agentic-jujutsu

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

2.62x

Quality

57%

Does it follow best practices?

Impact

84%

2.62x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

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

Quality

Content

65%

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

The content is highly actionable with concrete code and a thorough API reference, but it is verbose and monolithic: marketing padding and a large inline API section inflate the token budget and there is no progressive disclosure into bundle files. Workflow clarity is adequate but lacks explicit validation checkpoints for risky operations.

Suggestions

Move the full API reference tables into a separate REFERENCES.md and keep SKILL.md to a concise quick start, linking out for details.

Cut marketing claims, emoji bullets, the performance table, and version history that don't add actionable guidance.

Add explicit validate-then-proceed checkpoints for destructive operations (commits, rebases, merges), e.g. verify status before committing and re-check after.

Dimension	Reasoning	Score
Conciseness	The body is largely efficient and contains real API detail, but it is heavily padded with marketing claims ('23x faster than Git', '87% success rate'), emoji decoration, a performance table, version history, and redundant API listings repeated across 'Core Capabilities', 'API Reference', and 'Examples', so it could be tightened rather than being fully lean.	2 / 3
Actionability	It provides numerous concrete, executable JavaScript examples with real method calls and return values, plus API reference tables with types — copy-paste ready guidance rather than pseudocode.	3 / 3
Workflow Clarity	Multi-step processes (start trajectory → execute → addToTrajectory → finalize) are shown and some error handling exists, but there are no explicit validation checkpoints or feedback loops for destructive/batch version-control operations, which caps workflow clarity at 2.	2 / 3
Progressive Disclosure	The body has clear section structure but is monolithic — a large inline API reference and extensive examples all live in SKILL.md with no bundle reference files present, and external doc links are not clearly signaled as progressive-disclosure references.	2 / 3
	Total	9 / 12 Passed

Description

50%

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 identifies a coherent niche and names several capabilities, but it is padded with buzzwords, lacks natural trigger terms, and omits any explicit 'when to use' guidance. It lands at the middle level across all dimensions.

Suggestions

Add an explicit 'Use when...' clause naming natural triggers, e.g. 'Use when multiple AI agents need to edit a repo concurrently without lock conflicts.'

Replace jargon-heavy labels ('ReasoningBank intelligence', 'Quantum-resistant') with concrete actions a user performs, and include natural terms users would actually say.

Trim marketing buzzwords to sharpen distinctiveness and reduce overlap with generic version-control skills.

Dimension	Reasoning	Score
Specificity	Names the domain ('version control for AI agents') and several capabilities ('self-learning', 'ReasoningBank intelligence', 'multi-agent coordination', 'Quantum-resistant'), but these are high-level capability labels rather than concrete user-facing actions, so it is not the comprehensive list of specific actions of a 3.	2 / 3
Completeness	It states what the skill does but provides no 'Use when...' clause or equivalent explicit trigger guidance, so per the judging guidelines completeness is capped at 2 with the 'when' missing rather than explicit.	2 / 3
Trigger Term Quality	Contains some relevant terms a user might say ('version control', 'multi-agent', 'AI agents'), but leans heavily on jargon and branded terms ('Quantum-resistant', 'ReasoningBank') and omits natural variations like 'git for AI agents', leaving coverage incomplete relative to a 3.	2 / 3
Distinctiveness Conflict Risk	The self-learning multi-agent version-control niche is somewhat specific, but 'version control' and 'AI agents' are broad enough to overlap with general git/version-control skills, so it could still trigger for the wrong skill.	2 / 3
	Total	8 / 12 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 (663 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/ruvector
Path: .claude/skills/agentic-jujutsu/SKILL.md
Commit: 6a6c39e

Reviewed: about 14 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.