agentic-jujutsu

Quantum-resistant, self-learning version control for AI agents with ReasoningBank intelligence and multi-agent coordination

1.26x

Quality

21%

Does it follow best practices?

Impact

81%

1.26x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./.agents/skills/agentic-jujutsu/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 almost entirely composed of buzzwords and marketing-style language with no concrete actions, no trigger guidance, and no practical information for Claude to determine when to use this skill. It fails to communicate what the skill actually does in actionable terms. The only slightly redeeming quality is that its unusual jargon makes it unlikely to be confused with other skills, though this is not a meaningful advantage.

Suggestions

Replace buzzwords with concrete actions: describe specific operations the skill performs (e.g., 'Tracks file changes, manages branches, resolves merge conflicts').

Add an explicit 'Use when...' clause with natural trigger terms users would actually say (e.g., 'Use when the user asks about version control, git commits, branching, or tracking code changes').

Remove marketing language like 'quantum-resistant' and 'self-learning' that provides no useful selection signal, and instead describe the actual capabilities and scope.

Dimension	Reasoning	Score
Specificity	The description uses buzzwords like 'quantum-resistant', 'self-learning', and 'ReasoningBank intelligence' without describing any concrete actions. There are no specific capabilities listed—no verbs describing what the skill actually does.	1 / 3
Completeness	The description vaguely hints at 'what' (version control) but provides no 'when' clause or explicit trigger guidance. Both dimensions are extremely weak, with no actionable information about when Claude should select this skill.	1 / 3
Trigger Term Quality	The terms used ('quantum-resistant', 'ReasoningBank intelligence', 'multi-agent coordination') are highly technical jargon that no user would naturally say when requesting help. 'Version control' is somewhat natural but buried among buzzwords.	1 / 3
Distinctiveness Conflict Risk	The highly specific (if meaningless) buzzwords like 'quantum-resistant' and 'ReasoningBank intelligence' would ironically reduce conflict with other skills since no other skill would use these terms. However, the core concept 'version control' is generic enough to overlap with git-related skills.	2 / 3
	Total	5 / 12 Passed

Implementation

35%

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

This skill reads more like a comprehensive product README or marketing document than a focused skill for Claude. It is extremely verbose with repeated demonstrations of the same trajectory pattern, marketing claims (quantum-resistant, 23x faster), and extensive inline content that should be split into referenced files. While the code examples are concrete, the sheer volume of redundant content wastes token budget significantly.

Suggestions

Reduce content by 60-70%: consolidate the 5+ trajectory workflow examples into one canonical example, remove marketing language and performance comparison tables, and move the API reference tables and advanced use cases to separate referenced files.

Remove explanatory fluff like 'When to Use This Skill' bullet points with checkmarks, version history, status badges, and performance claims—these don't help Claude execute tasks.

Integrate validation checkpoints into the main workflow (e.g., 'after finalizeTrajectory, verify with getLearningStats that the trajectory was recorded') rather than having a disconnected troubleshooting section.

Move the API reference tables, advanced use cases, and examples into separate files (e.g., API_REFERENCE.md, EXAMPLES.md) and link to them from a concise overview.

Dimension	Reasoning	Score
Conciseness	Extremely verbose at ~400+ lines. Contains extensive marketing language ('23x faster than Git', 'quantum-resistant'), redundant examples showing the same patterns repeatedly, performance comparison tables, version history, and status badges—none of which help Claude execute tasks. The same trajectory workflow is demonstrated 5+ times with minor variations.	1 / 3
Actionability	Code examples are concrete and mostly executable JavaScript with proper imports and async/await patterns. However, many examples rely on undefined helper functions (executeOperation, verifyDeployment, executeTask, agent.analyze) making them incomplete, and some use cases are more illustrative than copy-paste ready.	2 / 3
Workflow Clarity	The trajectory workflow (start → operations → addToTrajectory → finalize) is demonstrated clearly and repeatedly. However, there are no explicit validation checkpoints or error recovery loops for multi-step processes—the error handling section shows try/catch but doesn't integrate it into a validated workflow sequence. The troubleshooting section helps but is disconnected from the main workflows.	2 / 3
Progressive Disclosure	References to external docs exist (VALIDATION_FIXES, AGENTDB_GUIDE, package README) but the skill itself is monolithic with massive inline content that should be split out. The API reference tables, advanced use cases, and extensive examples could all be separate files, with the main skill providing a concise overview and links.	2 / 3
	Total	7 / 12 Passed

Validation

81%

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 — 9 / 11 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (646 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	9 / 11 Passed

Repository: ruvnet/ruflo
Commit: 0f7c750

Reviewed: 3 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.