agentic-jujutsu

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

1.15x

Quality

57%

Does it follow best practices?

Impact

88%

1.15x

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 body is highly actionable with abundant executable code, but it is verbose from heavy cross-section repetition, lacks validation feedback loops in its batch/multi-agent workflows, and is a monolithic wall of text with no progressive disclosure to bundled reference files.

Suggestions

Consolidate the repeated trajectory pattern into one canonical example and reference it from later sections instead of re-stating it in Quick Start, Core Capabilities, Use Cases, Examples, and Best Practices.

Split the full API reference tables and the advanced use cases into bundled reference files (e.g. REFERENCE.md, USE_CASES.md) with clearly signaled one-level-deep links from SKILL.md.

Add explicit validation checkpoints (e.g. verify status/diff before and after multi-agent commits, and a re-validate-on-failure loop) to the destructive batch-operation workflows.

Dimension	Reasoning	Score
Conciseness	Individual sections are reasonably efficient, but the same startTrajectory/addToTrajectory/finalizeTrajectory/getSuggestion pattern is repeated nearly verbatim across Quick Start, Core Capabilities, four Advanced Use Cases, Examples, and Best Practices, so the document as a whole is verbose and could be tightened substantially.	2 / 3
Actionability	The body is dominated by concrete, executable JavaScript with specific commands ('npx agentic-jujutsu'), exact API method names, and copy-paste-ready examples covering installation through advanced coordination.	3 / 3
Workflow Clarity	Multi-step examples are sequenced, but workflows involving batch/destructive operations (concurrent multi-agent commits, merges) include no explicit validation checkpoints or validate->fix->retry feedback loops, which the rubric caps at 2.	2 / 3
Progressive Disclosure	Sections are well organized, but this is a monolithic ~640-line document with no bundle files; the full API reference tables and all use cases are inline rather than split into one-level-deep referenced files.	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 clear niche (version control for AI agents) but is padded with buzzwords and lacks any explicit 'Use when' trigger guidance, capping most dimensions at 2. It answers 'what' partially but never 'when'.

Suggestions

Add an explicit 'Use when...' trigger clause, e.g. 'Use when multiple AI agents need to modify a repo concurrently or when coordinating multi-agent commits'.

Replace marketing buzzwords ('Quantum-resistant', 'self-learning', 'ReasoningBank intelligence') with concrete, observable actions and natural user terms.

Lead with the concrete actions the skill performs (track operations, learn patterns, suggest next steps, coordinate concurrent agents) rather than adjective-heavy feature claims.

Dimension	Reasoning	Score
Specificity	The description names the domain ('version control for AI agents') and several capabilities, but they read as properties/adjectives ('Quantum-resistant, self-learning ... with ReasoningBank intelligence and multi-agent coordination') rather than a list of concrete actions; it stops short of the comprehensive concrete-action list of a 3.	2 / 3
Completeness	It states what the skill is (version control for AI agents with listed features) but provides no 'Use when...' clause or equivalent explicit trigger guidance, so per the rubric it cannot exceed 2.	2 / 3
Trigger Term Quality	It includes some natural terms a user might say ('version control', 'AI agents'), but these are buried under marketing buzzwords ('Quantum-resistant', 'self-learning', 'ReasoningBank intelligence') that users would not naturally utter, missing common variations.	2 / 3
Distinctiveness Conflict Risk	The 'AI agents' + 'multi-agent coordination' niche is somewhat distinct from generic VCS skills, but the buzzword-laden framing blurs the trigger and it could still overlap with plain version-control skills.	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 (649 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/agentic-flow
Path: .claude/skills/agentic-jujutsu/SKILL.md
Commit: d069fff

Reviewed: about 11 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.