jeo

JEO — Integrated AI agent orchestration skill. Plan with ralph+plannotator, execute with team/bmad, verify browser behavior with agent-browser, apply UI feedback with agentation(annotate), auto-cleanup worktrees after completion. Supports Claude, Codex, Gemini CLI, and OpenCode. Install: ralph, omc, omx, ohmg, bmad, plannotator, agent-browser, agentation.

Quality

40%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./.agent-skills/jeo/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 is heavily tool-focused and reads like technical documentation rather than a skill selection guide. It lists many internal tool names that users wouldn't naturally reference, lacks explicit trigger guidance ('Use when...'), and fails to explain the user-facing value proposition in accessible terms.

Suggestions

Add an explicit 'Use when...' clause describing user scenarios, e.g., 'Use when coordinating multiple AI agents, managing multi-step workflows, or automating browser-based verification tasks.'

Replace tool-specific jargon with natural user language - instead of 'plan with ralph+plannotator', describe the capability like 'create and annotate execution plans for complex tasks.'

Move installation details to the skill body; the description should focus on capability matching, not setup instructions.

Dimension	Reasoning	Score
Specificity	Names domain (AI agent orchestration) and lists several actions (plan, execute, verify, apply, auto-cleanup), but the actions are described with tool names rather than concrete user-facing capabilities. 'Plan with ralph+plannotator' tells what tools are used but not what planning actually entails.	2 / 3
Completeness	Describes what it does (orchestration with various tools) but completely lacks a 'Use when...' clause or any explicit trigger guidance. The description reads more like installation documentation than skill selection guidance.	1 / 3
Trigger Term Quality	Heavy use of technical jargon and tool-specific names (ralph, plannotator, bmad, agentation, omx, ohmg) that users would not naturally say. Terms like 'orchestration', 'worktrees', and tool names are developer-internal vocabulary, not natural user language.	1 / 3
Distinctiveness Conflict Risk	The specific tool names (ralph, bmad, plannotator) create some distinctiveness, but 'AI agent orchestration' is broad and could overlap with other agent-related skills. The mention of multiple AI systems (Claude, Codex, Gemini) adds ambiguity about when to select this over other skills.	2 / 3
	Total	6 / 12 Passed

Implementation

62%

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 actionability and workflow clarity with comprehensive, executable instructions and well-defined multi-step processes with validation checkpoints. However, it suffers significantly from verbosity - the same patterns (checkpoint recording, file locking, error handling) are repeated verbatim across sections, and the document's length (~800+ lines) makes it token-inefficient. The content would benefit greatly from extracting repeated code into referenced scripts and splitting platform-specific details into separate files.

Suggestions

Extract the repeated checkpoint/error recording Python blocks into a single reusable script (e.g., `scripts/update-state.py`) and reference it instead of inlining the same 15-line block 6+ times

Move platform-specific configuration sections (4.1-4.4) to separate files like `CLAUDE.md`, `CODEX.md`, `GEMINI.md` and reference them from the main skill

Consolidate the pre-flight bash blocks - they share 80%+ identical code and could be a single parameterized script

Remove explanatory comments that describe what code does when the code is self-evident (e.g., '# Record checkpoint' before obvious checkpoint code)

Dimension	Reasoning	Score
Conciseness	The skill is extremely verbose at ~800+ lines with extensive repetition of Python/bash code blocks across sections. Many concepts are over-explained (e.g., file locking patterns repeated 6+ times, checkpoint recording duplicated in every step), and the document could be reduced by 60-70% while preserving all actionable content.	1 / 3
Actionability	The skill provides fully executable code throughout - complete bash scripts, Python one-liners, curl commands, and JSON configurations. Commands are copy-paste ready with specific paths, environment variables, and error handling included.	3 / 3
Workflow Clarity	The multi-step workflow is exceptionally clear with numbered STEPs (0-4), explicit pre-flight checks before each phase, validation checkpoints, error recovery protocols with retry counts, and clear branching logic (approved → EXECUTE, feedback → revise). The feedback loops for destructive operations are well-defined.	3 / 3
Progressive Disclosure	While the document has clear section headers and a logical structure, it's largely monolithic with inline content that could be split into separate files (e.g., platform-specific setup details, troubleshooting, the extensive pre-flight scripts). References to external files exist but the main document is overwhelming.	2 / 3
	Total	9 / 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 (1274 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.