CtrlK
BlogDocsLog inGet started
Tessl Logo

agentic-jujutsu

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

46

1.26x
Quality

24%

Does it follow best practices?

Impact

81%

1.26x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

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

Quality

Content

42%Scale 1-3

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

This skill is highly actionable with concrete, executable code examples and a comprehensive API reference, but it is severely bloated. The same trajectory pattern (start → add → finalize → getSuggestion) is demonstrated roughly 10 times with minor variations, and marketing claims ('23x faster', 'quantum-resistant') waste tokens. The content would benefit enormously from splitting into a concise overview with references to detailed guides.

Suggestions

Reduce the body to Quick Start + Core Methods table + one Best Practices section, moving Advanced Use Cases, Troubleshooting, and detailed API tables into separate referenced files

Remove marketing language and performance comparison tables — Claude doesn't need to be sold on the tool, it needs to know how to use it

Consolidate the ~10 trajectory workflow examples into 1-2 canonical examples that cover the pattern, with a brief note about variations

Add explicit validation/verification checkpoints in the workflow (e.g., verify commit succeeded before adding to trajectory, check status after rebase)

DimensionReasoningScore

Conciseness

Extremely verbose at ~400+ lines. Includes extensive marketing language ('23x faster than Git', 'quantum-resistant'), redundant examples showing the same patterns repeatedly, performance comparison tables, version history, and status badges. Many code examples are variations of the same trajectory workflow. Claude doesn't need 4 separate 'Use Case' examples that all follow the identical start-trajectory/add/finalize pattern.

1 / 3

Actionability

The code examples are concrete, executable JavaScript with specific method calls, return types, and error handling patterns. The API reference tables clearly document methods, parameters, and return types. Code is copy-paste ready with proper imports and async/await usage.

3 / 3

Workflow Clarity

The trajectory workflow (start → operations → add → finalize) is clear and repeated many times, but there are no explicit validation checkpoints between steps. The troubleshooting section covers error cases but doesn't integrate validation into the main workflow sequences. For a tool involving version control operations, there should be explicit verification steps after commits/merges.

2 / 3

Progressive Disclosure

The skill is a monolithic wall of text with everything inline. Despite referencing external docs (VALIDATION_FIXES_v2.3.1.md, AGENTDB_GUIDE.md), the content that could be in those files is largely duplicated here. The 4 advanced use cases, full API reference tables, performance benchmarks, best practices, validation rules, troubleshooting, and examples could all be split into separate referenced files. No bundle files are provided to support the references.

1 / 3

Total

7

/

12

Passed

Description

7%Scale 1-3

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 reads like marketing copy rather than a functional skill description. It is packed with buzzwords ('quantum-resistant', 'self-learning', 'ReasoningBank intelligence') but fails to describe any concrete actions, lacks natural trigger terms users would use, and provides no guidance on when Claude should select this skill.

Suggestions

Replace buzzwords with concrete actions the skill performs, e.g., 'Manages version control branches, commits changes, resolves merge conflicts' or whatever the actual capabilities are.

Add a 'Use when...' clause with natural trigger terms users would say, such as 'Use when the user asks about version control, git operations, branching, or committing code changes.'

Remove or minimize jargon like 'quantum-resistant' and 'ReasoningBank intelligence' unless these map to specific, describable features that differentiate this skill from standard version control tools.

DimensionReasoningScore

Specificity

The description uses buzzwords like 'quantum-resistant', 'self-learning', and 'ReasoningBank intelligence' without describing any concrete actions. There are no specific capabilities listed—just abstract, marketing-style language.

1 / 3

Completeness

The description fails to clearly answer 'what does this do' in concrete terms and completely lacks any 'when should Claude use it' guidance. There is no 'Use when...' clause or equivalent trigger guidance.

1 / 3

Trigger Term Quality

The terms used ('quantum-resistant', 'ReasoningBank intelligence', 'multi-agent coordination') are highly technical jargon that no user would naturally say when needing version control help. Common terms like 'git', 'commit', 'branch', 'merge' are entirely absent.

1 / 3

Distinctiveness Conflict Risk

The buzzword-heavy language is unusual enough that it's unlikely to conflict with other skills, but the mention of 'version control' is generic enough to potentially overlap with standard git/VCS skills without clear differentiation of actual functionality.

2 / 3

Total

5

/

12

Passed

Validation

81%

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

Validation9 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

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

9

/

11

Passed

Repository
ruvnet/claude-flow
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.