CtrlK
BlogDocsLog inGet started
Tessl Logo

jujutsu

**REQUIRED** - Always activate FIRST on any git/VCS operations (commit, status, branch, push, etc.), especially when HEAD is detached. If `.jj/` exists -> this is a Jujutsu (jj) repo - raw git commands can corrupt data. Essential git safety instructions inside. DO NOT IGNORE.

87

1.19x
Quality

83%

Does it follow best practices?

Impact

93%

1.19x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

77%

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

This is a strong, highly actionable skill that provides excellent agent-specific guidance for working with Jujutsu. Its greatest strengths are the concrete, executable commands with consistent --no-pager flags, clear warnings about interactive commands that would hang agents, and well-structured workflows with validation checkpoints. The main weakness is its length — at ~300 lines with no supporting bundle files, some sections (Workspaces, detailed Git integration) could be extracted into separate reference files to improve token efficiency.

Suggestions

Extract the Workspaces section and detailed Git Integration into separate reference files (e.g., WORKSPACES.md, GIT_INTEGRATION.md) with brief summaries and links in the main SKILL.md

Remove the introductory sentence 'This skill helps you work with Jujutsu, a Git-compatible VCS with mutable commits and automatic rebasing' — Claude doesn't need this framing

DimensionReasoningScore

Conciseness

The skill is generally well-structured but includes some unnecessary explanations (e.g., 'This skill helps you work with Jujutsu' intro, explaining what working copy is, explaining what bookmarks are). Some sections like Workspaces go into significant detail about semantics that could be trimmed. However, most content is genuinely useful for an agent context and not padded with things Claude would already know.

2 / 3

Actionability

Nearly every section provides concrete, copy-paste-ready commands with correct flags. The skill consistently shows exact command syntax, includes agent-specific flags (--no-pager, -m), warns about interactive commands that will hang, and provides a comprehensive quick reference table. Code examples are executable and specific.

3 / 3

Workflow Clarity

The essential workflow is clearly sequenced (describe first, then code, then check status). Validation checkpoints are explicit throughout: 'Verify operations with jj st after mutations', the pre-push checklist (bookmark points to correct commit, commits are refined, user has requested push), and the commit quality review steps. The conflict resolution section provides a clear alternative to interactive tools. Feedback loops are present (e.g., fix and re-validate for conflicts).

3 / 3

Progressive Disclosure

The content is well-organized with clear sections and headers, and the quick reference table aids navigation. However, at ~300 lines this is a substantial document with no bundle files to offload detail into. The Workspaces section, Git Integration details, and some advanced topics could be split into separate reference files. For a standalone SKILL.md with no bundle, it's a reasonable monolith but could benefit from splitting.

2 / 3

Total

10

/

12

Passed

Description

89%

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 excels at trigger term coverage and completeness, clearly communicating when it should activate (git/VCS operations in Jujutsu repos) with strong urgency markers. Its main weakness is that it focuses heavily on when to activate and what to avoid, but doesn't clearly articulate the concrete actions the skill performs beyond providing 'safety instructions.' The imperative/instructional tone ('DO NOT IGNORE', 'REQUIRED') is unusual but functional for a safety-critical skill.

Suggestions

Add specific concrete actions the skill performs, e.g., 'Translates git commands to jj equivalents, prevents raw git usage in Jujutsu repos, provides safe VCS workflows.'

DimensionReasoningScore

Specificity

It names the domain (git/VCS operations) and mentions specific operations (commit, status, branch, push), but doesn't describe concrete actions the skill performs beyond 'safety instructions.' It tells you what triggers it but not what it actually does beyond preventing corruption.

2 / 3

Completeness

Clearly answers both 'what' (safety instructions for Jujutsu repos to prevent git corruption) and 'when' (any git/VCS operations, especially when HEAD is detached or .jj/ exists). The 'Always activate FIRST' and explicit trigger conditions serve as strong 'when' guidance.

3 / 3

Trigger Term Quality

Excellent coverage of natural trigger terms: 'git', 'VCS', 'commit', 'status', 'branch', 'push', 'HEAD', 'detached', '.jj/', 'Jujutsu', 'jj'. These are terms users would naturally use when working with version control.

3 / 3

Distinctiveness Conflict Risk

Highly distinctive with a clear niche: Jujutsu (jj) repo safety when git commands are used. The .jj/ directory check and the specific Jujutsu/jj terminology make it very unlikely to conflict with general git skills or other VCS tools.

3 / 3

Total

11

/

12

Passed

Validation

90%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

Total

10

/

11

Passed

Repository
danverbraganza/jujutsu-skill
Reviewed

Table of Contents

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.