agents-orchestrator

Autonomous pipeline manager that orchestrates the entire development workflow. You are the leader of this process.

Quality

13%

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 ./specialized-agents-orchestrator/skills/SKILL.md

Quality

Discovery

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 is extremely vague and provides no concrete actions, no trigger terms, and no guidance on when to use the skill. It uses second-person voice ('You are the leader') which violates the third-person requirement. The description reads more like a motivational prompt than a functional skill description.

Suggestions

Replace vague language with specific concrete actions the skill performs (e.g., 'Runs CI/CD pipelines, executes test suites, manages build and deployment steps').

Add an explicit 'Use when...' clause with natural trigger terms users would say (e.g., 'Use when the user asks to run the pipeline, deploy code, execute tests, or manage the build process').

Rewrite in third person voice ('Orchestrates...', 'Manages...') instead of second person ('You are the leader') and narrow the scope to reduce conflict with other development-related skills.

Dimension	Reasoning	Score
Specificity	The description uses vague, abstract language like 'orchestrates the entire development workflow' without listing any concrete actions. No specific capabilities are mentioned.	1 / 3
Completeness	The 'what' is extremely vague ('orchestrates the entire development workflow') and there is no 'when' clause or explicit trigger guidance whatsoever.	1 / 3
Trigger Term Quality	The terms 'pipeline manager', 'orchestrates', and 'development workflow' are abstract jargon rather than natural keywords a user would say. No common user-facing trigger terms are present.	1 / 3
Distinctiveness Conflict Risk	'Entire development workflow' is extremely broad and could conflict with virtually any development-related skill. Nothing narrows the scope to a clear niche.	1 / 3
	Total	4 / 12 Passed

Implementation

27%

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

This skill is excessively verbose, spending significant tokens on personality descriptions, motivational framing, emoji decoration, and a massive inline agent catalog that should be a separate reference. While the four-phase workflow structure is reasonable and includes retry logic, the actual actionable content is diluted by templates, abstract descriptions, and content Claude already understands. The skill would benefit enormously from being cut to ~25% of its current size with the agent catalog and templates moved to separate files.

Suggestions

Move the agent catalog (~100 lines) to a separate AGENTS.md reference file and link to it, reducing the main skill by roughly a third.

Remove personality/identity sections ('Your Identity & Memory', 'Learning & Memory', 'Communication Style', 'Success Metrics') — these describe traits rather than providing actionable instructions.

Move the status report and completion summary templates to a separate TEMPLATES.md file, keeping only a brief mention with a link.

Replace the abstract decision logic markdown blocks with more concrete, executable examples showing actual file paths, actual commands, and actual content being passed between agents.

Dimension	Reasoning	Score
Conciseness	Extremely verbose at ~300+ lines. Includes extensive personality descriptions, motivational language, emoji-heavy headers, learning/memory sections Claude doesn't need, and a massive agent catalog that belongs in a separate reference file. Much of the content describes abstract concepts ('You remember pipeline patterns, bottlenecks') rather than providing actionable instructions.	1 / 3
Actionability	Contains some concrete guidance with bash commands for file verification and specific spawn instructions with quoted text. However, much of the 'code' is pseudocode or template placeholders (e.g., '[project-name]', '[timestamp]'). The decision logic is described in markdown rather than executable form, and the actual orchestration commands are vague natural language instructions to 'spawn' agents.	2 / 3
Workflow Clarity	The four phases are clearly sequenced and the Dev-QA loop includes retry logic with limits (max 3 attempts) and escalation. However, validation checkpoints are weak — the 'verify' steps are just `ls -la` commands checking file existence rather than validating content quality. The feedback loop between QA failure and dev retry lacks specifics on how feedback is actually passed. Error recovery procedures are described abstractly.	2 / 3
Progressive Disclosure	This is a monolithic wall of text with no references to external files. The massive agent catalog (~100 lines) should be in a separate reference file. Status report templates, completion summary templates, and error handling procedures could all be split out. Everything is inlined in a single enormous document with no navigation structure beyond emoji-decorated headers.	1 / 3
	Total	6 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	10 / 11 Passed

Repository: OpenRoster-ai/awesome-openroster
Commit: 09aef5d

Reviewed: 1 day 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.