Name: agentic-jujutsu
Rating: 59.4 (1 reviews)
Author: ruvnet

agentic-jujutsu

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

1.26x

Quality

44%

Does it follow best practices?

Impact

81%

1.26x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/agentic-jujutsu/SKILL.md

The canonical home for this skill is agentic-jujutsu in ruvnet/claude-flow

Quality

Content

46%Weight 40%Scale 1-5

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

The content is rich with executable code but is overly long, repeats information across sections, and fails to split large reference material into bundle files. Destructive operations also lack the validation checkpoints the rubric expects.

Suggestions

Split the API reference tables and use-case catalog into separate bundle files (e.g., reference/API.md, reference/USE_CASES.md) and link them one level deep from SKILL.md.

Trim redundancy by keeping either the API tables OR the code examples for each method, not both, and move the version history and performance tables to a separate doc.

Add explicit validation/verification steps (e.g., check status/diff before commits and merges, confirm deployment success before finalizing a trajectory) to satisfy feedback-loop requirements for destructive operations.

Dimension	Reasoning	Score
Conciseness	The body is noticeably verbose at ~640 lines: it repeats the API in both tables and code blocks, includes marketing-style performance tables and version history, and restates relatively basic usage patterns multiple times across Quick Start, Core Capabilities, Use Cases, and Examples.	2 / 5
Actionability	It provides extensive copy-paste-ready JavaScript examples and concrete method signatures covering the common cases, with only minor gaps such as no install/availability verification step for the npx package.	4 / 5
Workflow Clarity	Capabilities are organized into sequenced sections, but operations that are destructive or batch-oriented (commits, merges, deploys) lack explicit validation checkpoints; the rubric caps workflow clarity at 3 when such operations have no validation feedback loops.	3 / 5
Progressive Disclosure	No bundle files exist despite references like 'See package README' and 'docs/...' links, and large inline API reference tables that belong in a separate file are inlined, making this a minimally structured monolith with buried pointers.	2 / 5
	Total	11 / 20 Passed

Description

42%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description states a clear domain but relies on buzzwords and brand names instead of natural trigger terms and omits any explicit 'Use when...' guidance. It is distinguishable but not optimally scoped for triggering.

Suggestions

Add an explicit 'Use when ...' clause naming concrete triggering situations (e.g., multiple agents committing concurrently, AI-agent version-control conflicts).

Replace brand/marketing language ('Quantum-resistant', 'ReasoningBank intelligence') with concrete natural-language actions users would say.

Add natural synonyms and concrete artifacts (e.g., 'commits, branches, merges across concurrent AI agents') to improve trigger-term coverage.

Dimension	Reasoning	Score
Specificity	It names the domain ('version control for AI agents') and a couple of concrete-sounding capabilities ('self-learning', 'multi-agent coordination'), but 'ReasoningBank intelligence' is a product/brand name rather than an action and 'Quantum-resistant' is a marketing attribute, so coverage is partial rather than comprehensive.	3 / 5
Completeness	It gives a clear 'what' (version control for AI agents with named capabilities) but provides no explicit 'when' / 'Use when' trigger guidance, which per the rubric caps completeness at 3.	3 / 5
Trigger Term Quality	The phrasing leans on technical jargon and brand buzzwords ('Quantum-resistant', 'ReasoningBank intelligence', 'self-learning') rather than natural phrases a user would actually say when needing this skill; only 'version control' is a natural keyword and it lacks common synonyms.	2 / 5
Distinctiveness Conflict Risk	The 'for AI agents' framing carves out a niche but the core 'version control' and 'multi-agent coordination' language could overlap with general dev/version-control skills, so it is somewhat distinct with residual overlap risk.	3 / 5
	Total	11 / 20 Passed

Validation

87%

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 — 14 / 16 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	14 / 16 Passed

Repository: ruvnet/ruflo
Path: .agents/skills/agentic-jujutsu/SKILL.md
Commit: fa13ee4

Reviewed: about 8 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.