agentic-jujutsu

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

2.62x

Quality

51%

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

50%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 skill is highly actionable with concrete code and a thorough API reference, but it is markedly verbose due to heavy repetition of the same trajectory pattern and lacks progressive disclosure, inlining ~640 lines that should be split across reference files. Workflow guidance omits explicit validation checkpoints for destructive VCS operations.

Suggestions

Consolidate the repeated startTrajectory/addToTrajectory/finalizeTrajectory/getSuggestion pattern into one canonical example and reference it from later sections instead of restating it six times.

Split the API reference, performance characteristics, and advanced examples into separate files under references/ and link to them from a concise overview, since no bundle files currently exist.

Add an explicit validate -> fix -> retry workflow (e.g. validate state before merge, on failure inspect diff and retry) for destructive operations like rebase and merge.

Dimension	Reasoning	Score
Conciseness	The body runs ~640 lines and repeats the same startTrajectory/addToTrajectory/finalizeTrajectory/getSuggestion pattern across Quick Start, six Core Capabilities, four Advanced Use Cases, two Examples, and four Best Practices sections, which is noticeably verbose padding rather than lean reference material.	2 / 5
Actionability	It provides extensive executable JavaScript code and complete API reference tables with method signatures and return types, but several Advanced Use Case examples call undefined placeholder helpers (executeOperation, executeTask, verifyDeployment, agent.analyze), leaving minor gaps.	4 / 5
Workflow Clarity	Capabilities and use cases are presented as numbered scenarios with internal sequences, but there is no explicit validate -> fix -> retry checkpoint flow for the destructive version-control operations (commits, rebases, merges); per the scoring notes, missing validation in destructive/batch operations caps workflow clarity at 3.	3 / 5
Progressive Disclosure	The body has clear section headers and lists related docs, but all API reference, performance tables, advanced use cases, and examples are inlined into a single ~640-line file rather than split into separate bundle files, and the referenced docs (docs/VALIDATION_FIXES_v2.3.1.md, docs/AGENTDB_GUIDE.md) are not present in any bundle directory.	3 / 5
	Total	12 / 20 Passed

Description

53%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 names a clear domain and several distinctive features but lacks action verbs and any 'Use when...' trigger guidance, capping both completeness and trigger coverage. It is reasonably distinct but reads more as a feature list than a usage-oriented description.

Suggestions

Add an explicit 'Use when...' clause naming concrete trigger phrases (e.g. 'Use when multiple AI agents need to commit, branch, or merge code concurrently without lock conflicts').

Replace adjectival feature labels with concrete actions a user would request (e.g. 'commit, branch, rebase, and merge changes across concurrent agents').

Include natural synonyms and tool names users actually say (git, jj, commits, branches, conflicts) to improve trigger-term coverage.

Dimension	Reasoning	Score
Specificity	The description names the domain ("version control for AI agents") and several concrete capabilities ("Quantum-resistant", "self-learning", "ReasoningBank intelligence", "multi-agent coordination"), but these are adjectival features rather than concrete action verbs like commit/branch/merge, so it sits at the 'names domain and 1-2 concrete actions' level rather than listing several specific actions.	3 / 5
Completeness	It clearly states what the skill is ("self-learning version control for AI agents with ReasoningBank intelligence and multi-agent coordination") but contains no 'Use when...' clause or equivalent explicit trigger guidance, so completeness is capped at 3 per the judging guidelines.	3 / 5
Trigger Term Quality	It includes some natural terms a user might say ("version control", "AI agents", "multi-agent coordination") but misses common variations and synonyms users actually use such as git, jj, commits, branches, merges, or conflicts.	3 / 5
Distinctiveness Conflict Risk	The niche is fairly specific (AI-agent version control with a named ReasoningBank component) and unlikely to trigger for unrelated skills, though the bare term 'version control' carries minor overlap risk with generic VCS skills, placing it just below the distinct-niche anchor.	4 / 5
	Total	13 / 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 (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: 14db7a3

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.