather than copy-paste ready instructions. The fabric pattern installation is executable, but many commands like `/ssd-cycle` are described rather than implemented.	2 / 3
Workflow Clarity	Excellent workflow clarity with explicit TEA cycle sequences, validation checkpoints (PASS/FAIL/REVISE verdicts), clear phase transitions, and feedback loops for error recovery. The ASCII flow diagrams and per-phase mapping tables clearly show the sequence with validation gates.	3 / 3
Progressive Disclosure	Content is structured with clear sections and tables, but the skill is monolithic with no references to external files for detailed content. The 400+ line document could benefit from splitting detailed per-phase mappings, fabric patterns, and state schemas into separate reference files.	2 / 3
	Total	8 / 12 Passed

Validation

90%

Warnings & errors only

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
skill_md_line_count	SKILL.md is long (514 lines); consider splitting into references/ and linking	Warning

	Total	10 / 11 Passed

Repository: supercent-io/skills-template
Commit: c033769

Reviewed: 15 days ago

Table of Contents

Discovery Implementation Validation

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.