agentic-jujutsu

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

1.26x

Quality

28%

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

Content

50%

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

This skill is highly actionable with complete, executable code examples and thorough API documentation, but it is severely bloated with marketing language, redundant examples, and promotional content that doesn't serve Claude's needs. The trajectory workflow pattern is repeated across 8+ examples with minimal variation, and the document would benefit greatly from consolidation and splitting advanced content into referenced files. The 'quantum-resistant' and performance comparison content reads as product marketing rather than operational guidance.

Suggestions

Reduce content by 60-70%: eliminate marketing language (performance comparison tables, '23x faster' claims, quantum-resistant branding), consolidate the 4+ advanced use cases into 1-2 representative examples, and remove the version history and status badges.

Move the full API reference tables, advanced use cases, and troubleshooting sections into separate referenced files (e.g., API_REFERENCE.md, ADVANCED_EXAMPLES.md, TROUBLESHOOTING.md) to improve progressive disclosure.

Add explicit validation checkpoints in multi-step workflows, e.g., verify trajectory was recorded after finalizeTrajectory, check learning stats after recording multiple trajectories before relying on suggestions.

Remove explanatory text that Claude already knows (e.g., what concurrent operations are, why lock-free is beneficial) and focus solely on the specific API patterns and constraints unique to this tool.

Dimension	Reasoning	Score
Conciseness	Extremely verbose at ~400+ lines. Contains extensive marketing language ('23x faster than Git', 'quantum-resistant'), redundant examples (4 advanced use cases that repeat the same trajectory pattern), performance comparison tables, version history, and status badges. Much of this is promotional rather than instructional. The same API patterns are demonstrated 5-6 times with minor variations. Claude doesn't need explanations of what version control is or why lock-free is beneficial.	1 / 3
Actionability	The skill provides fully executable JavaScript code examples throughout, with concrete API calls, specific method signatures, and copy-paste ready snippets. The API reference tables are complete with method signatures, descriptions, and return types. Code examples cover installation, basic usage, and advanced patterns.	3 / 3
Workflow Clarity	The trajectory workflow (start → operations → addToTrajectory → finalize) is demonstrated clearly through examples, and error handling patterns are shown. However, there are no explicit validation checkpoints between steps, no verification that trajectories were properly recorded, and the multi-step deployment/merge workflows lack explicit 'stop and verify' gates before proceeding to destructive operations.	2 / 3
Progressive Disclosure	References to external docs exist (VALIDATION_FIXES_v2.3.1.md, AGENTDB_GUIDE.md, package README.md) but no bundle files are provided to support them. The SKILL.md itself is monolithic — the 4 advanced use cases, full API reference tables, validation rules, troubleshooting, and examples could all be split into separate files. The content that is inline would benefit from being offloaded to referenced documents.	2 / 3
	Total	8 / 12 Passed

Description

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 dominated by marketing buzzwords and abstract jargon without conveying any concrete capabilities or usage triggers. It fails to tell Claude what specific actions the skill performs or when to select it. A user asking for version control help would not use terms like 'quantum-resistant' or 'ReasoningBank intelligence'.

Suggestions

Replace buzzwords with concrete actions the skill performs (e.g., 'Manages branches, commits, and merges for AI agent workflows' or similar specific operations).

Add an explicit 'Use when...' clause with natural trigger terms users would actually say, such as 'version control', 'git', 'commit', 'branch', 'merge', 'diff', or 'repository'.

Remove or minimize marketing language like 'quantum-resistant' and 'self-learning' that adds no actionable information for skill selection.

Dimension	Reasoning	Score
Specificity	The description uses abstract buzzwords like 'quantum-resistant', 'self-learning', and 'ReasoningBank intelligence' without describing any concrete actions. There are no specific operations listed (e.g., commit, branch, merge, diff).	1 / 3
Completeness	The description fails to clearly answer 'what does this do' in concrete terms and completely lacks any 'when should Claude use it' guidance. There is no 'Use when...' clause or equivalent trigger guidance.	1 / 3
Trigger Term Quality	The keywords are highly technical jargon ('quantum-resistant', 'ReasoningBank intelligence', 'multi-agent coordination') that no user would naturally say when needing version control help. 'Version control' is the only somewhat natural term, but it's buried among buzzwords.	1 / 3
Distinctiveness Conflict Risk	The heavy use of niche buzzwords like 'quantum-resistant' and 'ReasoningBank intelligence' ironically makes it unlikely to conflict with other skills, but the core concept of 'version control' is generic enough to potentially overlap with standard git/VCS skills.	2 / 3
	Total	5 / 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: 28c81c0

Reviewed: about 19 hours 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.